Papers by Yan Song

Improving Chinese Word Segmentation with Wordhood Memory Networks (2020.acl-main)

Challenge:	Existing studies focus on introducing salient word information to general text summarization framework to guide selection of key content in radiology findings.
Approach:	They propose a method for automatic impression generation using word graphs and a Word Graph guided Summarization model to capture critical words and their relations.
Outcome:	The proposed method is validated on two datasets, OPENI and MIMIC-CXR.

Copied to clipboard

Yuanhe Tian, Yan Song, Fei Xia, Tong Zhang, Yonggang Wang

PhysicsArena: The First Multimodal Physics Reasoning Benchmark Exploring Variable, Process, and Solution Dimensions (2025.findings-emnlp)

Challenge:	Contextual features are important in Chinese word segmentation (CWS) but it is difficult to integrate wordhood information into existing neural models.
Approach:	They propose a neural framework that integrates contextual wordhood information with several popular encoder-decoder combinations for Chinese word segmentation.
Outcome:	The proposed framework achieves state-of-the-art performance on five benchmark datasets.

Copied to clipboard

Song Dai, Yibo Yan, Jiamin Su, Zihao Dongfang, Yubo Gao, Yonghua Hei, Jungang Li, Junyan Zhang, Sicheng Tao, Zhuoran Gao, Xuming Hu

Reasoning

Challenge:	Current physics benchmarks focus on text-only inputs or only on problem-solving . current physics reasoning benchmarks neglect critical intermediate steps of variable identification and process formulation.
Approach:	a new benchmark evaluates multimodal large language models in physics reasoning . the benchmark measures variables, process formulations, and solution derivation .
Outcome:	PhysicsArena is the first multimodal physics reasoning benchmark . it evaluates MLLMs across three critical dimensions: variable identification, process formulation, and solution derivation.

Aspect-based Sentiment Analysis with Type-aware Graph Convolutional Networks and Layer Ensemble (2021.naacl-main)

Copied to clipboard

Yuanhe Tian, Guimin Chen, Yan Song

Enhancing Structure-aware Encoder with Extremely Limited Data for Graph-based Dependency Parsing (2022.coling-1)

Challenge:	Existing studies only leverage dependency relations without considering their dependency types . a valid and effective approach is demonstrated on six English benchmark datasets .
Approach:	They propose to explicitly utilize dependency types for ABSA with type-aware graph convolutional networks . attention is used in T-GCN to distinguish different edges in the graph and attentive layer ensemble to comprehensively learn from different layers of T-gCN.
Outcome:	The proposed approach performs well on six English benchmark datasets.

Copied to clipboard

Enhancing Aspect-level Sentiment Analysis with Word Dependencies (2021.eacl-main)

Challenge:	Dependency parsing is an important natural language processing task which analyzes the syntactic structure of an input sentence.
Approach:	They propose a structure-aware encoder pre-trained on auto-parsed data to improve dependency parsing . they propose combining gold dependency trees with existing parsers to improve parser performance .
Outcome:	The proposed approach outperforms baselines under different parsers and dependency standards under different parameters and model architectures.

Copied to clipboard

Yuanhe Tian, Guimin Chen, Yan Song

ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations (2020.findings-emnlp)

Challenge:	Existing approaches to enhance aspect-level sentiment analysis have omitted syntactic information . experimental results show that our approach outperforms baseline models on all datasets .
Approach:	They propose to leverage word dependencies to enhance aspect-level sentiment analysis . they propose to use key-value memory networks to leverage different dependency results .
Outcome:	The proposed approach outperforms baseline models on all datasets and achieves state-of-the-art performance on three of them.

Copied to clipboard

Shizhe Diao, Jiaxin Bai, Yan Song, Tong Zhang, Yonggang Wang

Chinese Couplet Generation with Syntactic Information (2022.coling-1)

Challenge:	Experimental results show that pre-trained text encoders can perform many NLP tasks with less resource.
Approach:	They propose a BERT-based Chinese text encoder enhanced by n-gram representations . they show reasonable performance when ZEN is trained on a small corpus .
Outcome:	The proposed encoder incorporates the comprehensive information of both the character sequence and words or phrases it contains.

Copied to clipboard

Yan Song

Improving Image Captioning via Predicting Structured Concepts (2023.emnlp-main)

Challenge:	Chinese couplet generation aims to generate a pair of clauses with certain rules adhered . previous studies have focused on learning the correspondences between antecedent and subsequent clauses .
Approach:	They propose to leverage syntactic information to generate Chinese couplets by POS tags and word dependencies.
Outcome:	The proposed approach outperforms baselines on a Chinese couplet generation dataset.

Copied to clipboard

Ting Wang, Weidong Chen, Yuanhe Tian, Yan Song, Zhendong Mao

hyperdoc2vec: Distributed Representations of Hypertext Documents (P18-1)

Challenge:	Existing studies on image captioning ignore the relationship between concepts . current methods for image caption generation ignore this relationship .
Approach:	They propose a structured concept predictor to predict concepts and their structures . they integrate these predictions into captioning to enhance visual signals .
Outcome:	The proposed approach improves image captioning performance by using semantic concepts as a bridge between images and texts.

Copied to clipboard

Jialong Han, Yan Song, Wayne Xin Zhao, Shuming Shi, Haisong Zhang

Representation Learning

Challenge:	Conventional text embedding methods suffer from information loss if directly adapted to hyper-documents.
Approach:	They propose an embedding approach for hyper-documents that incorporates four criteria to preserve necessary information for embeddable models.
Outcome:	The proposed model outperforms several existing models on two tasks in the academic domain.

The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agents (2025.emnlp-main)

Copied to clipboard

Yuhan Liu, Zirui Song, Juntian Zhang, Xiaoqing Zhang, Xiuying Chen, Rui Yan

ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences (2024.acl-long)

Challenge:	Existing studies assume fake news is inherently existing rather than exploring its gradual formation.
Approach:	They propose a Large Language Model-based simulation approach explicitly focusing on fake news evolution from real news.
Outcome:	The proposed framework captures fake news evolution patterns and accurately reproduces known fake news, aligning closely with human evaluations.

Copied to clipboard

Yuanhe Tian, Ruyi Gan, Yan Song, Jiaxing Zhang, Yongdong Zhang

LoopCoder: Scaling Code Intelligence via Looped Language Models (2026.findings-acl)

Challenge:	Current large language models (LLMs) are ineffective in learning domain knowledge and aligning with human preference.
Approach:	They propose a benchmark LLM for Chinese medical domain that uses pre-training, supervised fine-tuning and RLHF to train LLMs.
Outcome:	The proposed LLM performs better than existing LLMs in the Chinese medical domain.

Copied to clipboard

Jian Yang, Wei Zhang, Shuyue Guo, Yizhi LI, Linzheng Chai, Zhengmao Ye, Shukai Liu, Yuyang Song, Jiajun Wu, Che Liu, Tianyu Zheng, Siwei Wu, Leo L, Xudong Ma, Chuan Hao, Ran Tao, Yan Xing, Jianzhou Wang, Mingjie Tang, Aishan Liu, Zhoujun Li, Xianglong Liu, Weifeng Lv, Bryan Dai

Automatic Data Visualization Generation from Chinese Natural Language Questions (2024.lrec-main)

Challenge:	Large language models have mastered syntax-level code generation, but complex algorithmic reasoning remains a challenge.
Approach:	They propose a recurrent inductive bias that aligns with the recursive nature of programming logic.
Outcome:	The proposed model achieves comparable performance to standard dense models with more parameters.

Copied to clipboard

Yan Ge, Victor Junqiu Wei, Yuanfeng Song, Jason Chen Zhang, Raymond Chi-Wing Wong

Challenge:	Existing studies on data visualization generation from natural languages have not been conducted on Chinese Text-to-Vis.
Approach:	They propose to generate a Chinese text-to-vis dataset using a multilingual encoder and a cross-lingual ability.
Outcome:	The proposed dataset is challenging and deserves further research.

Towards the Law of Capacity Gap in Distilling Language Models (2025.acl-long)

Copied to clipboard

Chen Zhang, Qiuchi Li, Dawei Song, Zheyu Ye, Yan Gao, Yao Hu

Better Explain Transformers by Illuminating Important Information (2024.findings-eacl)

Challenge:	Language model (LM) distillation aims at distilling knowledge in a large teacher LM to a small student one.
Approach:	They propose to use the law of capacity gap to distill knowledge from a large teacher to a small student model.
Outcome:	The proposed model outperforms other language models on a larger scale by using the law of capacity gap inducted from a preliminary study on small-scale (3B) LMs.

Copied to clipboard

Linxin Song, Yan Cui, Ao Luo, Freddy Lecue, Irene Li

Explainability & Interpretability in NLP

Challenge:	Existing explanations focus on the input and output of the Transformers, resulting in confusing results.
Approach:	They propose to highlight important information and eliminate irrelevant information by a refined information flow on top of the layer-wise relevance propagation method.
Outcome:	The proposed method outperforms baseline models on classification and question-answering datasets with over 3% to 33% improvement on explanation metrics.

Iterative Document Representation Learning Towards Summarization with Polishing (D18-1)

Copied to clipboard

Xiuying Chen, Shen Gao, Chongyang Tao, Yan Song, Dongyan Zhao, Rui Yan

Multiplex Word Embeddings for Selectional Preference Acquisition (D19-1)

Challenge:	Existing summarization methods read through document only once to generate a document representation, resulting in a sub-optimal representation.
Approach:	They propose an iterative model for supervised extractive text summarization which polishes the document representation on many passes through the document.
Outcome:	The proposed model outperforms state-of-the-art extractive systems on CNN/DailyMail and DUC2002 datasets.

Copied to clipboard

Hongming Zhang, Jiaxin Bai, Yan Song, Kun Xu, Changlong Yu, Yangqiu Song, Wilfred Ng, Dong Yu

Representation Learning

Challenge:	Existing word embeddings are limited in their ability to represent fixed vectors . instead, they incorporate relational dependencies of different words into their embeddables - a limitation that is addressed by a multiplex model .
Approach:	They propose a word embedding model which incorporates relational dependencies of different words into their embeddables.
Outcome:	The proposed model can be easily extended according to various relations among words.

Beyond Static Testbeds: An Interaction-Centric Agent Simulation Platform for Dynamic Recommender Systems (2025.emnlp-main)

Copied to clipboard

Song Jin, Juntian Zhang, Yuhan Liu, Xun Zhang, Yufei Zhang, Guojun Yin, Fei Jiang, Wei Lin, Rui Yan

Challenge:	Existing platforms lack a mechanism for user actions to dynamically reshape the environment.
Approach:	They propose a novel agent-based simulation platform for recommender systems with a robust interaction mechanism.
Outcome:	The proposed platform improves the credibility of the simulation and replicates the Matthew Effect and Brand Loyalty.

TILGAN: Transformer-based Implicit Latent GAN for Diverse and Coherent Text Generation (2021.findings-acl)

Copied to clipboard

Shizhe Diao, Xinwei Shen, Kashun Shum, Yan Song, Tong Zhang

Group-wise Contrastive Learning for Neural Dialogue Generation (2020.findings-emnlp)

Challenge:	Existing autoregressive models suffer from the exposure bias problem due to mismatches between training and generation stages.
Approach:	They propose a Transformerbased Implicit Latent GAN which combines a transformer autoencoder and GAN in the latent space with a novel design and distribution matching based on the Kullback-Leibler divergence.
Outcome:	The proposed model improves local and global coherence and quality-diversity trade-off on three benchmark datasets.

Copied to clipboard

Hengyi Cai, Hongshen Chen, Yonghao Song, Zhuoye Ding, Yongjun Bao, Weipeng Yan, Xiaofang Zhao

Syntax-driven Approach for Semantic Role Labeling (2022.lrec-1)

Challenge:	Existing approaches to training dialogue models have low diversity in open-domain contexts . prior art suggests that naive MLE objective is not effective enough .
Approach:	They propose to incorporate contrastive learning into dialogue generation by using a pretrained baseline model as a reference.
Outcome:	The proposed framework is suited for training a wide range of dialogue generation models with favorable performance over baseline training approaches.

Copied to clipboard

Yuanhe Tian, Han Qin, Fei Xia, Yan Song

Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting (2023.findings-emnlp)

Challenge:	Existing studies focus on auto-generated syntactic knowledge to enhance semantic role labeling . experimental results show that map memories can enhance SRL .
Approach:	They propose to map memories to enhance semantic role labeling by encoding auto-generated syntactic knowledge from off-the-shelf toolkits.
Outcome:	The proposed model outperforms baselines and achieves state-of-the-art results on two English benchmark datasets.

Copied to clipboard

Haoyang Huang, Tianyi Tang, Dongdong Zhang, Xin Zhao, Ting Song, Yan Xia, Furu Wei

Text Style Transfer with Contrastive Transfer Pattern Mining (2023.acl-long)

Challenge:	Large language models (LLMs) demonstrate impressive multilingual capability, but their performance varies substantially across different languages.
Approach:	They propose a generic template prompt that stimulates cross-lingual and logical reasoning skills to enhance task performance across languages.
Outcome:	The proposed method improves multilingual capability across languages and covers high-resource and low-resourced languages.

Copied to clipboard

Jingxuan Han, Quan Wang, Licheng Zhang, Weidong Chen, Yan Song, Zhendong Mao

Text Generation

Challenge:	Existing methods for text style transfer only focus on the transformation between styles, yet they do not take into account that this transformation can be achieved via different hidden transfer patterns.
Approach:	They propose a novel approach which automatically mines hidden transfer patterns to improve TST . they use a clustering module to automatically discover hidden transfer pattern from the data .
Outcome:	The proposed method can be applied in a plug-and-play manner to enhance other methods to further improve their performance.

Combinatory Grammar Tells Underlying Relevance among Entities (2022.findings-emnlp)

Copied to clipboard

Yuanhe Tian, Yan Song

FedCoT: Federated Chain-of-Thought Distillation for Large Language Models (2025.findings-emnlp)

Challenge:	Existing approaches focus on dependencies among words while paying limited attention to other types of syntactic structure.
Approach:	They propose an alternative approach that takes advantage of combinatory categorial grammar to detect the relation between entities.
Outcome:	The proposed model performs state-of-the-art on two widely used English benchmark datasets.

Copied to clipboard

Tao Fan, Weijing Chen, Yan Kang, Guoqiang Ma, Hanlin Gu, Yuanfeng Song, Lixin Fan, Qiang Yang

Code Needs Comments: Enhancing Code LLMs with Comment Augmentation (2024.findings-acl)

Challenge:	Large Language Models (LLMs) have emerged as a transformative force in artificial intelligence, demonstrating exceptional proficiency across various tasks.
Approach:	They propose a federated framework for the Chain-of-Thought distillation of knowledge from LLMs to SLMs, while adhering to privacy requirements.
Outcome:	The proposed framework ensures secure knowledge transfer from an LLM on a high-powered server to an SLM on resource-constrained client while adhering to privacy requirements.

Copied to clipboard

Demin Song, Honglin Guo, Yunhua Zhou, Shuhao Xing, Yudong Wang, Zifan Song, Wenwei Zhang, Qipeng Guo, Hang Yan, Xipeng Qiu, Dahua Lin

Programming Languages in NLP

Challenge:	Large Language Models (LLMs) require a deep understanding of programming languages and their correlation with natural languages (NLs).
Approach:	They propose a data augmentation method that generates comments for existing code and a filtering strategy that filters out code data poorly correlated with natural language.
Outcome:	The proposed method outperforms the model trained on the augmented data and the model further trained on data without augmentation on two widely-used programming skill benchmarks.

End-to-end Aspect-based Sentiment Analysis with Combinatory Categorial Grammar (2023.findings-acl)

Copied to clipboard

Yuanhe Tian, Weidong Chen, Bo Hu, Yan Song, Fei Xia

Improving Arabic Diacritization with Regularized Decoding and Adversarial Training (2021.acl-short)

Challenge:	End-to-end aspect-based sentiment analysis (EASA) is a natural language processing task that requires a deep understanding of the running text.
Approach:	They propose a method to improve EASA with CCG supertags that carry syntactic and semantic information of the associated words.
Outcome:	The proposed approach outperforms baselines and achieves state-of-the-art results on all datasets.

Copied to clipboard

Han Qin, Guimin Chen, Yuanhe Tian, Yan Song

Improving English-Arabic Transliteration with Phonemic Memories (2022.findings-emnlp)

Challenge:	Existing studies regard auto-generated knowledge instances as gold references, which limits their effectiveness since they are not always accurate and inferior instances can lead to incorrect predictions.
Approach:	They propose to use regularized decoding and adversarial training to appropriately learn from noisy knowledge instances for Arabic diacritization.
Outcome:	The proposed model outperforms existing models on two benchmark datasets even with flawed auto-generated knowledge.

Copied to clipboard

Yuanhe Tian, Renze Lou, Xiangyu Pang, Lianxi Wang, Shengyi Jiang, Yan Song

Challenge:	Existing neural approaches to transliterate names from English to Arabic are limited and focus on leveraging the phonemic association between English and Arabic.
Approach:	They propose a model for English-Arabic transliteration using a memory module modeling the phonemic association between English and Arabic to guide the transliterations process.
Outcome:	The proposed model improves on EANames corpus, which better represents names in the general public than linked Wikipedia entries that are always names of famous people.

Relation Discovery with Out-of-Relation Knowledge Base as Supervision (N19-1)

Copied to clipboard

Yan Liang, Xin Liu, Jianwen Zhang, Yangqiu Song

In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents (2025.acl-long)

Challenge:	Existing methods to extract relations from text corpus without annotated data are violated by up to 31%.
Approach:	They propose to use out-of-relation knowledge bases to supervise the discovery of unseen relations where relations to discover from the text corpus and those in knowledge bases are not overlapped.
Outcome:	The proposed method improves the state-of-the-art relation discovery performance by a large margin.

Copied to clipboard

Zhen Tan, Jun Yan, I-Hung Hsu, Rujun Han, Zifeng Wang, Long Le, Yiwen Song, Yanfei Chen, Hamid Palangi, George Lee, Anand Rajan Iyer, Tianlong Chen, Huan Liu, Chen-Yu Lee, Tomas Pfister

Natural Language Interfaces

Challenge:	Existing approaches to long-term dialogue memory management fail to capture the natural semantic structure of conversations, leading to fragmented and incomplete representations.
Approach:	They propose a mechanism that integrates forward- and backward-looking reflections into a personalized memory bank for effective future retrieval.
Outcome:	The proposed mechanism outperforms state-of-the-art benchmarks on a long-term dialogue memory model.

ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants (2026.acl-long)

Copied to clipboard

Pei Wang, Yanan Wu, Xiaoshuai Song, Weixun Wang, Gengru Chen, Zhongwen Li, Kezhong Yan, Qi Liu, Ken Deng, Shuaibing Zhao, Shaopan Xiong, Xuepeng Liu, Xuefeng Chen, Wanxi Deng, Wenbo Su, Bo Zheng

Challenge:	Existing studies on large language model-based agents focus on evaluation benchmarks without training support.
Approach:	They propose a large-scale Chinese shopping simulation environment that uses large language models to train agents.
Outcome:	The proposed model performs poorly in a large-scale and challenging shopping environment in China.

Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey (2025.findings-emnlp)

Copied to clipboard

Zirui Song, Bin Yan, Yuhan Liu, Miao Fang, Mingzhe Li, Rui Yan, Xiuying Chen

Cross-modal Memory Networks for Radiology Report Generation (2021.acl-long)

Challenge:	specialized LLMs are often limited in domain-specific applications that require specialized knowledge.
Approach:	They provide a comprehensive overview of four key methods to enhance large language models by integrating domain-specific knowledge.
Outcome:	The proposed methods are categorized into four key approaches: dynamic knowledge injection, static knowledge embedding, modular adapters, and prompt optimization.

Copied to clipboard

Zhihong Chen, Yaling Shen, Yan Song, Xiang Wan

Low-code LLM: Graphical User Interface over Large Language Models (2024.naacl-demo)

Challenge:	Medical imaging reports are essential in clinical practice, and generating the reports is beneficial to reduce the burden of radiologists.
Approach:	They propose to use a shared memory to enhance the encoder-decoder framework for radiology report generation.
Outcome:	The proposed model can generate more accurate reports on two widely used datasets.

Copied to clipboard

Yuzhe Cai, Shaoguang Mao, Wenshan Wu, Zehua Wang, Yaobo Liang, Tao Ge, Chenfei Wu, WangYou WangYou, Ting Song, Yan Xia, Nan Duan, Furu Wei

Multi-Hop Knowledge Editing via Critic-Guided Multi-Agent Reasoning (2026.findings-acl)

Challenge:	Low-code LLM is a visual programming interface that allows users to incorporate their ideas into the process without writing trivial prompts.
Approach:	They propose a human-LLM interaction framework that incorporates low-code visual programming interactions to achieve more controllable and stable responses.
Outcome:	The proposed framework enables users to incorporate ideas into the process without writing trivial prompts.

Copied to clipboard

Xudong Li, Yuhang Tian, Dandan Song, Zhijing Wu, Shuhao Zhang, Jun Yang, Yongyu Huo, Changzhi Zhou, Xinyu Zhang, Chenhao Li, Huipeng Ma, Luan Zhang, Yan Xu, Qian Liu

Reasoning

Challenge:	Existing knowledge editing methods rely on unidirectional, feed-forward pipelines . a minor retrieval error or logical mismatch at an early hop can become a silent failure .
Approach:	They propose a framework for closed-loop post-edit reasoning that uses a Critic agent to verify coherence and step-wise correctness.
Outcome:	Experiments on MQuAKE-2002 and MQuADE-hard show that CARE effectively mitigates error propagation . a minor retrieval error or logical mismatch at an early hop can become a silent failure .

medIKAL: Integrating Knowledge Graphs as Assistants of LLMs for Enhanced Clinical Diagnosis on EMRs (2025.coling-main)

Copied to clipboard

Mingyi Jia, Junwen Duan, Yan Song, Jianxin Wang

MultiCodeAttack: Iterative Jailbreak Attacking on LLMs with Multi-Code Prompt Injection (2026.findings-acl)

Challenge:	Electronic Medical Records (EMRs) are the digitized record of a patient's medical and health information and are integral to modern healthcare.
Approach:	They propose a framework that combines Large Language Models (LLMs) with knowledge graphs (KGs) to enhance diagnostic capabilities.
Outcome:	The proposed framework assigns weighted importance to entities in medical records based on their type, enabling precise localization of candidate diseases within KGs.

Copied to clipboard

Weifeng Sun, Meng Yan, Zhou Yang, Yuchen Chen, Song Sun, David Lo

Named Entity Recognition for Social Media Texts with Semantic Augmentation (2020.emnlp-main)

Challenge:	Existing approaches to jailbreak rely on fixed template design and a single programming language . however, existing approaches do not consider language diversity or adaptive template evolution .
Approach:	They propose a structured jailbreak framework that explores and optimizes multi-language code templates.
Outcome:	The proposed framework outperforms existing jailbreak baselines and produces higher harmful outputs than baseline methods.

Copied to clipboard

Yuyang Nie, Yuanhe Tian, Xiang Wan, Yan Song, Bo Dai

Summarizing Medical Conversations via Identifying Important Utterances (2020.coling-main)

Challenge:	Existing approaches for named entity recognition suffer from data sparsity problems when conducted on short and informal texts.
Approach:	They propose a neural-based approach to named entity recognition for social media texts . they obtain augmented semantic information from a large-scale corpus and encode it .
Outcome:	The proposed approach outperforms existing approaches on three social media datasets.

Copied to clipboard

Yan Song, Yuanhe Tian, Nan Wang, Fei Xia

Summarization

Challenge:	Applying natural language processing (NLP) techniques to the medical field is a prevailing trend nowadays and has great potential in many applications, such as key information extraction in medical literature.
Approach:	They propose to use a hierarchical encoder-tagger model to generate medical conversation summarization by identifying important utterances.
Outcome:	The proposed model outperforms baseline models and models and adds conversation-related features to improve performance.

Reinforced Cross-modal Alignment for Radiology Report Generation (2022.findings-acl)

Copied to clipboard

Han Qin, Yan Song

Covariance Matrix-Driven Image Channel Allocation for Multimodal Fake News Detection (2026.findings-acl)

Challenge:	Medical images are widely used in clinical decision-making, where writing radiology reports can be enhanced by automatic solutions to alleviate physicians’ workload.
Approach:	They propose an approach with reinforcement learning over a cross-modal memory to better align visual and textual features for radiology report generation.
Outcome:	The proposed approach improves cross-modal alignment on two English radiology report datasets and human evaluation confirms the results.

Copied to clipboard

Zongliang Han, Wenyu Guo, Guoqing Jin, Yang Liu, Yan Song, Dong Yu, Wang Min

Relation Extraction with Word Graphs from N-grams (2021.emnlp-main)

Challenge:	Existing methods focus on designing efficient multimodal fusion frameworks to bridge the semantic gap between images and texts.
Approach:	They propose a covariance matrix-driven image channel allocation method that expands the number of original channel maps and assigns importance scores to the expanded channel maps.
Outcome:	The proposed method achieves state-of-the-art on three public multimodal fake news detection benchmark datasets.

Copied to clipboard

Han Qin, Yuanhe Tian, Yan Song

From Observation to Understanding: Front-Door Adjustments with Uncertainty Calibration for Enhancing Egocentric Reasoning in LVLMs (2025.findings-acl)

Challenge:	Recent studies for relation extraction (RE) leverage the dependency tree of the input sentence to improve performance.
Approach:	They propose to use a graph convolutional network to build a context graph without dependency parsers.
Outcome:	The proposed approach improves neural RE methods without dependency parsers on English benchmark datasets.

Copied to clipboard

Shenshen Li, Wenxin Meng, Lei Wang, Hao Yang, Chong Peng, Peng Yan, Fumin Shen, Jingkuan Song, Heng Tao Shen, Xing Xu

A Lightweight Mixture-of-Experts Neural Machine Translation Model with Stage-wise Training Strategy (2024.findings-naacl)

Challenge:	Existing methods that adapt LVLMs to egocentric tasks overlook critical agent-environment interactions, limiting their ability to perform egoic reasoning.
Approach:	They propose a zero-shot paradigm to enhance egocentric reasoning by simulating human causal reasoning by formalizing ego-centric reasoning using a structural causal model.
Outcome:	The proposed method improves egocentric reasoning abilities on six tasks.

Copied to clipboard

Fan Zhang, Mei Tu, Song Liu, Jinyao Yan

Text Generation

Challenge:	Using mixture-of-experts (MoE) to deal with language heterogeneity is a challenge in neural machine translation (NMT).
Approach:	They propose a lightweight MoE-based NMT model that is trained via an elaborate stage-wise training strategy.
Outcome:	The proposed model achieves stable improvements in translation tasks by introducing fewer extra parameters compared to baseline models.

Multilingual Generative Retrieval via Cross-lingual Semantic Compression (2025.findings-emnlp)

Copied to clipboard

Yuxin Huang, Simeng Wu, Ran Song, Yan Xiang, Yantuan Xian, Shengxiang Gao, Zhengtao Yu

Multilinguality

Challenge:	Existing methods for multilingual retrieval still face cross-lingual identifier misalignment and identifiere inflation.
Approach:	They propose a framework that unifies semantically equivalent multilingual keywords into shared atoms to align semantics and compresses the identifier space.
Outcome:	The proposed framework improves cross-lingual alignment and reduces redundancy.

Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence Generation (2020.acl-main)

Copied to clipboard

Kun Li, Chengbo Chen, Xiaojun Quan, Qing Ling, Yan Song

SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph (2026.findings-eacl)

Challenge:	Aspect term extraction is a task to extract aspect terms from review texts as opinion targets for sentiment analysis.
Approach:	They propose a conditional generation task for augmentation of aspect term extraction . they use a sequence-to-sequence method that generates a new sentence . results confirm that their method alleviates the data scarcity problem significantly .
Outcome:	The proposed method reduces the data scarcity problem significantly and boosts current models.

Copied to clipboard

Jiazheng Li, Yawei Wang, Qiaojing Yan, Yijun Tian, Zhichao Xu, Huan Song, Panpan Xu, Lin Lee Cheong

Structured Data in NLP

Challenge:	Large Language Models (LLMs) have demonstrated remarkable capabilities, but their application to complex, multi-step, and long-horizon tasks remains challenging.
Approach:	They propose a framework that provides a finer-grained advantage assignment derived solely from outcome rewards.
Outcome:	The proposed framework provides a finer-grained advantage assignment, derived solely from outcome rewards.

Meet Changes with Constancy: Learning Invariance in Multi-Source Translation (2020.coling-main)

Copied to clipboard

Jianfeng Liu, Ling Luo, Xiang Ao, Yan Song, Haoran Xu, Jian Ye

Machine Translation

Challenge:	Existing approaches to multi-source neural machine translation neglect inconsistencies between sources of information.
Approach:	They propose a source invariance network to learn invariant information of parallel sources . they propose to integrate such network with multi-encoder based multi-source NMT methods .
Outcome:	The proposed approach achieves clear gains in translation quality and captures implicit invariance between different sources.

Enhancing Relation Extraction via Adversarial Multi-task Learning (2022.lrec-1)

Copied to clipboard

Han Qin, Yuanhe Tian, Yan Song

BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data (2021.acl-long)

Challenge:	Existing studies have focused on re-modeling the given NEs and thus lead to inferior results when NE is sometimes ambiguous.
Approach:	They propose a relation extraction model with two training stages that uses adversarial multi-task learning to recover the given NEs.
Outcome:	The proposed model improves on two English benchmark datasets and shows state-of-the-art performance.

Copied to clipboard

Haoyu Song, Yan Wang, Kaiyan Zhang, Wei-Nan Zhang, Ting Liu

Supertagging Combinatory Categorial Grammar with Attentive Graph Convolutional Networks (2020.emnlp-main)

Challenge:	Existing persona-based dialogue models use crowd-sourced data, such as the PersonaChat . however, the cost of such datasets is limited, and the model is not robust.
Approach:	They propose to disentangle persona-based dialogue generation into two sub-tasks by using a BERT-over-BERT model.
Outcome:	The proposed model outperforms baselines in response quality and persona consistency under different limited data settings.

Copied to clipboard

Learning Multimodal Contrast with Cross-modal Memory and Reinforced Contrast Recognition (2024.findings-acl)

Challenge:	Existing studies have focused on supertagging but have not tapped into contextual information.
Approach:	They propose to build a graph from chunks extracted from a lexicon and apply attention over it to enhance supertagging by leveraging contextual information.
Outcome:	The proposed approach outperforms previous studies in terms of supertagging and parsing.

Copied to clipboard

Yuanhe Tian, Fei Xia, Yan Song

Dialogue Summarization with Mixture of Experts based on Large Language Models (2024.acl-long)

Challenge:	Using a memory module, we learn multimodal contrast using encoding-decoding paradigm . multimodal information are used in many applications, including news feeding, social media, etc.
Approach:	They propose an LLM-based approach for learning multimodal contrast following the encoding-decoding paradigm . they use a memory module with reinforced contrast recognition to enhance learning .
Outcome:	The proposed approach outperforms baseline and state-of-the-art studies on four English and Chinese benchmark datasets.

Copied to clipboard

Yuanhe Tian, Fei Xia, Yan Song

Generating Classical Chinese Poems via Conditional Variational Autoencoder and Adversarial Training (D18-1)

Challenge:	Existing studies for dialogue summarization use one model at a time or treat it as a black box.
Approach:	They propose an LLM-based approach with role-oriented routing and fusion generation to utilize mixture of experts for dialogue summarization.
Outcome:	The proposed approach produces informative and accurate dialogue summarization on widely used datasets.

Copied to clipboard

Juntao Li, Yan Song, Haisong Zhang, Dongmin Chen, Shuming Shi, Dongyan Zhao, Rui Yan

Joint Chinese Word Segmentation and Part-of-speech Tagging via Multi-channel Attention of Character N-grams (2020.coling-main)

Challenge:	Existing models for automatic poetry generation lack term novelty and thematic consistency.
Approach:	They propose a conditional variational autoencoder with adversarial training for classical Chinese poem generation.
Outcome:	The proposed model outperforms existing models on a large poetry corpus on 'classical Chinese' . it generates poems with novel terms and learns their thematic consistency with their titles.

Copied to clipboard

CapArena: Benchmarking and Analyzing Detailed Image Captioning in the LLM Era (2025.findings-acl)

Challenge:	Chinese word segmentation and part-of-speech tagging can be performed in a sequential order . existing studies have shown that jointly performing them can be effective .
Approach:	They propose a character-based neural model enhanced by multi-channel attention of n-grams.
Outcome:	The proposed model outperforms baseline models on five benchmark datasets.

Copied to clipboard

Kanzhi Cheng, Wenpo Song, Jiaxin Fan, Zheng Ma, Qiushi Sun, Fangzhi Xu, Chenyang Yan, Nuo Chen, Jianbing Zhang, Jiajun Chen

Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration (2024.findings-emnlp)

Challenge:	Image captioning has been a challenge for vision-language researchers for decades . current VLMs focus on tasks like visual question answering (YA) but image captioning is not as advanced as expected.
Approach:	They evaluate VLMs' performance on image captioning using human annotations . they find that some metrics show high caption-level agreement with humans .
Outcome:	The proposed model outperforms open-source models on image captioning . it achieves 93.4% correlation with human rankings at $4 per test .

Copied to clipboard

Weikang Yuan, Junjie Cao, Zhuoren Jiang, Yangyang Kang, Jun Lin, Kaisong Song, Tianqianjin Lin, Pengwei Yan, Changlong Sun, Xiaozhong Liu

Improving Constituency Parsing with Span Attention (2020.findings-emnlp)

Challenge:	Existing studies have found that when LLMs are given criminal facts and legal rules, then asked whether cases constitute a certain charge, they struggle to understand legal theories and perform basic legal reasoning tasks.
Approach:	They propose a task to assess LLMs' understanding of legal theories and reasoning capabilities by using a novel framework: Multi-Agent framework for improving complex legal reasoning capability.
Outcome:	The proposed framework improves LLMs' understanding of legal theories and reasoning abilities in real-world scenarios.

Copied to clipboard

Yuanhe Tian, Yan Song, Fei Xia, Tong Zhang

Challenge:	Constituency parsing is a fundamental task for natural language understanding . n-grams are a conventional type of feature for contextual information . experimental results show that neural parsers with no grammar rules outperform statistical ones .
Approach:	They propose to incorporate n-grams into span representations by weighting them according to their contributions to the parsing process.
Outcome:	The proposed approach outperforms existing statistical grammar-based models on Arabic, Chinese, and English datasets.

Prompting Few-shot Multi-hop Question Generation via Comprehending Type-aware Semantics (2024.findings-naacl)

Copied to clipboard

Zefeng Lin, Weidong Chen, Yan Song, Yongdong Zhang

MLLM-Bench: Evaluating Multimodal LLMs with Per-sample Criteria (2025.naacl-long)

Challenge:	Existing approaches for multi-hop question generation rely on large annotated data . supervised approaches rely only on large labeled data, making it hard to perform tasks.
Approach:	They propose a type-aware semantics extraction-based chain-of-thought method for multi-hop question generation for documents . they first extract question types and essential semantic phrases from the given documents and the answer .
Outcome:	The proposed approach extracts question types and essential semantic phrases from documents and the answer.

Copied to clipboard

Wentao Ge, Shunian Chen, Hardy Chen, Nuo Chen, Junying Chen, Zhihong Chen, Wenya Xie, Shuo Yan, ChenghaoZhu ChenghaoZhu, Ziyue Lin, Dingjie Song, Xidong Wang, Anningzhe Gao, Zhang Zhiyi, Jianquan Li, Xiang Wan, Benyou Wang

MoDification: Mixture of Depths Made Easy (2025.naacl-long)

Challenge:	Existing evaluation methodologies for multimodal large language models are limited in evaluating objective queries without considering real-world user experiences.
Approach:	They propose to evaluate multimodal large language models with per-sample criteria using potent MLLM as the judge.
Outcome:	The proposed evaluation paradigm shows that it can be used to evaluate multimodal large language models with per-sample criteria.

Copied to clipboard

Chen Zhang, Meizhi Zhong, Qimeng Wang, Xuantao Lu, Zheyu Ye, Chengqiang Lu, Yan Gao, Yao Hu, Kehai Chen, Min Zhang, Dawei Song

Green & Sustainable NLP

Challenge:	Long-context efficiency is a trending topic in large language model (LLM) serving.
Approach:	They propose a method to combine long-context efficiency and mixture of depths to bring down both latency and memory.
Outcome:	The proposed method achieves 1.2 speedup in latency and 1.8 reduction in memory compared to original LLMs especially in long-context applications.

Multi-Scale Spectral Selection and Entropy-Guided Uncertainty Fusion for Multimodal Rumor Detection (2026.findings-acl)

Copied to clipboard

Zongliang Han, Wenyu Guo, Guoqing Jin, Yang Liu, Fan Li, Dong Yu, Yan Song, null Zhangfengzhen

Profile Consistency Identification for Open-domain Dialogue Agents (2020.emnlp-main)

Challenge:	Existing methods for multimodal content detection fail to capture cross-modal semantic inconsistencies and ignore inherent noise in multimodal features.
Approach:	They propose a multimodal rumor detection method based on a frequency domain spectral selection method and entropy-guided uncertainty fusion method to capture cross-modal semantic inconsistencies.
Outcome:	The proposed method outperforms state-of-the-art methods in multimodal rumor detection . it shows stronger detection capability and robustness on multiple datasets .

Copied to clipboard

Haoyu Song, Yan Wang, Wei-Nan Zhang, Zhengyu Zhao, Ting Liu, Xiaojiang Liu

Directional Skip-Gram: Explicitly Distinguishing Left and Right Context for Word Embeddings (N18-2)

Challenge:	Existing studies on improving attribute consistency focus on incorporating attribute information in responses, but few efforts have identified the consistency relations between response and attribute profile.
Approach:	They propose a key-value structure information enriched BERT model to identify the profile consistency . they propose to incorporate attribute information into the generated responses .
Outcome:	The proposed model improves over strong baselines on downstream tasks.

Copied to clipboard

Yan Song, Shuming Shi, Jing Li, Haisong Zhang

Representation Learning

Challenge:	Existing word embedding models are limited by semantic resources, which are hard to obtain or annotate.
Approach:	They propose a directional skip-gram model that explicitly distinguishes between left and right contexts in word prediction.
Outcome:	The proposed model outperforms other models on different datasets in semantic and syntactic evaluations.

What Matters in Training a GPT4-Style Language Model with Multimodal Inputs? (2024.naacl-long)

Copied to clipboard

Yan Zeng, Hanbo Zhang, Jiani Zheng, Jiangnan Xia, Guoqiang Wei, Yang Wei, Yuchen Zhang, Tao Kong, Ruihua Song

Challenging Large Language Models with New Tasks: A Study on their Adaptability and Robustness (2024.findings-acl)

Challenge:	Recent advances in GPT-4V have demonstrated remarkable multi-modal capabilities in processing image inputs and following open-ended instructions.
Approach:	They propose a plug-and-play technique to enhance multi-modal LLMs . they propose 'lynx' to train multi-modal LLM models .
Outcome:	The proposed training strategy improves understanding accuracy and instruction-following proficiency of multi-modal models.

Copied to clipboard

Chenxi Li, Yuanhe Tian, Zhaxi Zerong, Yan Song, Fei Xia

Act as you think: Reinforcing Consistent Reasoning in Medical Visual Question Answering (2026.acl-long)

Challenge:	Existing evaluation approaches for large language models (LLMs) rely on existing tasks and benchmarks, raising concerns about test set contamination and the genuine comprehension abilities of LLMs.
Approach:	They propose to evaluate LLMs by designing new tasks, automatically generating evaluation datasets for the tasks, and conducting detailed error analyses to scrutinize LLM's adaptability to new tasks.
Outcome:	The proposed method examines LLMs’ adaptability to new tasks, their sensitivity to prompt variations, and their error tendencies.

Copied to clipboard

Songtao Jiang, Yuan Wang, Ruizhe Chen, Yan Zhang, Ruilin Luo, Bohan Lei, Yeying Jin, Sibo Song, ZhiBo Yang, Jimeng Sun, Jian Wu, Zuozhu Liu

Reading Like HER: Human Reading Inspired Extractive Summarization (D19-1)

Challenge:	Recent advances have improved the accuracy of medical visual question answering (Med-VQA) however, the high stakes nature of the medical domain has precipitated a shift towards interpretability and transparency of reasoning processes.
Approach:	They propose a reinforcement learning from verifiable rewards framework that rewards internal consistency and logical coherence.
Outcome:	The proposed framework rewards internal consistency and logical coherence, and is highly versatile, the authors show.

Copied to clipboard

Ling Luo, Xiang Ao, Yan Song, Feiyang Pan, Min Yang, Qing He

RESEMO: A Benchmark Chinese Dataset for Studying Responsive Emotion from Social Media Content (2024.findings-acl)

Challenge:	Existing methods for extracting text summarization are abstractive and extractive.
Approach:	They propose a novel approach for extractive summarization by simulating two stages . they adopt a convolutional neural network to encode gist of paragraphs for rough reading .
Outcome:	The proposed method significantly outperforms the state-of-the-art extractive methods on CNN and DailyMail datasets.

Copied to clipboard

Bo Hu, Meng Zhang, Chenfei Xie, Yuanhe Tian, Yan Song, Zhendong Mao

Towards Effective and Efficient Continual Pre-training of Large Language Models (2025.acl-long)

Challenge:	Existing studies on social media text processing do not focus on responsive emotion analysis.
Approach:	They propose a Chinese dataset named ResEmo for responsive emotion analysis, including 3813 posts with 68,781 comments collected from Weibo, the largest social media platform in China.
Outcome:	The proposed dataset includes 3813 posts with 68,781 comments collected from weibo, the largest social media platform in China.

Copied to clipboard

Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu, Jinhao Jiang, Yingqian Min, Xin Zhao, Zhicheng Dou, Jiaxin Mao, Yankai Lin, Ruihua Song, Jun Xu, Xu Chen, Rui Yan, Zhewei Wei, Di Hu, Wenbing Huang, Ji-Rong Wen

FedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models (2025.coling-main)

Challenge:	Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks.
Approach:	They propose a Continual pre-training method that can greatly improve Chinese language ability and scientific reasoning ability of LLMs.
Outcome:	The proposed method can greatly improve Chinese language ability and scientific reasoning ability of LLMs.

Copied to clipboard

Tao Fan, Guoqiang Ma, Yan Kang, Hanlin Gu, Yuanfeng Song, Lixin Fan, Kai Chen, Qiang Yang

Improving Relation Extraction through Syntax-induced Pre-training with Dependency Masking (2022.findings-acl)

Challenge:	Recent research in large language models (LLMs) has focused on enabling clients to fine-tune their locally deployed homogeneous LLMs collaboratively or on transferring knowledge from server-based LLM to small language models at downstream clients.
Approach:	They propose a parameter-efficient federated mutual knowledge transfer framework for large and small language models that allows for token alignment and selective knowledge transfer between client-side LLMs and a server-side SLM.
Outcome:	The proposed framework enhances the performance of both LLMs and SLMs with clients' unique domain insights while preserving the server's LLM and client's unique domain insight.

Copied to clipboard

Reinforced Training Data Selection for Domain Adaptation (P19-1)

Challenge:	Existing studies require modifications to existing baseline architectures to leverage syntactic information.
Approach:	They propose to leverage syntactic information to improve relation extraction by training a syntax-induced encoder on auto-parsed data through dependency masking.
Outcome:	The proposed approach outperforms baseline models and achieves state-of-the-art results on two English datasets.

Copied to clipboard

Miaofeng Liu, Yan Song, Hongbin Zou, Tong Zhang

Generating Radiology Reports via Memory-driven Transformer (2020.emnlp-main)

Challenge:	Existing approaches to learn domains with massive data are not easy to implement and require a predefined threshold.
Approach:	They propose a framework that searches for training instances relevant to the target domain and learns better representations for them.
Outcome:	The proposed framework is effective in data selection and representation, but generalized to accommodate different NLP tasks.

Copied to clipboard

Zhihong Chen, Yan Song, Tsung-Hui Chang, Xiang Wan

Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation (2020.acl-main)

Challenge:	Medical imaging reports are time-consuming and can be error-prone for inexperienced radiologists.
Approach:	They propose to generate radiology reports with memory-driven Transformer using relational memory and memory-based conditional layer normalization.
Outcome:	The proposed method outperforms existing models on IU X-Ray and MIMIC-CXR . it generates long reports with medical terms and meaningful image-text attention mappings .

Copied to clipboard

Haoyu Song, Yan Wang, Wei-Nan Zhang, Xiaojiang Liu, Ting Liu

GRPO-Guided Modality Selection Enhanced LoRA-Tuned LLMs for Multimodal Emotion Recognition (2025.findings-emnlp)

Challenge:	Existing persona-based dialogue models generate human-like responses but can hardly avoid the generation of inconsistent persona words.
Approach:	They propose a framework that deletes inconsistent words from a generated response prototype and further rewrites it to a personality-consistent one.
Outcome:	The proposed framework achieves good performance on the persona-chat dataset.

Copied to clipboard

Yang Chen, Shuwan Yang, Yan Xiang, Ran Song, Yuxin Huang, Zhengtao Yu

Scene Graph and Dependency Grammar Enhanced Remote Sensing Change Caption Network (SGD-RSCCN) (2025.coling-main)

Challenge:	Multimodal emotion recognition in conversation (MERC) aims to identify speakers’ emotional states by utilizing text, audio, and visual modalities.
Approach:	They propose an adaptive modality selection framework for multimodal emotion recognition in conversation that integrates all available modalities into one .
Outcome:	The proposed framework outperforms existing methods on multimodal dialogue datasets and is available at https://github.com/youflyaway/Modality-Selection-Enhanced-LoRA-Tuned-LLMs.

Copied to clipboard

Qiaoli Sun, Yan Wang, Xiaoyu Song

Effidit: An Assistant for Improving Writing Efficiency (2023.acl-demo)

Challenge:	Remote sensing images are used for disaster assessment, urban planning and disaster response.
Approach:	They propose a Scene Graph and Dependency Grammar Enhanced Remote Sensing Change Caption Network to improve the accuracy and naturalness of extracting and describing change information from remote sensing images.
Outcome:	The proposed method improves the naturalness and accuracy of extracting and describing change information from remote sensing images.

Copied to clipboard

Shuming Shi, Enbo Zhao, Wei Bi, Deng Cai, Leyang Cui, Xinting Huang, Haiyun Jiang, Duyu Tang, Kaiqiang Song, Longyue Wang, Chenyan Huang, Guoping Huang, Yan Wang, Piji Li

Green & Sustainable NLP

Challenge:	Effidit is a digital writing assistant that provides three modules to help users write faster and more efficiently.
Approach:	They present Effidit, a digital writing assistant that provides three modules to help users write higher-quality text more efficiently.
Outcome:	Effidit expands the capabilities of a typical writing assistant by providing three modules . Effit can help users create their own text faster and more efficiently .

When Personalization Tricks Detectors: The Feature-Inversion Trap in Machine-Generated Text Detection (2026.acl-long)

Copied to clipboard

Lang Gao, Xuhui Li, Chenxi Wang, Mingzhe Li, Wei Liu, Zirui Song, Jinghui Zhang, Rui Yan, Preslav Nakov, Xiuying Chen

Improving Federated Learning for Aspect-based Sentiment Analysis via Topic Memories (2021.emnlp-main)

Challenge:	Personalized MGT detection remains largely underexplored due to personalization challenges . large language models (LLMs) can imitate personal writing styles, but they can generate fake news and misinformation.
Approach:	They propose a benchmark to evaluate detector robustness under personalization . they attribute this limitation to a feature-inversion trap that flips the effect in personalized contexts .
Outcome:	The proposed framework predicts detector robustness under personalization with an 85% correlation to actual results.

Copied to clipboard

Han Qin, Guimin Chen, Yuanhe Tian, Yan Song

Topic Memory Networks for Short Text Classification (D18-1)

Challenge:	Aspect-based sentiment analysis (ABSA) predicts sentiment polarity for aspect term in sentences . labeled data stored at different locations and inaccessible due to privacy or legal concerns .
Approach:	They propose a model with federated learning to combine labeled data across different domains . they incorporate topic memory to take data from diverse domains into consideration .
Outcome:	The proposed model outperforms baselines on a simulated environment with three nodes.

Copied to clipboard

Jichuan Zeng, Jing Li, Yan Song, Cuiyun Gao, Michael R. Lyu, Irwin King

What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues (D19-1)

Challenge:	Existing classification models for short texts are weak due to data sparsity .
Approach:	They propose topic memory networks for short text classification with a novel topic memory mechanism to encode latent topic representations indicative of class labels.
Outcome:	The proposed model outperforms state-of-the-art models on short text classification, while generating coherent topics.

Copied to clipboard

Xintong Yu, Hongming Zhang, Yangqiu Song, Yan Song, Changshui Zhang

Visual Data in NLP

Challenge:	a core task of natural language understanding is to ground a pronoun to a visual object it refers to . problem arises when people use pronounos to refer to something they can see without prior introduction . a novel visual-aware PCR model is proposed to solve this problem .
Approach:	They propose a visual-aware PCR model to ground a pronoun to a visible object . they propose PCR using a large-scale dialogue dataset to investigate this problem .
Outcome:	The proposed model can help resolve pronouns in conversational contexts.

Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information (2020.findings-emnlp)

Copied to clipboard

Yuyang Nie, Yuanhe Tian, Yan Song, Xiang Ao, Xiang Wan

Joint Aspect Extraction and Sentiment Analysis with Directional Graph Convolutional Networks (2020.coling-main)

Challenge:	Existing studies have shown that named entity recognition (NER) is effective in encoding and aggregating syntactic information, but they lack the appropriate knowledge to model such properties.
Approach:	They propose to leverage syntactic information by leveraging attentive ensembles to model NER . they propose key-value memory networks, syntax attention and gate mechanism for encoding, weighting and aggregating syntaktic information.
Outcome:	The proposed model outperforms previous studies on six English and Chinese benchmark datasets.

Copied to clipboard

Guimin Chen, Yuanhe Tian, Yan Song

Dynamics of Instruction Fine-Tuning for Chinese Large Language Models (2025.coling-main)

Challenge:	End-to-end aspect-based sentiment analysis uses two sub-tasks to extract aspect terms . experimental results demonstrate the effectiveness of our approach on all datasets .
Approach:	They propose to combine aspect extraction and sentiment analysis with encoding syntactic information to improve model's representation of input sentences.
Outcome:	The proposed approach achieves state-of-the-art on three benchmark datasets.

Copied to clipboard

Chiyu Song, Zhanchao Zhou, Jianhao Yan, Yuejiao Fei, Zhenzhong Lan, Yue Zhang

Incorporating Context and External Knowledge for Pronoun Coreference Resolution (N19-1)

Challenge:	Instruction tuning is a burgeoning method to elicit the general intelligence of Large Language Models.
Approach:	They investigate the effects of data quantity, model size, and data construction methods on instruction tuning for Chinese LLMs.
Outcome:	The proposed model includes over 40,000 high-quality instruction instances covering ten underlying abilities.

Copied to clipboard

Hongming Zhang, Yan Song, Yangqiu Song

Creative and Context-Aware Translation of East Asian Idioms with GPT-4 (2024.findings-emnlp)

Challenge:	Existing models for pronoun coreference resolution rely on manual definitions and features to resolve pronounous coreferences.
Approach:	They propose a two-layer model for pronoun coreference resolution that leverages both context and external knowledge.
Outcome:	The proposed model outperforms state-of-the-art models by a large margin.

Copied to clipboard

Kenan Tang, Peiyang Song, Yao Qin, Xifeng Yan

Multilinguality

Challenge:	figurative language is a challenge for human translators, who often choose a context-aware translation . a set of commonly used idioms condenses its figurativ meaning into a few characters .
Approach:	They evaluate whether GPT-4 can generate high-quality translations using Pareto-optimal prompting strategies that outperform translation engines from Google and DeepL.
Outcome:	The proposed translations outperform translation engines from Google and DeepL at low cost.

Aspect-based Sentiment Analysis with Context Denoising (2024.findings-naacl)

Copied to clipboard

Yuanhe Tian, Chang Liu, Yan Song, Fei Xia, Yongdong Zhang

A Hybrid Approach to Automatic Corpus Generation for Chinese Spelling Check (D18-1)

Challenge:	Existing approaches to ABSA use text encoders to locate important context features or remove them from input.
Approach:	They propose to improve ABSA with context denoising to remove noise from text . they use diffusion networks to perform denoizing process to gradually eliminate noise . paper shows that aspect-based sentiment analysis is effective for fine-grained analysis .
Outcome:	The proposed approach improves ABSA on five widely used ABSA datasets.

Copied to clipboard

Dingmin Wang, Yan Song, Jing Li, Jialong Han, Haisong Zhang

Challenge:	Chinese spelling check (CSC) is a challenging but meaningful task that serves as a preprocessing in many natural language processing(NLP) applications.
Approach:	They propose to construct Chinese spelling check corpus with automatically generated spelling errors, which are either visually or phonologically resembled characters, corresponding to OCR- and ASR-based methods. Experimental results demonstrate the effectiveness of the approach.
Outcome:	The proposed method is based on visual or phonologically similar spelling errors, and is validated with respect to three standard test sets.

Improving Large Language Models in Event Relation Logical Prediction (2024.acl-long)

Copied to clipboard

Meiqi Chen, Yubo Ma, Kaitao Song, Yixin Cao, Yan Zhang, Dongsheng Li

Constructing a Chinese Medical Conversation Corpus Annotated with Conversational Structures and Actions (L18-1)

Challenge:	Event relation extraction tasks require rigorous logical reasoning and semantic comprehension, a challenge for narrative understanding and reasoning.
Approach:	They propose three approaches to endow LLMs with event relation logic to generate more coherent answers across different scenarios.
Outcome:	The proposed approach improves on a set of ERE tasks and provides insights for future work.

Copied to clipboard

Nan Wang, Yan Song, Fei Xia

Natural Language Interfaces

Challenge:	Recent studies have found that patients' advocacy for antibiotic treatment is consequential on antibiotic over-prescribing.
Approach:	They propose to analyze a manually transcribed corpus of medical dialogue in Chinese pediatric consultations with annotation of conversational structures and actions.
Outcome:	The proposed corpus can shed light on ways to improve physician-patient communication in order to reduce antibiotic over-prescribing.

ChiMST: A Chinese Medical Corpus for Word Segmentation and Medical Term Recognition (2022.lrec-1)

Copied to clipboard

Yuanhe Tian, Han Qin, Fei Xia, Yan Song

Federated Chinese Word Segmentation with Global Character Associations (2021.findings-acl)

Challenge:	Chinese word segmentation and named entity recognition are important tasks in natural language processing.
Approach:	They develop a Chinese medical corpus annotated with Chinese word boundary and medical term information to address this problem.
Outcome:	The proposed corpus will be a valuable resource for Chinese word segmentation and named entity recognition research on the medical domain.

Copied to clipboard

Yuanhe Tian, Guimin Chen, Han Qin, Yan Song

Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation (2021.acl-long)

Challenge:	Chinese word segmentation (CWS) is a fundamental task for natural language processing.
Approach:	They propose a neural model for Chinese word segmentation with federated learning to help CWS deal with data isolation.
Outcome:	The proposed model outperforms baselines on a simulated environment with five nodes.

Copied to clipboard

Shizhe Diao, Ruijia Xu, Hongjin Su, Yilei Jiang, Yan Song, Tong Zhang

Knowledge-aware Pronoun Coreference Resolution (P19-1)

Challenge:	Existing methods to train pre-trained models require domain-specific data and computational resources.
Approach:	They propose a domain-aware N-gram Adaptor to incorporate unseen and domain-specific words into a generic pretrained model.
Outcome:	The proposed model can improve on eight low-resource tasks using limited data with lower computational costs.

Copied to clipboard

Hongming Zhang, Yan Song, Yangqiu Song, Dong Yu

Bitnet.cpp: Efficient Edge Inference for Ternary LLMs (2025.acl-long)

Challenge:	Existing models for pronoun coreference resolution only use triplets, the most common format for knowledge graphs.
Approach:	They propose a model that leverages different types of knowledge to resolve pronoun coreference with a neural model.
Outcome:	The proposed model outperforms state-of-the-art baselines on two datasets from different domains.

Copied to clipboard

Jinheng Wang, Hansong Zhou, Ting Song, Shijie Cao, Yan Xia, Ting Cao, Jianyu Wei, Shuming Ma, Hongyu Wang, Furu Wei

Green & Sustainable NLP

Challenge:	1-bit large language models have spurred interest in ternary LLMs, but efficient edge inference is still scarce.
Approach:	They propose an inference system optimized for 1-bit large language models . they propose a new library that facilitates sub-2-bits-per-weight inference .
Outcome:	The proposed inference system achieves 6.25x speed increase over full-precision baselines and 2.32x over low-bit baselines.

Large Language Models Are No Longer Shallow Parsers (2024.acl-long)

Copied to clipboard

Yuanhe Tian, Fei Xia, Yan Song

Composing Ci with Reinforced Non-autoregressive Text Generation (2022.emnlp-main)

Challenge:	Recent advances in large language models (LLMs) have reshaped the field of natural language processing (NLP) however, fundamental NLP tasks that involve linguistic analysis still play essential roles in the field.
Approach:	They propose to use constituency parsing to improve performance of LLMs on deep syntactic parse trees to prompt LLM chunking, filter out low-quality chunks and add remaining chunks to prompts to instruct LLM for parser.
Outcome:	The proposed approach improves LLMs' performance on constituency parsing on English and Chinese benchmark datasets.

Copied to clipboard

Yan Song

Text Generation

Challenge:	Existing approaches to compose Ci are limited in handling the constraints of tune patterns . authors propose a non-autoregressive approach to generate Ci using a synchronous process .
Approach:	They propose to compose Ci using a non-autoregressive approach that takes into account rigid formats . they propose to apply reinforcement learning to the generation process with rigid constraints .
Outcome:	The proposed method outperforms baselines and previous studies on a Ci dataset . it allows the model to perform synchronous generation while maintaining the format and content requirement.

Complementary Learning of Aspect Terms for Aspect-based Sentiment Analysis (2022.lrec-1)

Copied to clipboard

Han Qin, Yuanhe Tian, Fei Xia, Yan Song

LAGCL4Rec: When LLMs Activate Interactions Potential in Graph Contrastive Learning for Recommendation (2025.findings-emnlp)

Challenge:	Existing ABSA models do not pay attention to aspect terms and their contexts . a discriminator is introduced to improve ABSA, allowing for better understanding of aspect terms .
Approach:	They propose to improve ABSA by complementary learning of aspect terms . they explicitly recover aspect terms from each input sentence to better understand aspects .
Outcome:	The proposed approach improves ABSA on five widely used English benchmark datasets.

Copied to clipboard

Leqi Zheng, Chaokun Wang, Canzhi Chen, Jiajun Zhang, Cheng Wu, Zixin Song, Shannan Yan, Ziyang Liu, Hongwei Li

DiningBench: A Hierarchical Multi-view Benchmark for Perception and Reasoning in the Dietary Domain (2026.acl-long)

Challenge:	Traditional contrastive learning methods treat negative feedback as equally hard or easy, ignoring informative semantic difficulty during training.
Approach:	They propose a framework leveraging Large Language Models to Activate interactions in Graph Contrastive Learning for Recommendation.
Outcome:	The proposed framework outperforms state-of-the-art benchmarks on multiple benchmarks.

Copied to clipboard

Song Jin, Juntian Zhang, Xun Zhang, Zeying Tian, Fei Jiang, Guojun Yin, Wei Lin, Yong Liu, Rui Yan

Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network (P19-1)

Challenge:	Existing vision-language models lack fine-grained classification, single-view imagery, and inaccurate metadata.
Approach:	They propose a hierarchical, multi-view benchmark to evaluate VLMs across three levels of cognitive complexity.
Outcome:	The proposed benchmark evaluates vision-language models across three levels of complexity . it systematically identifies five primary failure modes . the proposed benchmarks are available on https://github.com/meituan/DiningBench.

Copied to clipboard

Kun Xu, Liwei Wang, Mo Yu, Yansong Feng, Yan Song, Zhiguo Wang, Dong Yu

Structured Data in NLP

Challenge:	Existing approaches to cross-lingual knowledge graph (KG) alignment rely on entity embeddings derived from monolingual KG structural information.
Approach:	They propose a topic entity graph to represent entities with contextual information in KGs.
Outcome:	The proposed model outperforms state-of-the-art methods by a large margin.

Learning to Customize Model Structures for Few-shot Dialogue Generation Tasks (2020.acl-main)

Copied to clipboard

Yiping Song, Zequn Liu, Wei Bi, Rui Yan, Ming Zhang

RevCore: Review-Augmented Conversational Recommendation (2021.findings-acl)

Challenge:	Existing methods for training generative models with minimal corpus are difficult . fine-tuning distinguishes tasks from parameter perspective but ignores model-structure perspective .
Approach:	They propose an algorithm that can customize a unique dialogue model for each task in the few-shot setting.
Outcome:	The proposed method outperforms baselines on two datasets in task consistency, response quality, diversity and consistency.

Copied to clipboard

Yu Lu, Junwei Bao, Yan Song, Zichen Ma, Shuguang Cui, Youzheng Wu, Xiaodong He

Dependency-driven Relation Extraction with Attentive Graph Convolutional Networks (2021.acl-long)

Challenge:	Existing conversational recommendation systems lack item information when conducted on short dialogue history and unfamiliar items.
Approach:	They propose a framework where reviews are seamlessly incorporated into conversational recommendation systems.
Outcome:	The proposed framework yields better performance on recommendation and conversation responding.

Copied to clipboard

Yuanhe Tian, Guimin Chen, Yan Song, Xiang Wan

Case2Code: Scalable Synthetic Data for Code Generation (2025.coling-main)

Challenge:	Existing studies suffer from noise in dependency trees, which can cause confusions in relation extraction.
Approach:	They propose a dependency-driven approach for relation extraction with attentive graph convolutional networks . they apply an attention mechanism upon graph convolutional networks to different word dependencies .
Outcome:	The proposed approach outperforms previous studies on two English datasets and achieves state-of-the-art performance.

Copied to clipboard

Yunfan Shao, Linyang Li, Yichuan Ma, Peiji Li, Demin Song, Qinyuan Cheng, Shimin Li, Xiaonan Li, Pengyu Wang, Qipeng Guo, Hang Yan, Xipeng Qiu, Xuanjing Huang, Dahua Lin

Programming Languages in NLP

Challenge:	Large Language Models (LLMs) have shown outstanding breakthroughs in code generation.
Approach:	They propose a case-to-code induction task that exploits the expressiveness and correctness of programs by incorporating LLMs into their training.
Outcome:	The proposed task improves distribution case-to-code induction and various coding generation tasks.

Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed Knowledge (2020.acl-main)

Copied to clipboard

Yuanhe Tian, Yan Song, Xiang Ao, Fei Xia, Xiaojun Quan, Tong Zhang, Yonggang Wang

Encoding Conversation Context for Neural Keyphrase Extraction from Microblog Posts (N18-1)

Challenge:	Chinese word segmentation and part-of-speech tagging are important fundamental tasks in natural language processing.
Approach:	They propose a neural model for Chinese word segmentation and part-of-speech tagging . they incorporate context features and syntactic knowledge for each input character .
Outcome:	The proposed model can learn and benefit from existing tools, but its quality may be poor.

Copied to clipboard

Yingyi Zhang, Jing Li, Yan Song, Chengzhi Zhang