Papers by Lemao Liu

ReFreeKV: Towards Threshold-Free KV Cache Compression (2026.findings-acl)

Challenge:	Empirical studies show low missampling rate and high uncertainty are both essential for achieving promising performances with negative sampling.
Approach:	They propose an adaptive and weighted sampling distribution that further improves negative sampling by introducing missampling and uncertainty concepts.
Outcome:	The proposed approach improves on synthetic and well-annotated datasets in terms of F1 score and loss convergence.

Copied to clipboard

Xuanfan Ni, Liyan Xu, Chenyang Lyu, Longyue Wang, Mo Yu, Lemao Liu, Fandong Meng, Jie Zhou, Piji Li

Responsible & Trustworthy NLP

Challenge:	Towards the KV cache efficiency, we propose a new objective that lifts the threshold constraints for robust KV compression.
Approach:	They propose a method that adjusts KV cache budgets while preserving full-cache performance.
Outcome:	The proposed method can reduce memory consumption while preserving full-cache performance.

IMTLab: An Open-Source Platform for Building, Evaluating, and Diagnosing Interactive Machine Translation Systems (2023.emnlp-main)

Copied to clipboard

Xu Huang, Zhirui Zhang, Ruize Gao, Yichao Du, Lemao Liu, Guoping Huang, Shuming Shi, Jiajun Chen, Shujian Huang

Nearest Neighbor Machine Translation is Meta-Optimizer on Output Projection Layer (2023.emnlp-main)

Challenge:	Existing systems that use a left-to-right completion paradigm are inefficient and expensive.
Approach:	They propose an open-source end-to-end interactive machine translation system platform . they propose to use a prefix-constrained decoding approach to achieve end- to-end evaluation .
Outcome:	The proposed system can guarantee high-quality, error-free translations . it uses prefix-constrained decoding and improves on previous systems .

Copied to clipboard

Ruize Gao, Zhirui Zhang, Yichao Du, Lemao Liu, Rui Wang

E-NER: Evidential Deep Learning for Trustworthy Named Entity Recognition (2023.findings-acl)

Challenge:	Nearest Neighbor Machine Translation (kNN-MT) is a powerful domain adaptation tool . the reasons for its success have not been thoroughly investigated .
Approach:	They propose to integrate pre-trained Neural Machine Translation models with token-level retrieval . they propose to implicitly execute gradient descent on the output projection layer of NMT .
Outcome:	The proposed approach outperforms model fine-tuning on in-domain tests while achieving better performance on out-of-domain sets.

Copied to clipboard

Zhen Zhang, Mengting Hu, Shiwan Zhao, Minlie Huang, Haotian Wang, Lemao Liu, Zhirui Zhang, Zhe Liu, Bingzhe Wu

TexSmart: A System for Enhanced Natural Language Understanding (2021.acl-demo)

Challenge:	Named entity recognition (NER) systems focus on improving model performance, ignoring the need to quantify model uncertainty.
Approach:	They propose to introduce two uncertainty-guided loss terms to the conventional EDL and a series of uncertainty-guiding training strategies to solve these challenges.
Outcome:	The proposed method achieves better OOV/OOD detection performance and generalization ability on OOV entities compared to state-of-the-art methods.

Copied to clipboard

Lemao Liu, Haisong Zhang, Haiyun Jiang, Yangming Li, Enbo Zhao, Kun Xu, Linfeng Song, Suncong Zheng, Botong Zhou, Dick Zhu, Xiao Feng, Tao Chen, Tao Yang, Dong Yu, Feng Zhang, ZhanHui Kang, Shuming Shi

GWLAN: General Word-Level AutocompletioN for Computer-Aided Translation (2021.acl-long)

Challenge:	TexSmart supports fine-grained named entity recognition (NER) Large-scale fine-granular entity types are expected to provide richer semantic information for downstream NLP applications.
Approach:	They introduce TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
Outcome:	The proposed system supports fine-grained named entity recognition (NER) and enhanced semantic analysis functions.

Copied to clipboard

Huayang Li, Lemao Liu, Guoping Huang, Shuming Shi

On the Hallucination in Simultaneous Machine Translation (2024.acl-short)

Challenge:	Computer-aided translation (CAT) is a form of software that assists a human translator in the translation process.
Approach:	They propose to use computer-aided translation (CAT) to assist a human translator in the translation process.
Outcome:	The proposed method can give significantly more accurate predictions than baseline methods on CAT datasets.

Copied to clipboard

Meizhi Zhong, Kehai Chen, Zhengshan Xue, Lemao Liu, Mingming Yang, Min Zhang

Rethinking the Evaluation of In-Context Learning for LLMs (2024.emnlp-main)

Challenge:	Currently, there are no studies which systematically analyze hallucination in SiMT.
Approach:	They conduct a comprehensive analysis of hallucination in simultaneous machine translation (SiMT) they find that halluciation is extremely severe, especially as latency increases .
Outcome:	The results show that it is possible to alleviate hallucination by decreasing the over usage of target-side information for SiMT.

Copied to clipboard

Guoxin Yu, Lemao Liu, Mo Yu, Yue Yu, Xiang Ao

Evaluating Explanation Methods for Neural Machine Translation (2020.acl-main)

Challenge:	Existing studies evaluate In-context learning methods based on task performance . however, this evaluation protocol overlooks the significant cost associated with the demonstration configuration process .
Approach:	They propose a two-dimensional evaluation paradigm that considers both configuration costs and task performance.
Outcome:	The proposed evaluation paradigm can be applied to any ICL method as a plugin.

Copied to clipboard

Jierui Li, Lemao Liu, Huayang Li, Guanlin Li, Guoping Huang, Shuming Shi

On the Branching Bias of Syntax Extracted from Pre-trained Language Models (2020.findings-emnlp)

Challenge:	Neural machine translation (NMT) has seen great success during recent years.
Approach:	They propose a metric that measures the fidelity of explanation methods on translation tasks . they use an efficient approximation to evaluate several explanation methods .
Outcome:	The proposed metric is efficient and can be used on translation tasks.

Copied to clipboard

Huayang Li, Lemao Liu, Guoping Huang, Shuming Shi

Learning from Sibling Mentions with Scalable Graph Inference in Fine-Grained Entity Typing (2022.acl-long)

Challenge:	Existing methods for extracting constituency trees from language models suffer from branching bias.
Approach:	They propose to measure the branching bias by comparing the performance gap on a language and its reversed language.
Outcome:	The proposed method is agnostic to language models and extracting methods, and it can be implemented with three factors to introduce the branching bias.

Copied to clipboard

Yi Chen, Jiayang Cheng, Haiyun Jiang, Lemao Liu, Haisong Zhang, Shuming Shi, Ruifeng Xu

Structured Data in NLP

Challenge:	Existing models struggle to handle hard mentions due to insufficient contexts, limiting their overall typing performance.
Approach:	They propose to exploit sibling mentions to enhance the mention representations by adding unseen test mentions as new nodes for inference.
Outcome:	The proposed model outperforms ten strong baseline models and outperformed strong baselines.

Logic Unveils Truth, While Disguise Obscures It: Transition Logic Augmented Response Selection for Multi-Turn Dialogue (2023.findings-emnlp)

Copied to clipboard

Tingchen Fu, Xueliang Zhao, Lemao Liu, Rui Yan

Natural Language Interfaces

Challenge:	Existing methods of negative samples tend to yield false negatives due to one-to-many property in open-domain dialogue.
Approach:	They propose a sequential variational ladder auto-encoder to capture one-to-many transition pattern of multiple characteristics in open-domain dialogue.
Outcome:	The proposed approach improves the performance of a retrieval dialogue system on two benchmarks.

BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models (2024.findings-acl)

Copied to clipboard

Xueliang Zhao, Xinting Huang, Tingchen Fu, Qintong Li, Shansan Gong, Lemao Liu, Wei Bi, Lingpeng Kong

Automatic Article Commenting: the Task and Dataset (P18-2)

Challenge:	Multimodal reasoning is a key capability for large vision-language models . however, the vanilla Chain-of-Thought method fails to address critical steps in multi-step reasoning tasks.
Approach:	They propose a bi-modal Behavioral Alignment method to augment multimodal reasoning . they use domain-specific language to integrate multimodal information into a precise alternative form .
Outcome:	The proposed method significantly improves GPT-4V(ision) on geometry problem solving, chess positional advantage prediction and molecular property prediction.

Copied to clipboard

Lianhui Qin, Lemao Liu, Wei Bi, Yan Wang, Xiaojiang Liu, Zhiting Hu, Hai Zhao, Shuming Shi

Challenge:	Existing methods to make comments on articles are based on human-annotated subsets, but they are not suitable for online forums.
Approach:	They propose to use a large-scale Chinese corpus with millions of real comments and a human-annotated subset characterizing the comments’ varying quality to generalize a broad set of popular reference-based metrics.
Outcome:	The proposed model incorporates human-annotated subset characterizing the comments’ varying quality and shows that it is more accurate than previous models.

BiTIIMT: A Bilingual Text-infilling Method for Interactive Machine Translation (2022.acl-long)

Copied to clipboard

Yanling Xiao, Lemao Liu, Guoping Huang, Qu Cui, Shujian Huang, Shuming Shi, Jiajun Chen

MCPG: A Flexible Multi-Level Controllable Framework for Unsupervised Paraphrase Generation (2022.findings-emnlp)

Challenge:	Existing IMT systems relying on lexical constrained decoding (LCD) are limited in translation efficiency and quality due to LCD.
Approach:	They propose a novel interactive neural machine translation system that uses lexical constraints to decode missing words in a manually revised translation.
Outcome:	The proposed system performs significantly better and faster than state-of-the-art IMT on three translation tasks.

Copied to clipboard

Yi Chen, Haiyun Jiang, Lemao Liu, Rui Wang, Shuming Shi, Ruifeng Xu

XQ-MEval: A Dataset with Cross-lingual Parallel Quality for Benchmarking Translation Metrics (2026.findings-acl)

Challenge:	Existing studies on controllable unsupervised paraphrase generation are expensive and require supervised training on large parallel corpora.
Approach:	They propose a method for controllable unsupervised paraphrase generation that is flexible to adapt to specific domains without extra training.
Outcome:	The proposed method outperforms state-of-the-art unsupervised baselines by a margin.

Copied to clipboard

Jingxuan Liu, Zhi Qu, Jin Tei, Hidetaka Kamigaito, Lemao Liu, Taro Watanabe

Touch Editing: A Flexible One-Time Interaction Approach for Translation (2020.aacl-main)

Challenge:	averaging metric scores across languages is suspicious since translations of equal quality receive different scores across language.
Approach:	They propose a semi-automatically built dataset to benchmark translation metrics using MQM-defined errors and a normalization strategy to mitigate cross-lingual scoring bias.
Outcome:	The proposed model shows that translation metrics suffer from cross-lingual scoring bias . the proposed model is based on a semi-automatically built dataset covering nine translation directions .

Copied to clipboard

Qian Wang, Jiajun Zhang, Lemao Liu, Guoping Huang, Chengqing Zong

Towards Efficient Dialogue Pre-training with Transferable and Interpretable Latent Structure (2022.emnlp-main)

Challenge:	Existing methods for machine translation require intensive keyboard interaction, which is inconvenient on mobile devices.
Approach:	They propose a touch-based editing method that is more flexible than keyboard-mouse-based translation postediting.
Outcome:	The proposed method significantly outperforms existing interactive translation methods on translation datasets and on post-editing datasets.

Copied to clipboard

Xueliang Zhao, Lemao Liu, Tingchen Fu, Shuming Shi, Dongyan Zhao, Rui Yan

Responsible & Trustworthy NLP

Challenge:	Existing models that use millions of parameters on massive data are inefficient and lack interpretability.
Approach:	They propose a model with a latent structure that is easily transferable from the general domain to downstream tasks in a lightweight and transparent way.
Outcome:	The proposed model performs better than four strong baseline models in terms of automatic and human evaluations and is 5x faster than the strongest baseline model.

An Empirical Study on Multiple Information Sources for Zero-Shot Fine-Grained Entity Typing (2021.emnlp-main)

Copied to clipboard

Yi Chen, Haiyun Jiang, Lemao Liu, Shuming Shi, Chuang Fan, Min Yang, Ruifeng Xu

Advancement in Graph Understanding: A Multimodal Benchmark and Fine-Tuning of Vision-Language Models (2024.acl-long)

Challenge:	Auxiliary information from multiple sources has been demonstrated to be effective in zero-shot fine-grained entity typing (ZFET) however, there is no comprehensive understanding of how to make better use of the existing information sources and how they affect the performance of ZFET.
Approach:	They propose a multi-source fusion model targeting auxiliary information from multiple sources to improve zero-shot fine-grained entity typing (ZFET)
Outcome:	The proposed model achieves 11.42% and 22.84% gains over state-of-the-art baselines on BBN and Wiki respectively with regard to macro F1 scores.

Copied to clipboard

Qihang Ai, Jiafan Li, Jincheng Dai, Jianwu Zhou, Lemao Liu, Haiyun Jiang, Shuming Shi

Multimodality

Challenge:	Graph data organizes complex relationships and interactions between objects . Graph neural networks (GNNs) are becoming more popular in graph learning .
Approach:	They propose a new paradigm for interactive and instructional graph data understanding and reasoning . they first evaluate the capabilities of public VLMs in graph learning from multiple aspects .
Outcome:	The proposed model achieves an accuracy increase of 5%-15% compared to baseline models . the best-performing model achieve scores comparable to Gemini in GPT-asissted Evaluation .

On the Word Alignment from Neural Machine Translation (P19-1)

Copied to clipboard

Xintong Li, Guanlin Li, Lemao Liu, Max Meng, Shuming Shi

TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild (2024.findings-acl)

Challenge:	Prior researches suggest that neural machine translation (NMT) captures word alignment through its attention mechanism, however, attention may fail to capture word alignment for some NMT models.
Approach:	They propose two methods to induce word alignment which are general and agnostic to specific NMT models.
Outcome:	The proposed methods induce much better word alignment than attention.

Copied to clipboard

Huayang Li, Siheng Li, Deng Cai, Longyue Wang, Lemao Liu, Taro Watanabe, Yujiu Yang, Shuming Shi

Multimodality

Challenge:	Large language models with instruction-following capabilities have revolutionized the field of artificial intelligence.
Approach:	They propose an annotation-free framework for empowering large language models with instruction-following capabilities.
Outcome:	The proposed framework generates multi-turn multimodal instruction-response conversations from a language model.

Investigating Data Variance in Evaluations of Automatic Machine Translation Metrics (2022.findings-acl)

Copied to clipboard

Jiannan Xiang, Huayang Li, Yahui Liu, Lemao Liu, Guoping Huang, Defu Lian, Shuming Shi

Segmenting Natural Language Sentences via Lexical Unit Analysis (2021.findings-emnlp)

Challenge:	Current evaluation methods focus on one dataset, e.g., Newstest dataset in each year’s WMT Metrics Shared Task.
Approach:	They propose to use a single dataset to evaluate the performance of automatic translation metrics.
Outcome:	The results show that the rankings of metrics vary when the evaluation is conducted on different datasets.

Copied to clipboard

Yangming Li, Lemao Liu, Shuming Shi

Syntactic Text Processing

Challenge:	Recent work on sequence segmentation models suffer from invalid predictions and a lack of consistency.
Approach:	They propose a unified span-based model that embeds every span and computes a score for each segmentation candidate.
Outcome:	The proposed model achieves state-of-the-art on 6 of the 3 tasks tested.

The Stochastic Parrot on LLM’s Shoulder: A Summative Assessment of Physical Concept Understanding (2025.naacl-long)

Copied to clipboard

Mo Yu, Lemao Liu, Junjie Wu, Tsz Ting Chung, Shunchi Zhang, Jiangnan Li, Dit-Yan Yeung, Jie Zhou

Challenge:	Recent years have witnessed remarkable advancements in large language models (LLMs) many researchers argue that LLMs may not * Equal contribution.
Approach:	They propose a task that summarises the memorization issue by using grid inputs that abstractly describe physical phenomena.
Outcome:	The proposed task alleviates the memorization issue by using grid-format inputs that abstractly describe physical phenomena.

DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models (2025.findings-emnlp)

Copied to clipboard

Tsz Ting Chung, Lemao Liu, Mo Yu, Dit-Yan Yeung

Unsupervised Keyphrase Extraction by Learning Neural Keyphrase Set Function (2023.findings-acl)

Challenge:	Existing logic reasoning benchmarks are limited in language diversity and their distributions are deviated from ideal distributions, which may lead to biased evaluation results.
Approach:	They propose a new logic benchmark DivLogicEval that uses natural sentences to evaluate logical reasoning .
Outcome:	The proposed evaluation metric mitigates bias and randomness inherent in LLMs.

Copied to clipboard

Mingyang Song, Haiyun Jiang, Lemao Liu, Shuming Shi, Liping Jing

Visualizing the Relationship Between Encoded Linguistic Information and Task Performance (2022.findings-acl)

Challenge:	Unsupervised keyphrase extraction is a task of extracting a keyphrase set that provides readers with highlevel information about the key ideas or important topics described in the document.
Approach:	They propose an unsupervised keyphrase extraction task that is a document-set matching problem instead of modeling the relevance between an individual phrase and the document.
Outcome:	The proposed model outperforms the state-of-the-art unsupervised keyphrase extraction baselines by a large margin.

Copied to clipboard

Jiannan Xiang, Huayang Li, Defu Lian, Guoping Huang, Taro Watanabe, Lemao Liu

Syntactic Text Processing

Challenge:	Recent studies show that encoding more syntactic information does not lead to better performance.
Approach:	They propose a method to optimize pareto-optimal models by formalizing it as a multi-objective optimization problem.
Outcome:	The proposed method is better than a baseline method on two NLP tasks.

Making Better Use of Training Corpus: Retrieval-based Aspect Sentiment Triplet Extraction via Label Interpolation (2023.findings-acl)

Copied to clipboard

Guoxin Yu, Lemao Liu, Haiyun Jiang, Shuming Shi, Xiang Ao

Understanding and Improving Hidden Representations for Neural Machine Translation (N19-1)

Challenge:	Existing methods to extract sentimental triplets are infeasible and counterproductive . aspect Sentiment Triplets Extraction (ASTE) task is an emerging sub-task of Aspect-based Sentimence Analysis .
Approach:	They propose a retrieval-based approach to the Aspect Sentiment Triplet Extraction task . they retrieve semantic similar triplets from the training corpus and interpolate their label information .
Outcome:	The proposed approach establishes a new state-of-the-art on the Aspect Sentiment Triplet Extraction task.

Copied to clipboard

Guanlin Li, Lemao Liu, Xintong Li, Conghui Zhu, Tiejun Zhao, Shuming Shi

Assessing Dialogue Systems with Distribution Distances (2021.findings-acl)

Challenge:	Existing studies have explored some methods for understanding hidden representations, but they have not sought to improve the translation quality rationally according to their understanding.
Approach:	They propose to construct a sequence of nested relative tasks and measure the feature generalization ability of the learned hidden representation over these tasks.
Outcome:	The proposed methods achieve consistent improvements (up to +1.3 BLEU) on two widely-used datasets.

Copied to clipboard

Jiannan Xiang, Yahui Liu, Deng Cai, Huayang Li, Defu Lian, Lemao Liu

Natural Language Interfaces

Challenge:	Existing evaluation metrics focus on turnlevel quality, which is not well suited for open-end dialogue tasks.
Approach:	They propose to measure the performance of a dialogue system by computing the distributionwise distance between its generated conversations and real-world conversations.
Outcome:	The proposed metrics correlate better with human judgments than existing metrics on dialogue systems.

SimCSE++: Improving Contrastive Learning for Sentence Embeddings from Two Perspectives (2023.emnlp-main)

Copied to clipboard

Jiahao Xu, Wei Shao, Lihui Chen, Lemao Liu

Understanding LLMs’ Fluid Intelligence Deficiency: An Analysis of the ARC Task (2025.naacl-long)

Challenge:	Experimental results show that combining both proposed methods leads to a gain of 1.8 points compared to the strong baseline SimCSE configured with BERT base.
Approach:	They propose a method to deal with dropout noise and a dimension-wise contrastive learning objective to address feature corruption.
Outcome:	The proposed method achieves 1.8 points compared to the strong baseline SimCSE and 1.4 points for DiffCSE.

Copied to clipboard

Junjie Wu, Mo Yu, Lemao Liu, Dit-Yan Yeung, Jie Zhou

Challenge:	Recent research on fluid intelligence assessments has highlighted significant deficiencies in LLMs’ abilities.
Approach:	They analyze the challenges LLMs face in demonstrating fluid intelligence through controlled experiments using the most representative ARC task as an example.
Outcome:	The proposed model shows that it lacks the ability to combine skill composition and abstract input formats and lacks left-to-right decoding.

Neural Machine Translation with Monolingual Translation Memory (2021.acl-long)

Copied to clipboard

Deng Cai, Yan Wang, Huayang Li, Wai Lam, Lemao Liu

Regularized Context Gates on Transformer for Machine Translation (2020.acl-main)

Challenge:	Existing work has shown that Translation Memory (TM) can boost the performance of Neural Machine Translation (NMT)
Approach:	They propose a framework that uses monolingual memory and performs learnable memory retrieval in a cross-lingual manner.
Outcome:	The proposed framework outperforms strong TM-augmented NMT baselines using bilingual TM and outperformed existing models in low-resource and domain adaptation scenarios.

Copied to clipboard

Xintong Li, Lemao Liu, Rui Wang, Guoping Huang, Max Meng

Neural Sequence Segmentation as Determining the Leftmost Segments (2021.naacl-main)

Challenge:	Context gates are effective to control the contributions from the source and target contexts in the recurrent neural network (RNN) based neural machine translation.
Approach:	They propose a method to identify source and target contexts and introduce a gate mechanism to control the contributions from source and targets in the advanced Transformer architecture.
Outcome:	The proposed model achieves an averaged gain of 1.0 BLEU score over a strong transformer baseline.

Copied to clipboard

Yangming Li, Lemao Liu, Kaisheng Yao

Syntactic Text Processing

Challenge:	Existing methods to segment sentences are mostly at token level, limiting their full potential to capture long-term dependencies.
Approach:	They propose a framework that incrementally segments natural language sentences at segment level.
Outcome:	The proposed framework outperforms baseline methods on syntactic chunking and Chinese part-of-speech tagging datasets.

Retrieval-Augmented Few-shot Text Classification (2023.findings-emnlp)

Copied to clipboard

Guoxin Yu, Lemao Liu, Haiyun Jiang, Shuming Shi, Xiang Ao

Information Retrieval

Challenge:	Existing methods for retrieval-augmented text classification are successful in the few-shot scenario with limited retrieval space.
Approach:	They propose to use EM-L and R-L to provide task-specific guidance to retrieval metric . they also propose to incorporate retrieved memory alongside parameters for better generalization .
Outcome:	The proposed methods perform better on the few-shot scenario with limited retrieval space.

Enhancing the Open-Domain Dialogue Evaluation in Latent Space (2021.findings-acl)

Copied to clipboard

Zhangming Chan, Lemao Liu, Juntao Li, Haisong Zhang, Dongyan Zhao, Shuming Shi, Rui Yan

Dialogue Systems & Conversational Agents

Challenge:	Existing methods to evaluate opendomain dialogues are limited due to the one-to-many nature of dialogues.
Approach:	They propose a self-supervised setting to obtain a smooth latent space that captures discourse-level context information and implicitly models more references in latent spaces.
Outcome:	The proposed method outperforms baseline methods on two real-world dialogue datasets.

Fast and Accurate Neural Machine Translation with Translation Memory (2021.acl-long)

Copied to clipboard

Qiuxiang He, Guoping Huang, Qu Cui, Li Li, Lemao Liu

Cross-lingual Contextualized Phrase Retrieval (2024.findings-emnlp)

Challenge:	Existing knowledge demonstrates the superiority of TM-based neural machine translation only on TM specialized tasks .
Approach:	They propose a translation memory-based approach to machine translation using a single bilingual sentence as its TM.
Outcome:	The proposed approach surpasses baselines on two general tasks and improves on the TM-specialized translation tasks.

Copied to clipboard

Huayang Li, Deng Cai, Zhi Qu, Qu Cui, Hidetaka Kamigaito, Lemao Liu, Taro Watanabe

Towards General Error Diagnosis via Behavioral Testing in Machine Translation (2023.findings-emnlp)

Challenge:	Phrase-level dense retrieval has shown many appealing characteristics in downstream NLP tasks.
Approach:	They propose a task formulation of dense retrieval, cross-lingual contextualized phrase retrieval . they extract pairs of cross-linguistic phrases using word alignment information .
Outcome:	The proposed task formulation surpasses baselines on the phrase retrieval task and a downstream task, i.e., machine translation, and achieves top-1 accuracy 13 points higher.

Copied to clipboard

Junjie Wu, Lemao Liu, Dit-Yan Yeung

Rethinking Word-Level Auto-Completion in Computer-Aided Translation (2023.emnlp-main)

Challenge:	Existing behavioral testing approaches only evaluate translation quality without references, restricting diagnosis to specific types of errors.
Approach:	They propose a bilingual translation pair generation based behavior testing framework that auto-generates test cases and pseudo-references to facilitate general error diagnosis.
Outcome:	The proposed framework can provide comprehensive and accurate behavioral testing results for general error diagnosis on machine translation systems.

Copied to clipboard

Xingyu Chen, Lemao Liu, Guoping Huang, Zhirui Zhang, Mingming Yang, Shuming Shi, Rui Wang

On the Evaluation Metrics for Paraphrase Generation (2022.emnlp-main)

Challenge:	Existing models for word-level auto-completion (WLAC) do not meet the criterion of good auto-completes.
Approach:	They propose a measurable criterion to address the question: what kind of words are good auto-completions? they propose an approach to enhance WLAC performance by promoting adherence to the cri-terion.
Outcome:	The proposed approach outperforms the top-performing system submitted to the WLAC shared tasks in WMT2022 while using significantly smaller model sizes.

Copied to clipboard

Lingfeng Shen, Lemao Liu, Haiyun Jiang, Shuming Shi

DistillCSE: Distilled Contrastive Learning for Sentence Embeddings (2023.findings-emnlp)

Challenge:	Existing evaluation metrics for paraphrase generation are not designed for the task, but adopted from other evaluation tasks.
Approach:	They propose a new evaluation metric for paraphrase generation that uses reference-based and reference-free metrics.
Outcome:	The proposed evaluation metric outperforms existing metrics and is more reliable than reference-based metrics.

Copied to clipboard

Jiahao Xu, Wei Shao, Lihui Chen, Lemao Liu

Selection-p: Self-Supervised Task-Agnostic Prompt Compression for Faithfulness and Transferability (2024.findings-emnlp)

Challenge:	Existing approaches to sentence embeddings are based on contrastive learning (CL) .
Approach:	They propose a framework which performs contrastive learning under the self-training paradigm with knowledge distillation and propose 'Group-P shuffling strategy' and averaging logits from multiple teacher components.
Outcome:	The proposed framework outperforms many strong baseline methods and yields a new state-of-the-art performance.

Copied to clipboard

Tsz Ting Chung, Leyang Cui, Lemao Liu, Xinting Huang, Shuming Shi, Dit-Yan Yeung

Low-Resource NLP

Challenge:	Large Language Models (LLMs) have demonstrated impressive capabilities when leveraging in-context learning.
Approach:	They propose a method that discretizes uninformative tokens using a self-supervised pre-training technique.
Outcome:	The proposed method achieves state-of-the-art performance across classification tasks while requiring only 0.8% decrease in performance.

SORTIE: Dependency-Aware Symbolic Reasoning for Logical Data-to-text Generation (2023.findings-acl)

Copied to clipboard

Xueliang Zhao, Tingchen Fu, Lemao Liu, Lingpeng Kong, Shuming Shi, Rui Yan

Multimodality

Challenge:	Existing studies on logical data-to-text generation rely on neural language models to generate the final table description, but they have difficulty working out key entities in the description.
Approach:	They propose a symbolic reasoning framework that reasons out each entity in the table description with a table-compatible programming language.
Outcome:	The proposed framework outperforms existing methods on three datasets and three backbones with an absolute improvement of 5.7%11.5% on SP-Acc.

Context Consistency between Training and Inference in Simultaneous Machine Translation (2024.acl-long)

Copied to clipboard

Meizhi Zhong, Lemao Liu, Kehai Chen, Mingming Yang, Min Zhang

Disperse-Then-Merge: Pushing the Limits of Instruction Tuning via Alignment Tax Reduction (2024.findings-acl)

Challenge:	Simultaneous machine translation (SiMT) aims to yield a partial translation with a monotonically growing source-side context.
Approach:	They propose a training approach that encourages consistent context usage between training and inference by optimizing translation quality and latency as bi-objectives and exposing the predictions to the model during the training.
Outcome:	The proposed system outperforms existing SiMT systems with context inconsistency for the first time.

Copied to clipboard

Tingchen Fu, Deng Cai, Lemao Liu, Shuming Shi, Rui Yan

A Pretraining Numerical Reasoning Model for Ordinal Constrained Question Answering on Knowledge Base (2021.findings-emnlp)

Challenge:	Pre-trained language models may not follow human instructions and produce toxic, hallucinated, or biased content.
Approach:	They propose a disperse-then-merge framework that dispersers instruction-following data into portions and trains multiple sub-models using different data portions.
Outcome:	The proposed framework outperforms data curation and training regularization on standard knowledge and reasoning benchmarks.

Copied to clipboard

Yu Feng, Jing Zhang, Gaole He, Wayne Xin Zhao, Lemao Liu, Quan Liu, Cuiping Li, Hong Chen

Situated Embedding Models for Context-Aware Dense Retrieval (2026.acl-short)

Challenge:	Existing knowledge bases (KBs) can explicitly facilitate the QA process.
Approach:	They propose a numerical reasoning model pretraining NumGNN and NumTransformer, guided by explicit self-supervision signals, to enhance numerical reasoning ability for IR-based KBQA models.
Outcome:	Extensive experiments on two KBQA benchmarks confirm the effectiveness of the proposed model.

Copied to clipboard

Junjie Wu, Jiangnan Li, Yuqing Li, Lemao Liu, Liyan Xu, Jiwei Li, Dit-Yan Yeung, Jie Zhou, Mo Yu

Representation Learning

Challenge:	Existing embedding models are not well-equipped to encode situated context effectively, i.e., situating a chunk’s meaning within its context.
Approach:	They propose to represent short chunks in a way that is conditioned on a broader context window to enhance retrieval performance.
Outcome:	The proposed model outperforms state-of-the-art embedding models on a book-plot retrieval dataset.

Rethinking Translation Memory Augmented Neural Machine Translation (2023.findings-acl)

Copied to clipboard

Hongkun Hao, Guoping Huang, Lemao Liu, Zhirui Zhang, Shuming Shi, Rui Wang

On the Compositional Generalization in Versatile Open-domain Dialogue (2023.acl-long)

Challenge:	Existing approaches to enhance neural machine translation (NMT) by using a TM have been reported to be effective.
Approach:	They propose a translation memory augmented neural machine translation model that is good at fitting data but more sensitive to fluctuations in training data.
Outcome:	The proposed model achieves consistent gains over conventional and existing models under two variance-preferable scenarios as well as the high resource scenario.

Copied to clipboard

Tingchen Fu, Xueliang Zhao, Lemao Liu, Rui Yan

Dialogue Systems & Conversational Agents

Challenge:	Existing approaches to multi-task learning suffer from interference among datasets or fail to effectively reuse knowledge and skills learned from other datasets.
Approach:	They propose a sparsely activated modular network with a well-rounded set of operators and instantiate each operator with an independent module.
Outcome:	The proposed model outperforms state-of-the-art supervised approaches on 4 datasets with only 10% training data thanks to the modular architecture and multi-task learning.

On Synthetic Data for Back Translation (2022.naacl-main)

Copied to clipboard

Jiahao Xu, Yubin Ruan, Wei Bi, Guoping Huang, Shuming Shi, Lihui Chen, Lemao Liu

Fine-grained Entity Typing without Knowledge Base (2021.emnlp-main)

Challenge:	Existing studies on back translation (BT) focus on beam search or random sampling . a new method to generate synthetic data with a backward model is proposed to improve BT performance.
Approach:	They propose a method to generate synthetic data to trade off quality and importance factors . back translation (BT) is one of the most significant technologies in NMT research fields .
Outcome:	The proposed method outperforms the baseline methods on WMT14 DE-EN, EN-DE, and RU-EN benchmark tasks.

Copied to clipboard

Jing Qian, Yibin Liu, Lemao Liu, Yangming Li, Haiyun Jiang, Haisong Zhang, Shuming Shi

Knowledge Representation

Challenge:	Existing work on fine-grained entity typing (FET) relies on knowledge bases as distant supervision, but lack of or incompleteness of KB can hinder training.
Approach:	They propose a two-step framework that trains FET models without accessing any knowledge base.
Outcome:	The proposed framework achieves competitive performance with respect to the models trained on the original KB-supervised datasets.

Engage the Public: Poll Question Generation for Social Media Posts (2021.acl-long)

Copied to clipboard

Zexin Lu, Keyang Ding, Yuji Zhang, Jing Li, Baolin Peng, Lemao Liu

Target Foresight Based Attention for Neural Machine Translation (N18-1)

Challenge:	a novel application to generate poll questions for social media posts offers an easy way to hear the public's voice . for the silent majority, they tend to read others' messages instead of voicing their opinions with words .
Approach:	They propose to encode user comments and discover latent topics therein as contexts to generate poll questions for social media posts.
Outcome:	The proposed model outperforms popular models without exploiting topics from comments . human evaluations show it can generate high-quality polls useful to draw user engagements .

Copied to clipboard

Xintong Li, Lemao Liu, Zhaopeng Tu, Shuming Shi, Max Meng

Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization (D19-1)

Challenge:	Empirical experiments on Chinese-to-English and Japanese-to English datasets show that the proposed attention model delivers significant improvements in terms of alignment error rate and BLEU.
Approach:	They propose to explicitly access the target foresight word in the attention model to improve alignment and translation accuracy.
Outcome:	Empirical results show that the proposed model improves alignment error rate and BLEU on Chinese-to-English and Japanese-toEnglish datasets.

Copied to clipboard

Guanlin Li, Lemao Liu, Guoping Huang, Conghui Zhu, Tiejun Zhao