Papers by Hai Chen

25 papers
Multimodal Fusion and Coherence Modeling for Video Topic Segmentation (2025.findings-acl)

Copied to clipboard

Challenge: Traditional video topic segmentation methods struggle to discern topical transitions . supervised approaches have improved performance on video action or scene segmentation .
Approach: They propose a new task for video topic segmentation that enhances multimodality alignment and fusion by exploring different architectures using Cross-Attention and Mixture of Experts.
Outcome: The proposed model improves on educational videos, in the form of lectures . it combines cross-attention and mixture of experts to strengthen multimodality alignment and fusion .
Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling (2023.emnlp-main)

Copied to clipboard

Challenge: Recent supervised neural models have greatly promoted the development of topic segmentation, but the deeper relationship between coherence and topic segmenting is underexplored.
Approach: They propose to use topic-aware Sentence Structure Prediction and Contrastive Semantic Similarity Learning to capture coherence from logical structure and semantic similarity perspectives to further improve topic segmentation performance.
Outcome: The proposed approach outperforms state-of-the-art methods on WIKI-727K and achieves an average relative reduction of 4.3% on Pk on WikiSection.
Lattice-Based Transformer Encoder for Neural Machine Translation (P19-1)

Copied to clipboard

Challenge: Neural machine translation (NMT) takes deterministic sequences for source representations. However, word-level or subword-level segmentation has multiple choices to split a source sequence with different word segmentors or different subword vocabulary sizes.
Approach: They propose lattice-based encoders to explore effective word or subword representations in an automatic way during training.
Outcome: The proposed encoders can explore effective word or subword representation in an automatic way during training.
MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training (2026.acl-long)

Copied to clipboard

Challenge: Existing systems for multi-turn Text-to-SQL are limited to a short-horizon paradigm, generating a query per turn without execution, explicit verification, and refinement, which leads to non-executable or incoherent outputs.
Approach: They propose to train an agentic training framework for long-horizon multi-turn Text-to-SQL that uses a Markov Decision Process to generate a query per turn without execution, explicit verification, and refinement.
Outcome: Experiments on CoSQL and SParC show that MTSQL-R1 consistently outperforms strong baselines, highlighting the importance of environment-driven verification and memory-guided refinement for conversational semantic parsing.
Omni-Chart-600K: A Comprehensive Dataset of Chart Types for Chart Understanding (2025.findings-naacl)

Copied to clipboard

Challenge: Existing chart-related training methods lack capabilities in information extraction, mathematical reasoning, and understanding of multiple chart types.
Approach: They propose a two-stage training strategy and method for jointly training a vision encoder tailored for multi-type charts to address the deficiencies in chart types and limited scope of chart tasks in existing datasets.
Outcome: The proposed dataset includes 21 diverse chart types and tasks, including data retrieval and mathematical reasoning.
Modeling Hierarchical Reasoning Chains by Linking Discourse Units and Key Phrases for Reading Comprehension (2022.coling-1)

Copied to clipboard

Challenge: Existing methods of logical reasoning focus on entity-aware information but ignore hierarchical relations that may even have mutual effects.
Approach: They propose a holistic graph network that deals with context at both discourse-level and word-level as the basis for logical reasoning.
Outcome: The proposed method improves on logical reasoning QA datasets and natural language inference datasets.
Forging Multiple Training Objectives for Pre-trained Language Models via Meta-Learning (2022.findings-emnlp)

Copied to clipboard

Challenge: Empirical studies show that learning multiple training objectives in a single model makes the learned language representation barely converge to the desired optimum.
Approach: They propose a meta-learning-based adaptive sampler which learns latent sampling pattern on arbitrary pre-training objectives.
Outcome: Empirical studies show that learning multiple objectives in a single model makes it difficult to achieve the desired optimum.
Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction (2021.findings-acl)

Copied to clipboard

Challenge: Existing approaches to extract triplets from sentences neglect the mutual information between aspects and have the problem of error propagation.
Approach: They propose a Semantic and Syntactic Enhanced aspect Sentiment triplet Extraction model to exploit the syntactical and semantic relationships between the triplet elements and jointly extract them.
Outcome: The proposed model outperforms existing methods on four benchmark datasets and significantly outperformed existing approaches.
Abstractive Text-Image Summarization Using Multi-Modal Attentional Hierarchical RNN (D18-1)

Copied to clipboard

Challenge: Recent research shows the strength of the Encoder-Decoder model in text summarization.
Approach: They propose to use the attentional hierarchical Encoder-Decoder model to summarize a text document and its accompanying images simultaneously and then to align the sentences and images in summaries.
Outcome: The proposed model outperforms the existing methods that do not consider images . it can generate informative summaries of images, and it can be used to summarize documents .
Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decoding (2025.emnlp-main)

Copied to clipboard

Challenge: In-Context Learning (ICL) is a key method in prompt engineering, but its long retrieved contexts and limited token throughput will slow reasoning speeds.
Approach: They propose a method that leverages the overlap between context and model output to generate drafts from the context.
Outcome: The proposed method achieves the highest mean speedup on Vicuna-7B, Llama2-7B-Chat, and Llma3-8B-Instruct tasks.
Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection (2024.naacl-long)

Copied to clipboard

Challenge: Instruction-tuned Large Language Models (LLMs) can modulate responses based on human instructions, but they can be maliciously steered to impact society in subtle but persistent ways.
Approach: They propose a backdoor attack setting that allows an attacker to inject a virtual prompt into an LLM to steer it without any explicit injection at its input.
Outcome: The proposed method is able to poison the model's instruction tuning data and show that it is highly effective in steering the model.
Skeletons Matter: Dynamic Data Augmentation for Text-to-Query (2025.emnlp-main)

Copied to clipboard

Challenge: Existing studies focus on a single query language, resulting in limited generalizability . a new task paradigm is proposed to unify semantic parsing tasks across different query languages .
Approach: They propose a task paradigm that unifies parsing tasks across query languages . they identify query skeletons as a shared optimization target of Text-to-Query tasks .
Outcome: The proposed method achieves state-of-the-art performance using only a small amount of synthesized data.
A DQN-based Approach to Finding Precise Evidences for Fact Verification (2021.acl-long)

Copied to clipboard

Challenge: Existing methods for fact verification do not target the retrieval of precise evidences.
Approach: They propose a DQN-based approach to retrieval of precise evidences . they propose best thresholds for determining the true labels of computed evidences.
Outcome: The proposed method improves accuracy of fact verification by reducing label bias . it can retrieve evidence consisting of the first two sentences, but it can contain unnecessary sentences .
OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation (2025.acl-long)

Copied to clipboard

Challenge: Full-duplex spoken dialogue systems allow simultaneous bidirectional communication . low latency and natural interactions in full-duplice systems remains a challenge .
Approach: They propose a multi-stage post-training scheme that adapts a text large language model into a speech-text dialogue LLM.
Outcome: The proposed model can model human conversation behaviors with low latency and natural interactions with low delay.
Jointly Identifying Rhetoric and Implicit Emotions via Multi-Task Learning (2021.findings-acl)

Copied to clipboard

Challenge: Experimental results validate the benefit of the proposed model over the state-of-the-art baselines for rhetoric and emotion identification tasks.
Approach: They propose a multi-task learning framework that can encode categorical correlation between tasks to improve rhetoric and emotion identification problem.
Outcome: The proposed model can encode the categorical correlation between tasks to improve rhetoric and emotion identification problem.
Label-Free Distant Supervision for Relation Extraction via Knowledge Graph Embedding (D18-1)

Copied to clipboard

Challenge: Existing methods to generate large scale labeled data for relation extraction produce noisy relation labels when there are multiple relationships between entities.
Approach: They propose a method which assumes that a pair of entities appears in a Knowledge Graph and trains a relation classifier.
Outcome: The proposed method performs well in the current distant supervision dataset.
Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings (2023.emnlp-main)

Copied to clipboard

Challenge: Prior studies diagnose the anisotropy problem in sentence embeddings from pre-trained language models without fine-tuning.
Approach: They propose an unsupervised method that weights words with model-based importance estimations and computes the weighted average of word representations from pre-trained models as sentence embeddings.
Outcome: Empirical evaluations show that the proposed method can alleviate the anisotropy problem and improve various pre-trained models on the STS benchmarks.
Enhancing Cross-lingual Natural Language Inference by Prompt-learning from Cross-lingual Templates (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for enhancing pre-trained cross-lingual language models with additional data are rare in practice, especially for low-resource languages.
Approach: They propose a prompt-learning framework for enhancing cross-lingual natural language inference by constructing cloze-style questions through cross-linguistic templates.
Outcome: The proposed framework significantly outperforms existing models under cross-lingual transfer settings.
SANCL: Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive Learning (2022.coling-1)

Copied to clipboard

Challenge: e-commerce has become a research hotspot for review helpfulness prediction . a new approach to help predict helpfulness of multimodal product reviews is proposed .
Approach: They propose a machine learning task to identify helpfulness of multimodal product reviews . they use a probe-based strategy to enforce high attention weights on regions of greater significance .
Outcome: The proposed model achieves state-of-the-art performance with lower memory consumption on two benchmark datasets with three categories.
ControlSpeech: Towards Simultaneous and Independent Zero-shot Speaker Cloning and Zero-shot Language Style Control (2025.acl-long)

Copied to clipboard

Challenge: Prior zero-shot TTS models only mimic the speaker’s voice without further control and adjustment capabilities while prior controllable TTS systems cannot perform speaker-specific voice generation.
Approach: They propose a style control module that captures codec representations corresponding to timbre, content, and style in a discrete decoupling codec space.
Outcome: The proposed system can fully clone the speaker's voice and perform speech-specific adjustment and control functions.
Finding the Sweet Spot: Preference Data Construction for Scaling Preference Optimization (2025.acl-long)

Copied to clipboard

Challenge: Large language models generate unintended outputs due to their unsupervised nature.
Approach: They propose a method to construct preference pairs of selected and rejected LLMs by repeated random sampling to improve alignment performance.
Outcome: The proposed method improves performance as the sample size increases.
Multi-label and Multi-target Sampling of Machine Annotation for Computational Stance Detection (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for data-driven annotations require domain-specific and task-aligned supervision.
Approach: They propose a multi-label and multi-target sampling strategy to optimize the annotation quality.
Outcome: The proposed method significantly improves performance and learning efficacy on the benchmark stance detection corpora.
Syntax in End-to-End Natural Language Processing (2021.emnlp-tutorials)

Copied to clipboard

Challenge: tutorial focuses on syntactic parsing and syntax in end-to-end natural language processing (NLP) tasks.
Approach: tutorial will introduce syntactic parsing and the role of syntax in end-to-end natural language processing (NLP) tasks.
Outcome: This tutorial will introduce the background and the latest progress of syntactic parsing and SRL/NMT.
LESA: Learnable LLM Layer Scaling-Up (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for depth scaling-up rely on empirical heuristic rules for layer duplication, resulting in poor initialization and slower convergence during continual pre-training.
Approach: They propose a method for learning latent parameters between layers by concatenating parameters from each layer and applying Singular Value Decomposition.
Outcome: Experiments show that LESA outperforms baseline models with less than half the cost of existing methods.
Harnessing the Power of Large Language Model for Uncertainty Aware Graph Processing (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for graph processing rely on assumptions about data relations that are inadequate when handling large and complex graph data.
Approach: They propose a large language model enhanced by an uncertainty-aware module to provide a confidence score on the generated graph data.
Outcome: The proposed approach surpasses state-of-the-art algorithms by a substantial margin on ten datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations