Papers by Qiaoming Zhu

Building a Macro Chinese Discourse Treebank (L18-1)

Challenge:	Experimental results show that our model outperforms the SOTA baselines due to the encoding length limitation.
Approach:	They propose a longformer-based encoder and an encoder with a trigger-mask mechanism to learn sentence-level embeddings based on local context.
Outcome:	The proposed model outperforms the baselines on the KBP 2017 dataset.

Copied to clipboard

Xiaomin Chu, Feng Jiang, Sheng Xu, Qiaoming Zhu

Syntactic Text Processing

Challenge:	Discourse structure analysis is an important research topic in natural language processing.
Approach:	They propose to construct a macro discourse structure framework and annotate 147 Newswire articles.
Outcome:	The proposed framework can lay the foundation for further analysis of macro discourse structure.

CorefPrompt: Prompt-based Event Coreference Resolution by Measuring Event Type and Argument Compatibilities (2023.emnlp-main)

Copied to clipboard

Sheng Xu, Peifeng Li, Qiaoming Zhu

Chinese Paragraph-level Discourse Parsing with Global Backward and Local Reverse Reading (2020.coling-main)

Challenge:	Existing methods for event coreference resolution (ECR) do not leverage human-summarized rules to guide the model.
Approach:	They propose to transform ECR into a cloze-style MLM task using a prompt-based approach . they introduce two auxiliary prompt tasks, event-type compatibility and argument compatibility .
Outcome:	The proposed method performs well in a state-of-the-art (SOTA) benchmark.

Copied to clipboard

Feng Jiang, Xiaomin Chu, Peifeng Li, Fang Kong, Qiaoming Zhu

Document-Level Event Factuality Identification via Adversarial Neural Network (N19-1)

Challenge:	Existing methods on discourse parsing in English suffer from long discourse units and fewer explicit connectives.
Approach:	They propose to use two reading modes to construct Chinese paragraph level discourse trees.
Outcome:	The proposed model outperforms baselines on Chinese discourse trees.

Copied to clipboard

Zhong Qian, Peifeng Li, Qiaoming Zhu, Guodong Zhou

Robustness in NLP

Challenge:	Document-level event factuality identification is crucial for discourse understanding in NLP . identifying document-level factual of events requires comprehensive understanding of documents .
Approach:	They propose to construct a corpus annotated with document- and sentence-level event factuality information on English and Chinese texts.
Outcome:	The proposed model outperforms baselines on the constructed corpus.

Improving Dialogue Discourse Parsing through Discourse-aware Utterance Clarification (2025.acl-long)

Copied to clipboard

Yaxin Fan, Peifeng Li, Qiaoming Zhu

Multi-Faceted Self-Consistent Preference Alignment for Query Rewriting in Conversational Search (2026.findings-acl)

Challenge:	Extensive experiments on the STAC and Molweni datasets demonstrate that our approach effectively resolves ambiguities and significantly outperforms the state-of-the-art (SOTA) baselines.
Approach:	They propose a Discourse-aware Clarification Module (DCM) that generates clarifications for the parser through systematic clarification type reasoning and discourse goal reasoning.
Outcome:	Extensive experiments on the STAC and Molweni datasets demonstrate that the proposed module significantly outperforms the state-of-the-art (SOTA) framework.

Copied to clipboard

Zhiyu Cao, Peifeng Li, Qiaoming Zhu

Employing Text Matching Network to Recognise Nuclearity in Chinese Discourse (C18-1)

Challenge:	Existing approaches to rewrite ambiguous queries ignore feedback from query rewriting, passage retrieval and response generation in the rewritten process.
Approach:	They propose to construct self-consistent preference alignment data to generate more diverse rewritten queries.
Outcome:	The proposed method is effective in both in- and out-of-distribution scenarios.

Copied to clipboard

Sheng Xu, Peifeng Li, Guodong Zhou, Qiaoming Zhu

Challenge:	Experimental results show that nuclearity recognition is a challenging task in Chinese discourse parsing due to the need for more deep semantic information.
Approach:	They propose a text matching network that encodes discourse units and paragraphs by combining Bi-LSTM and CNN to capture global dependency information and local n-gram information.
Outcome:	The proposed model outperforms baselines on the Chinese Discourse TreeBank . the proposed model is based on a novel text matching network .

Enhancing Goal-oriented Proactive Dialogue Systems via Consistency Reflection and Correction (2025.acl-long)

Copied to clipboard

Didi Zhang, Yaxin Fan, Peifeng Li, Qiaoming Zhu

A Distance-Aware Multi-Task Framework for Conversational Discourse Parsing (2022.coling-1)

Challenge:	Unlike traditional dialogue systems, goal-oriented proactive dialogue systems focus on achieving specific objectives by actively guiding and anticipating user needs.
Approach:	They propose a model-agnostic two-stage Consistency Reflection and Correction framework that allows the model to reflect on discrepancies between generated responses and dialogue contexts and suggest possible corrections.
Outcome:	The proposed framework significantly improves the consistency between generated responses and dialogue contexts on three datasets.

Copied to clipboard

Yaxin Fan, Peifeng Li, Fang Kong, Qiaoming Zhu

Employing Discourse Coherence Enhancement to Improve Cross-Document Event and Entity Coreference Resolution (2025.acl-long)

Challenge:	Existing studies have focused on graph-based and transition-based discourse parsing, but no study has investigated the advantages of both paradigms for conversational discourse paring.
Approach:	They propose a distance-aware multi-task framework that incorporates the strengths of transition-based paradigms to facilitate conversational discourse parsing.
Outcome:	The proposed framework improves the graph-based paradigm on long-distance dependency links.

Copied to clipboard

Xinyu Chen, Peifeng Li, Qiaoming Zhu

Factual Relation Discrimination for Factuality-oriented Abstractive Summarization (2023.findings-emnlp)

Challenge:	Existing work on cross-document coreference resolution focuses on within-document events and entities, but cross-doc mentions lack such critical contexts.
Approach:	They propose a task to enhance the discourse coherence between two cross-document mentions by adding coherent texts to a document to form a new coherent document.
Outcome:	The proposed method outperforms state-of-the-art baselines on three popular datasets.

Copied to clipboard

Zhiguang Gao, Peifeng Li, Feng Jiang, Xiaomin Chu, Qiaoming Zhu

Summarization

Challenge:	Existing factuality-oriented abstractive summarization models only consider the integration of factual information and ignore the causes of factuual errors.
Approach:	They propose a factuality-oriented abstractive summarization model that can identify the causes of factual errors.
Outcome:	The proposed model outperforms state-of-the-art models in factual metrics.

Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch (2025.acl-long)

Copied to clipboard

Yuyang Ding, Xinyu Shi, Xiaobo Liang, Juntao Li, Zhaopeng Tu, Qiaoming Zhu, Min Zhang

Discourse Coherence and Response-Guided Context Rewriting for Multi-Party Dialogue Generation (2026.acl-long)

Challenge:	Existing methods to improve the mathematical reasoning capabilities of Large Language Models (LLMs) are limited due to the proprietary nature of the data.
Approach:	They propose a data synthesis method that generates large-scale mathematical reasoning datasets using lightweight 7B-scale models.
Outcome:	The proposed method outperforms existing open-source datasets in both in-domain and out-of-domain evaluations and shows improvements in code reasoning tasks.

Copied to clipboard

Zhiyu Cao, Peifeng Li, Qiaoming Zhu

Text Generation

Challenge:	Existing research on multi-party dialogue generation has focused on structural information inherent in dialogues, but colloquial expressions and incomplete utterances often impede comprehension and weaken the fidelity of dialogue structure representations.
Approach:	They propose a framework to improve multi-party dialogue generation through dialogue context rewriting using two complementary feedback signals to construct preference data for both context & response generation.
Outcome:	The proposed framework improves multi-party dialogue generation through dialogue context rewriting.

Incomplete Utterance Rewriting with Editing Operation Guidance and Utterance Augmentation (2024.emnlp-main)

Copied to clipboard

Zhiyu Cao, Peifeng Li, Yaxin Fan, Qiaoming Zhu

Paraphrasing

Challenge:	Existing generation methods on Incomplete Utterance Rewriting (IUR) can generate coherent utterances, but they often include irrelevant and redundant tokens in rewritten utteras .
Approach:	They propose a multi-task learning framework that uses editing operation labels to guide generation model to focus on critical tokens in dialogue context.
Outcome:	The proposed model outperforms state-of-the-art models on open-domain and task-oriented dialogues on three datasets.

Improving Multi-party Dialogue Generation via Topic and Rhetorical Coherence (2024.emnlp-main)

Copied to clipboard

Yaxin Fan, Peifeng Li, Qiaoming Zhu

MCDTB: A Macro-level Chinese Discourse TreeBank (C18-1)

Challenge:	Existing studies on multi-party dialogue generation focus on the reply-to structure of dialogue histories, but they neglect the coherence between generated responses and target utterances.
Approach:	They propose a Reinforcement Learning approach emphasizing Topic and Rhetorical Coherence to enhance the model's perception of coherence with the target utterance.
Outcome:	The proposed approach significantly outperforms the state-of-the-art baselines on two popular datasets.

Copied to clipboard

Feng Jiang, Sheng Xu, Xiaomin Chu, Peifeng Li, Qiaoming Zhu, Guodong Zhou

Syntactic Text Processing

Challenge:	Discourse analysis is becoming increasingly important in the field of natural language processing.
Approach:	They propose to annotate macro discourse information and additional discourse information to make annotation more objective and accurate.
Outcome:	The results show that the annotations are more objective and accurate than the previous ones.

Document-level Event Factuality Identification via Machine Reading Comprehension Frameworks with Transfer Learning (2022.coling-1)

Copied to clipboard

Zhong Qian, Heng Zhang, Peifeng Li, Qiaoming Zhu, Guodong Zhou

Language Models

Challenge:	Document-level Event Factuality Identification (DEFI) is a fundamental and crucial task in NLP.
Approach:	They propose a framework for document-level event factuality identification (DEFI) they propose to use Span-Extraction and Multiple-Choice to model DEFI as machine reading comprehension tasks .
Outcome:	The proposed model outperforms state-of-the-art models on a document-based event factuality task . it uses Span-Extraction (Ext) and Multiple-Choice (Mch) knowledge to extract knowledge from large-scale MRC corpus .

Winnowing Knowledge for Multi-choice Question Answering (2021.findings-emnlp)

Copied to clipboard

Yeqiu Li, Bowei Zou, Zhifeng Li, Ai Ti Aw, Yu Hong, Qiaoming Zhu

Enhancing Goal-oriented Proactive Dialogue Systems via Dynamic Multi-dimensional Consistency Optimization (2025.findings-emnlp)

Challenge:	Existing reasoning models suffer from noises in retrieved knowledge . encoding methods that use commonsense knowledge are less effective .
Approach:	They propose a method which conducts interception and soft filtering to reduce noise . they use commonsense knowledge from Wikipedia and ConceptNet to encode questions and options .
Outcome:	The proposed method improves on commonsense question answering tasks compared to baselines . it is able to conduct interception and soft filtering to shield the encoder from noise .

Copied to clipboard

Didi Zhang, Yaxin Fan, Peifeng Li, Qiaoming Zhu

Simulating Dual-Process Thinking in Dialogue Topic Shift Detection (2025.coling-main)

Challenge:	Existing work on goal-oriented proactive dialogue systems failed to address the multi-dimensional consistency issue between generated responses and key contextual elements.
Approach:	They propose a Dynamic Multi-dimensional Consistency Reinforcement Learning framework which measures the impact of each consistency dimension on overall dialogue quality and provides feedback to improve response quality.
Outcome:	The proposed framework significantly improves the consistency of generated responses on two datasets.

Copied to clipboard

Huiyao Wang, Peifeng Li, Yaxin Fan, Qiaoming Zhu

Generative Reward Modeling via Synthetic Criteria Preference Learning (2025.acl-long)

Challenge:	Existing methods for topic shift detection focus on shallow local reasoning, overlooking the importance of considering the global historical structure and local details to elucidate the underlying causes of topic shift.
Approach:	They propose a dual-process theory for dialogue topic shift detection that employs Large Language Models to extract and store the global topic structure of historical dialogue, while a reasoning module introduces a LLM to generate reasoning samples between the response and the most recent topic of historical dialog.
Outcome:	The proposed framework outperforms the state-of-the-art on three public datasets and is based on a dual-process theory.

Copied to clipboard

Xiaobo Liang, Haoke Zhang, Juntao Li, Kehai Chen, Qiaoming Zhu, Min Zhang

Incorporating Temporal Coherence to Cross-Document Event Coreference Resolution (2026.acl-long)

Challenge:	Generative Reward Models (GenRMs) leverage synthesized Chains of Thought (CoT) but this approach introduces risks of overoptimization due to the inability to guarantee the correctness of the CoTs.
Approach:	They propose a criteria-based preference tree for GenRMs that uses chain of thought to generate reasoning . they show that synthesized data can be learned using a long CoT format .
Outcome:	The proposed model shows significant improvements over baselines on multiple human preference benchmarks.

Copied to clipboard

Xinyu Chen, Peifeng Li, Qiaoming Zhu

Cross-Document Event Coreference Resolution on Discourse Structure (2023.emnlp-main)

Challenge:	Existing approaches focus on enhancing semantic coherence between event mentions, but they overlook the critical aspect of temporal coherency.
Approach:	They propose a Temporal Cohorence-driven event coreference framework that explicitly models temporal constraints by constructing a temporal event graph and a GNN to resolve conflicts.
Outcome:	Experiments on the ECB+, GVC, WEC, and ECb+META datasets show that CohTP outperforms state-of-the-art methods.

Copied to clipboard

Xinyu Chen, Sheng Xu, Peifeng Li, Qiaoming Zhu

ICR: Iterative Clarification and Rewriting for Conversational Search (2025.emnlp-main)

Challenge:	Experimental results show that our proposed model outperforms several baselines and achieves the competitive performance with the start-of-the-art baselines.
Approach:	They propose to use discourse rhetorical structure constructor to construct tree structures to represent documents and a multi-layer perceptron to capture similarities of event mention pairs.
Outcome:	The proposed model outperforms baselines and achieves competitive performance with the start-of-the-art baselines.

Copied to clipboard

Zhiyu Cao, Peifeng Li, Qiaoming Zhu

Topic Tensor Network for Implicit Discourse Relation Recognition in Chinese (P19-1)

Challenge:	Conversational Query Rewriting (CQR) is a key step in conversational question answering . it aims to rewrite vague queries into de-contextualized queries, thereby promoting conversational search.
Approach:	They propose an iterative rewriting scheme that pivots on clarification questions . they propose to rewrite queries into de-contextualized queries to promote conversational search .
Outcome:	The proposed framework improves retrieval performance on two popular datasets.

Copied to clipboard

Sheng Xu, Peifeng Li, Fang Kong, Qiaoming Zhu, Guodong Zhou

Challenge:	Currently, most studies on implicit discourse relation recognition use sentence-level representations . Chinese is a paratactic language that tends to pro-drop clause connectives .
Approach:	They propose a topic tensor network to recognize Chinese implicit discourse relations with both sentence-level and topic-level representations.
Outcome:	The proposed model outperforms state-of-the-art models in micro and macro F1 scores on a Chinese discourse corpus.

Self-regulation: Employing a Generative Adversarial Network to Improve Event Detection (P18-1)

Copied to clipboard

Yu Hong, Wenxuan Zhou, Jingli Zhang, Guodong Zhou, Qiaoming Zhu

Robustness in NLP

Challenge:	Recent studies show that neural networks can be used for event detection but can be contaminated by spurious features.
Approach:	They propose a self-regulated learning approach by utilizing a generative adversarial network to generate spurious features.
Outcome:	The proposed method is highly effective and adaptable on the ACE 2005 and TAC-KBP 2015 corpora.

Advancing Topic Segmentation and Outline Generation in Chinese Texts: The Paragraph-level Topic Representation, Corpus, and Benchmark (2024.lrec-main)

Copied to clipboard

Feng Jiang, Weihao Liu, Xiaomin Chu, Peifeng Li, Qiaoming Zhu, Haizhou Li

Joint Modeling of Structure Identification and Nuclearity Recognition in Macro Chinese Discourse Treebank (C18-1)

Challenge:	Compared with sentence-level topic structure, paragraph-level topics can grasp and understand the context of a document from a higher level.
Approach:	They propose a hierarchical paragraph-level topic structure representation with three layers to guide corpus construction.
Outcome:	The proposed method achieves the largest Chinese paragraph-level topic structure corpus, achieving high quality.

Copied to clipboard

Xiaomin Chu, Feng Jiang, Yi Zhou, Guodong Zhou, Qiaoming Zhu

Improving Dialogue Discourse Parsing via Reply-to Structures of Addressee Recognition (2023.emnlp-main)

Challenge:	Discourse parsing is a challenging task and plays a critical role in discourse analysis.
Approach:	They propose a macro discourse structure presentation schema to present the macro level discourse structure analysis.
Outcome:	The proposed corpus is based on two tasks of macro discourse structure analysis, including structure identification and nuclearity recognition.

Copied to clipboard

Yaxin Fan, Feng Jiang, Peifeng Li, Fang Kong, Qiaoming Zhu

Trucidator: Document-level Event Factuality Identification via Hallucination Enhancement and Cross-Document Inference (2025.coling-main)

Challenge:	Existing approaches to learn dialogue discourse parsing with related tasks require additional annotation, thus limiting their generality.
Approach:	They propose a multitasking framework that integrates dialogue discourse parsing with addressee recognition to reflect relation-based structure of dialogue.
Outcome:	The proposed framework outperforms baselines on the Molweni and STAC datasets.

Copied to clipboard

Zihao Zhang, Zhong Qian, Xiaoxu Zhu, Peifeng Li, Qiaoming Zhu

More than Text: Multi-modal Chinese Word Segmentation (2021.acl-short)

Challenge:	Document-level event factuality identification (DEFI) assesses the veracity degree to which an event mentioned in a document has happened.
Approach:	They propose a document-level event factuality identification framework with hallucination features . they propose factualusion corpus that integrates both genuine and hallucinous false information .
Outcome:	The proposed framework outperforms baselines in document event factuality identification.

Copied to clipboard

Dong Zhang, Zheng Hu, Shoushan Li, Hanqian Wu, Qiaoming Zhu, Guodong Zhou

Multimodality

Challenge:	Currently, word segmentation is performed in many languages without word delimiters.
Approach:	They propose to combine the multi-modality to perform Chinese word segmentation . they propose a time-dependent multi-module interactive model to integrate multi-modality information .
Outcome:	The proposed model integrates multi-modal information for word sequence labeling with Chinese language as target . the proposed model performs well on three training sets on Chinese and other languages without word delimiters.

Multi-modal Multi-label Emotion Detection with Modality and Label Dependence (2020.emnlp-main)

Copied to clipboard

Dong Zhang, Xincheng Ju, Junhui Li, Shoushan Li, Qiaoming Zhu, Guodong Zhou

Sentiment Analysis

Challenge:	Existing studies on multi-label emotion detection focus on one modality . current studies focus on label dependence, but there is no consensus on the model .
Approach:	They propose a multi-modal sequence-to-set approach to model label dependence and modality dependence in a multiple-modal scenario.
Outcome:	The proposed approach is able to model the label dependence and the modality dependence in a multi-modal scenario.

A Hybrid Model of Classification and Generation for Spatial Relation Extraction (2022.coling-1)

Copied to clipboard

Feng Wang, Peifeng Li, Qiaoming Zhu

Enhancing Multi-party Dialogue Discourse Parsing with Explanation Generation (2025.coling-main)

Challenge:	Existing studies only focus on spatial relations extraction as a classification task . spatial information is one kind of critical information for natural language understanding .
Approach:	They propose a hybrid model that generates null-role relations and extracts non-null-rol . they propose varying kinds of schemes to represent spatial relation .
Outcome:	The proposed model outperforms the baselines on the spatial relation extraction task on SpaceEval.

Copied to clipboard

Shannan Liu, Peifeng Li, Yaxin Fan, Qiaoming Zhu

Two-stage Incomplete Utterance Rewriting on Editing Operation (2025.coling-main)

Challenge:	Multi-party dialogue discourse parsing is an important and challenging task in natural language processing.
Approach:	They propose a model to integrate external knowledge from Large Language Models to analyze dialogue discourse structures and semantic relations between utterances in multi-party conversations.
Outcome:	The proposed model outperforms the state-of-the-art (SOTA) models on two public datasets.

Copied to clipboard

Zhiyu Cao, Peifeng Li, Qiaoming Zhu, Yaxin Fan

Paraphrasing

Challenge:	Existing methods to generate rewritten utterances based on dialogue context ignore coreference and ellipsis in dialogues.
Approach:	They propose a framework where the first stage generates editing operations and the second stage rewrites incomplete utterances utilizing the generated editing operations.
Outcome:	The proposed framework outperforms the existing models on three IUR datasets.

From Awareness to Adaptability: Enhancing Tool Utilization for Scientific Reasoning (2025.findings-acl)

Copied to clipboard

Wenjing Xie, Xiaobo Liang, Juntao Li, Wanfu Wang, Kehai Chen, Qiaoming Zhu, Min Zhang

Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and Generation (2021.emnlp-main)

Challenge:	Existing approaches enhance reasoning through Chain-of-Thought, Program-ofThough, and Tool-Integration.
Approach:	They propose a tool-awareness training method that leverages both forward and backward data generation strategies to strengthen the model’s conscious and selective tool utilization in multi-step reasoning tasks.
Outcome:	The proposed method improves the model's tool utilization capabilities, including proactivity and execution success rates.

Copied to clipboard

Feng Jiang, Yaxin Fan, Xiaomin Chu, Peifeng Li, Qiaoming Zhu

Text Classification

Challenge:	Existing methods of implicit discourse relation recognition (IDRR) focus on three aspects: enhancing discourse units representation, enhancing semantic interaction, and joint learning with other tasks.
Approach:	They propose a joint model to recognize the relation label and generate the target sentence containing the meaning of relations simultaneously.
Outcome:	The proposed model achieves the best performance against several state-of-the-art systems on Chinese and English datasets.

Stance Detection with Hierarchical Attention Network (C18-1)

Copied to clipboard

Qingying Sun, Zhongqing Wang, Qiaoming Zhu, Guodong Zhou

Sentiment Analysis

Challenge:	Recent studies have focused on document-level opinion mining, but linguistic information is correlated with the stance of the document.
Approach:	They propose a hierarchical attention neural model to employ various linguistic information to construct the document representation.
Outcome:	The proposed model can detect stance of documents on two datasets.

Non-Emotion-Centric Empathetic Dialogue Generation (2025.coling-main)

Copied to clipboard

Yuanxiang Huangfu, Peifeng Li, Yaxin Fan, Qiaoming Zhu