Papers by Bowei Zou

27 papers
GLGR: Question-aware Global-to-Local Graph Reasoning for Multi-party Dialogue Reading Comprehension (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches for multi-hop reasoning are lacking for local graph reasoning . existing approaches neglect local semantic structures in utterances .
Approach: They propose a question-aware global-to-local graph reasoning approach that expands the canonical Interlocutor-Utterance graph by introducing a query node.
Outcome: The proposed approach outperforms existing methods on Molweni and FriendsQA.
Negative Focus Detection via Contextual Attention Mechanism (D19-1)

Copied to clipboard

Challenge: Negation is a universal but complicated linguistic phenomenon that reverses the polarity of a statement or its property into opposite.
Approach: They propose a framework which consists of a Bidirectional Long Short-Term Memory neural network and a Conditional Random Fields layer to capture contextual information.
Outcome: The proposed framework improves on the SEM’12 shared task corpus, yielding an absolute improvement of 2.11% over the state-of-the-art.
Enhancing Attributed Question Answering using Tailored Progressive Curriculum Learning (2025.findings-emnlp)

Copied to clipboard

Challenge: Attributed Question Answering models are not yet leveraged to enhance their essential capabilities, including evidence identification, cross-source relation recognition and anti-distraction reasoning.
Approach: They propose a progressive progressive curriculum learning approach that optimizes both encoder-decoder and decoder-only AQA models.
Outcome: The proposed approach improves both encoder-decoder and decoder-only AQA models on the quotesum benchmark.
NUT-RC: Noisy User-generated Text-oriented Reading Comprehension (2020.coling-main)

Copied to clipboard

Challenge: Existing RC models focus on extractive or generative, but ignore integration of them.
Approach: They propose a noisy user-generated text-oriented RC model that integrates extractive and generative RC models by a multi-task learning mechanism and an answer selection module.
Outcome: The proposed model outperforms state-of-the-art models on Twitter.
A Benchmark for Translations Across Styles and Language Variants (2025.findings-emnlp)

Copied to clipboard

Challenge: lack of comprehensive evaluation benchmarks has hindered progress in this field . lack of evaluation benchmarking has hinder MT's ability to generate accurate outputs .
Approach: They evaluate translations across semantic preservation, cultural and regional specificity, expression style, and fluency at both the word and sentence levels.
Outcome: The proposed evaluation framework is validated on translations of state-of-the-art large language models .
GCDST: A Graph-based and Copy-augmented Multi-domain Dialogue State Tracking (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to training DST on a single domain ignore information across domains.
Approach: They construct a dialogue state graph to transfer structured features among related domain-slot pairs across domains and encode the graph information of dialogue states by graph convolutional networks.
Outcome: The proposed model improves the performance of the multi-domain DST baseline with the absolute joint accuracy of 2.0% and 1.0% on the MultiWOZ 2.0 and 2.1 dialogue datasets.
Leveraging Contrastive Learning and Knowledge Distillation for Incomplete Modality Rumor Detection (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing rumor detection models neglect the semantic coherence between text and image components in multimodal posts . Existing models neglect incomplete modalities in single modal posts, such as missing text or images .
Approach: They propose a framework for incomplete modality rumor detection that captures semantic consistency between text and image pairs while enhancing model generalization to incomplete modalities within individual posts.
Outcome: The proposed framework outperforms state-of-the-art methods on two English and two Chinese benchmark datasets for rumor detection in social media.
MMAC: A Multilingual, Multimodal Alignment Framework for Cultural Grounding Evaluation (2026.acl-long)

Copied to clipboard

Challenge: Existing models lack cultural alignment across modalities and languages . a new framework to assess cultural awareness across linguistics and languages is needed .
Approach: They propose a framework that integrates tri-modally aligned cultural benchmarks and a five-dimensional evaluation protocol to assess cross-country awareness disparities.
Outcome: The proposed framework assesses cultural awareness disparities across modalities and languages . it is the first dataset aligned at the input level across text, image, and speech .
CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation (2025.findings-emnlp)

Copied to clipboard

Challenge: Multilingual Large Language Models (MLLMs) exhibit strong generalization across languages, yet they remain prone to hallucinations due to training data imbalances.
Approach: They propose a cross-lingual Chain-of-Thought framework that enhances cross-linguistic alignment . the framework guides the model to reason in a high-resource language before generating answers in low-resourced language.
Outcome: The proposed framework reduces hallucination rates by up to 62% and significantly improves factual knowledge transfer across language pairs.
Winnowing Knowledge for Multi-choice Question Answering (2021.findings-emnlp)

Copied to clipboard

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 .
Incorporating Image Matching Into Knowledge Acquisition for Event-Oriented Relation Recognition (C18-1)

Copied to clipboard

Challenge: Event relation recognition is a challenging language processing task because the query events are selected from different paragraphs in a document or even different documents, so there is lack of explicit clue.
Approach: They propose to use image processing to acquire similar event instances and use image matching to approximate calculation between events.
Outcome: The proposed model performs comparable to CNN while slightly better than LSTM on the ACE-R2 corpus.
Unseen Entity Handling in Complex Question Answering over Knowledge Base via Language Generation (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for complex question answering are limited in the search space of all possible relation paths.
Approach: They propose a method that directly generates an executable SPARQL query without simplification.
Outcome: The proposed method significantly outperforms the previous methods and has higher interpretability and computational efficiency than the previous ones.
Empowering Tree-structured Entailment Reasoning: Rhetorical Perception and LLM-driven Interpretability (2024.lrec-main)

Copied to clipboard

Challenge: Existing models for science question answering lack a framework for entailment trees . ambiguities and similarities between science facts complicate the fact retrieval process .
Approach: They propose a framework for building entailment trees for science question answering . they propose to infuse knowledge that bridges the gap between reasoning types and rhetorical relations .
Outcome: The proposed framework improves retrieval capabilities, understanding relationships and generating intermediate conclusions.
Interview Evaluation: A Novel Approach for Automatic Evaluation of Conversational Question Answering Models (2023.emnlp-main)

Copied to clipboard

Challenge: Existing evaluation methods for CQA use pre-collected human-human conversations . previous methods use model-predicted dialogue history instead of ground truth .
Approach: They propose an automatic evaluation approach that uses the model's dialogue history to evaluate models.
Outcome: The proposed method improves on existing models and their evaluations on QuAC and CoQA.
Adversarial Feature Adaptation for Cross-lingual Relation Classification (C18-1)

Copied to clipboard

Challenge: Existing methods for relation classification exploit monolingual data due to lack of annotated data in other languages.
Approach: They propose an adversarial feature adaptation approach for cross-lingual relation classification using a generative adversarial network.
Outcome: The proposed approach yields an improvement of 5.7% over the state-of-the-art.
Making Pre-trained Language Models Better Learn Few-Shot Spoken Language Understanding in More Practical Scenarios (2023.findings-acl)

Copied to clipboard

Challenge: Existing few-shot Spoken Language Understanding models need to be trained on a set of data-rich source domains and adapt to the target domain with a few examples.
Approach: They propose a scenario where only a pre-trained language model and a few labeled examples are used to train few-shot SLU models.
Outcome: The proposed model outperforms existing models on few-shot settings by reducing the number of slot labels and reducing training complexity.
Multi-grained Chinese Word Segmentation with Weakly Labeled Data (2020.coling-main)

Copied to clipboard

Challenge: Existing work on single-grained word segmentation (SWS) focuses on segmenting a sentence into multiple word sequences to preserve all words of different granularities.
Approach: They propose to use a graph-based parser to accommodate weakly labeled data for MWS by employing a simple yet competitive graph-basic parsers with local loss.
Outcome: The proposed model outperforms the state-of-the-art model on weakly labeled data on a high-quality dataset from canonical newswire (NEWS) and non-canonical web (BAIKE) data.
DSPM-NLG: A Dual Supervised Pre-trained Model for Few-shot Natural Language Generation in Task-oriented Dialogue System (2023.findings-acl)

Copied to clipboard

Challenge: Existing models for few-shot natural language generation are based on a dual correlation between NLG and SLU from the perspective of probability.
Approach: They propose a dual supervised pre-trained model to regularize the pre-training process . they use a probabilistic approach to learn the dual correlation between NLG and SLU .
Outcome: The proposed model outperforms the previous state-of-the-art models on a few-shot dataset.
Improving Explainable Fact-Checking with Claim-Evidence Correlations (2025.coling-main)

Copied to clipboard

Challenge: Existing fact-checking systems that employ large language models fail to reveal reasoning principles behind their decision-making for the claim verdict.
Approach: They propose an LLM-based fact-checking system that simulates human reasoning principles . they propose a test set to evaluate the CorXFact system in real-world and closed-domain scenarios .
Outcome: The proposed system outperforms four strong fact-checking baselines in claim authenticity prediction and verdict explanation.
Enhancing Event-centric News Cluster Summarization via Data Sharpening and Localization Insights (2025.acl-long)

Copied to clipboard

Challenge: Existing work on text summarization approaches are approaching or exceeding human excellence .
Approach: They propose a framework that optimizes the balance between information volume and entropy in input texts.
Outcome: The proposed framework optimizes information volume and entropy in input texts, achieving notable improvements in localized contexts.
Don’t Eclipse Your Arts Due to Small Discrepancies: Boundary Repositioning with a Pointer Network for Aspect Extraction (2020.acl-main)

Copied to clipboard

Challenge: Existing aspect extraction methods suffer from boundary errors, but they hurt performance severely.
Approach: They propose to use a pointer network to reposition the boundaries of extracted aspects . they conduct experiments on laptop and restaurant benchmark datasets .
Outcome: The proposed method outperforms state-of-the-art methods on benchmark datasets . it achieves substantial improvements over baseline and outperformed existing methods .
Modeling What-to-ask and How-to-ask for Answer-unaware Conversational Question Generation (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to generate conversational question are naive and do not account for the answer span.
Approach: They propose a framework for generating a conversational question from a context.
Outcome: The proposed framework achieves state-of-the-art in two different settings compared to existing models . it uses a sentence as the rationale and extracts the answer span from it .
CoHS-CQG: Context and History Selection for Conversational Question Generation (2022.coling-1)

Copied to clipboard

Challenge: Existing studies focus on single-turn question generation, but few studies have studied the challenges of multiturn QG.
Approach: They propose a two-stage conversational question generation framework that shortens the context and history of the input and calculates relevance scores.
Outcome: The proposed framework achieves state-of-the-art on CoQA in answer-aware and answer-unaware settings.
Capturing Conversational Interaction for Question Answering via Global History Reasoning (2022.findings-naacl)

Copied to clipboard

Challenge: Existing studies have studied history-dependent reasoning for question answering . utilizing global conversation history for enhancement is gaining interest .
Approach: They propose to establish long-distance dependency among global utterances in multi-turn conversation.
Outcome: The proposed method improves on QuAC by 1%, yielding the F1 score of 73.7%.
CLFFRD: Curriculum Learning and Fine-grained Fusion for Multimodal Rumor Detection (2024.lrec-main)

Copied to clipboard

Challenge: Existing multimodal rumor detection models overlook sample difficulty and order when training . Existing models overlook text-level difficulty, image-level and multimodal difficulty when training samples .
Approach: They propose a curriculum learning framework that uses fine-grained fusion to detect rumors . they propose fusion-based methods that combine text and images to enhance semantic cohesion .
Outcome: The proposed framework outperforms state-of-the-art models on English and Chinese benchmark datasets.
Looking Beyond the One: Operationalizing and Eliciting Visual Ambiguity in VLLMs (2026.acl-long)

Copied to clipboard

Challenge: Visual question answering systems typically collapse ambiguity, committing to a single interpretation during decoding and evaluation.
Approach: They operationalize ambiguity as the existence of multiple answer-supporting regions in an image . they show that ambiguities are already encoded in their internal representations .
Outcome: The proposed approach makes ambiguity observable without exhaustive annotations . ambiguities are already encoded in models, but not reliably expressed in outputs despite hidden states .
Comprehensive Abstractive Comment Summarization with Dynamic Clustering and Chain of Thought (2024.findings-acl)

Copied to clipboard

Challenge: Recent work on news comment summarization has focused on extractive methods within constraints.
Approach: They propose an enhanced fast clustering algorithm that maintains a dynamic similarity threshold to ensure high density of each comment cluster being built.
Outcome: The proposed method improves the baseline methods and the test suite on real-world news comments.

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