Papers by Yunqi Zhang

11 papers
Two Challenges, One Solution: Robust Multimodal Learning through Dynamic Modality Recognition and Enhancement (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing methods require full-modality data during training phase or require explicit annotations to detect missing modalities.
Approach: They propose a Dynamic modality Recognition and Enhancement for Adaptive Multimodal fusion framework that directs selective reconstruction of missing or underperforming modalities.
Outcome: The proposed framework outperforms several baseline and state-of-the-art models on three benchmark datasets.
Think Before You Act: A Two-Stage Framework for Mitigating Gender Bias Towards Vision-Language Tasks (2024.naacl-long)

Copied to clipboard

Challenge: Existing vision-language models focus on salient attributes but ignore contextualized nuances, resulting in gender bias.
Approach: They propose a task-agnostic generation framework to mitigate gender bias in vision-language models.
Outcome: The proposed framework can mitigate gender bias in vision-language models . it yields all-sided but gender-obfuscated narratives, which prevents concentration on localized image features, especially gender attributes.
KnowVrDU: A Unified Knowledge-aware Prompt-Tuning Framework for Visually-rich Document Understanding (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for integrating layout and image features into pre-training language models are not suitable for few-shot settings.
Approach: They propose to reformulate VrDU tasks into a single question-answering format with task-specific prompts and train the pre-trained model with the parameter-efficient prompt tuning method.
Outcome: The proposed framework can be used in few-shot settings and reduces data requirements.
Meta-CQG: A Meta-Learning Framework for Complex Question Generation over Knowledge Bases (2022.coling-1)

Copied to clipboard

Challenge: Existing methods train one encoder-decoder-based model to fit all questions . however, such a one-size-fits-all strategy may not perform well for complex questions involving multiple KB relations or functional constraints.
Approach: They propose a meta-learning framework for complex question generation over knowledge bases . they propose he meta-trained generator can acquire universal meta-knowledge .
Outcome: The proposed framework can acquire universal and transferable meta-knowledge and quickly adapt to long-tailed samples under different dimensions.
Learning Reasoning Patterns for Relational Triple Extraction with Mutual Generation of Text and Graph (2022.findings-acl)

Copied to clipboard

Challenge: Existing methods focused on learning text patterns from explicit mentions but failed to extract the implicitly implied triples.
Approach: They propose to construct a relational graph from a sentence and apply multi-layer graph convolutions to capture the type inference logic of the paths.
Outcome: The proposed framework can find multi-hop reasoning paths and capture type inference logic with the sentence's supplementary relational expressions.
Thought-Action Graph Reasoning: Faithful and Efficient Reasoning of Large Language Models via Reusing Past Experience (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for integrating knowledge graphs with LLMs suffer from poor generalization or low reasoning efficiency.
Approach: They propose a thought-action Graph (TAG) that decomposes LLM-KG interaction trajectories into fine-grained semantic operators and guides LLM to execute on them.
Outcome: The proposed paradigm outperforms state-of-the-art methods on KGQA benchmarks while reducing the number of LLM calls and generated tokens.
DecorateLM: Data Engineering through Corpus Rating, Tagging, and Editing with Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are pre-trained on vast datasets composed of billions of tokens harvested from diverse text sources.
Approach: They propose a data engineering method to refine the pretraining corpus through data rating, tagging and editing.
Outcome: The proposed method improves the quality of the pretraining corpus by enhancing 100 billion tokens of the training corpus.
Jointly Extracting Explicit and Implicit Relational Triples with Reasoning Pattern Enhanced Binary Pointer Network (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods for relational triple extraction ignore implicit triples that lack explicit expressions, leading to incomplete knowledge graphs.
Approach: They propose a binary pointer network to extract explicit and implicit relational triples from sentences and to retain the information of extracted triples in an external memory.
Outcome: The proposed framework extracts overlapping triples relevant to each word sequentially and retains the information of extracted triples in an external memory.
RelU-Net: Syntax-aware Graph U-Net for Relational Triple Extraction (2022.emnlp-main)

Copied to clipboard

Challenge: Existing methods focused on capturing semantic information but failed to incorporate syntactic structures of the sentence, which is proved to contain rich relational information.
Approach: They propose a framework to capture syntactic information for relational triple extraction by contracting dependency tree into a core relational topology and eliminating redundant information with graph pooling operations.
Outcome: The proposed framework incorporates syntactic information for relational triple extraction.
Better Late Than Never: Model-Agnostic Hallucination Post-Processing Framework Towards Clinical Text Summarization (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for generating concise and coherent summaries may include unintended text with hallucinations, causing computational costs.
Approach: They propose a model-agnostic framework to post-process medical hallucinations . MEDAL integrates with any medical summarization model, requiring no additional computational overhead .
Outcome: MEDAL can post-process medical hallucinations without additional computational overhead.
Data Collection for Dialogue System: A Startup Perspective (N18-3)

Copied to clipboard

Challenge: Developing dialogue systems such as Apple Siri and Google Now requires high quality training data but data collection with crowdsourcing is largely an open question.
Approach: They propose to use crowdsourcing to collect data for a user intent classification task in a dialogue system.
Outcome: The proposed method improves the quality of the collected data and the model performance on real user queries.

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