Papers by Longyin Zhang

11 papers
Multi-Hop Question Generation via Dual-Perspective Keyword Guidance (2025.findings-acl)

Copied to clipboard

Challenge: Existing work fails to fully utilize the guiding potential of keywords and neglect to differentiate the distinct roles of question-specific and document-specific keywords.
Approach: They propose a dual-perspective keyword-guided framework that integrates question and document keywords into the multi-hop question generation process.
Outcome: The proposed framework integrates question and document keywords into the multi-hop question generation process.
A Top-down Neural Architecture towards Text-level Parsing of Discourse Rhetorical Structure (2020.acl-main)

Copied to clipboard

Challenge: Text-level discourse parsing of discourse rhetorical structure (DRS) is a fundamental research topic in natural language processing.
Approach: They propose a top-down neural architecture for text-level discourse parsing . they cast the parser as a recursive split point ranking task .
Outcome: The proposed top-down approach is more suitable for text-level discourse parsing.
Hierarchical Modeling of Global Context for Document-Level Neural Machine Translation (D19-1)

Copied to clipboard

Challenge: Document-level machine translation (MT) remains challenging due to the difficulty in efficiently using document context.
Approach: They propose a hierarchical model to learn document context for document-level neural machine translation . they use a sentence encoder to capture intra-sentence dependencies and a document encoder .
Outcome: The proposed model significantly improves document-level translation performance over strong baselines.
Adversarial Learning for Discourse Rhetorical Structure Parsing (2021.acl-long)

Copied to clipboard

Challenge: Existing top-down discourse rhetorical structure parsers make local decisions and ignore global parsing.
Approach: They propose a method to transform gold standard and predicted constituency trees into tree diagrams with two color channels.
Outcome: The proposed method improves performance on RST-DT and CDTB corpora and can leverage global context.
EDTC: A Corpus for Discourse-Level Topic Chain Parsing (2021.findings-emnlp)

Copied to clipboard

Challenge: Discourse analysis is a fundamental part of natural language processing.
Approach: They propose a discourse-level topic chain parsing system which can be automated . they propose lexical cohesion modeling instead of lexically measuring topic structure .
Outcome: The proposed system is robust and reliable, and can provide high reliability and low confidence scores.
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.
Danger Depends on the Mind: A Theory-of-Mind Grounded Dataset and Model for Context-Dependent Dangerous Speech (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for dangerous speech detection rely on binary labels that ignore who is speaking and in what mental state.
Approach: They propose a context-dependent variant of dangerous speech detection by grounding it in Theory-of-Mind.
Outcome: The proposed model outperforms proprietary and open-source models with significantly fewer parameters.
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.
Discourse Parsing Enhanced by Discourse Dependence Perception (2022.aacl-main)

Copied to clipboard

Challenge: Top-down neural models still suffer from the top-down error propagation issue . previous studies gradually switch from feature-based machine learning methods to deep neural models .
Approach: They propose a top-down framework that learns from discourse dependency and constituency parsing through one shared encoder and two independent decoders.
Outcome: The proposed framework learns from discourse dependency and constituency parsing through one shared encoder and two independent decoders on a Chinese discourse corpus.
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.
Coupling Context Modeling with Zero Pronoun Recovering for Document-Level Natural Language Generation (2021.emnlp-main)

Copied to clipboard

Challenge: ZP-annotated natural language generation (NLG) corpora are scarce in pro-drop languages . despite efforts to bridge the discrepancy between human and machine, zero pronouns still persist in pro -drop tasks.
Approach: They propose a highly adaptive two-stage approach to couple context modeling with ZP recovering to mitigate the ZP problem in NLG tasks.
Outcome: The proposed approach can improve translation, question answering, and summarization tasks.

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