Papers by Lay-Ki Soon

9 papers
Can ChatGPT Perform Reasoning Using the IRAC Method in Analyzing Legal Scenarios Like a Lawyer? (2023.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) have attracted a lot of attention in the legal domain due to their ability to tackle a variety of legal tasks.
Approach: They constructed a corpus consisting of two legal scenarios using the IRAC method and used it to perform analysis on the corpus.
Outcome: The proposed model can analyze a contract act in Malaysia and the Australian Social Act for Dependent Child using the IRAC method.
CrudeOilNews: An Annotated Crude Oil News Corpus for Event Extraction (2022.lrec-1)

Copied to clipboard

Challenge: a corpus of English crude oil news for event extraction is presented . the corpus contains 425 news articles with approximately 11k events annotated .
Approach: They present a corpus of English Crude Oil news for event extraction . it is the first of its kind for Commodity News and contributes to text mining .
Outcome: The proposed corpus of English crude oil news is the first of its kind for Commodity News . the annotated news articles are compared with the standard news articles .
Malaysian English News Decoded: A Linguistic Resource for Named Entity and Relation Extraction (2024.lrec-main)

Copied to clipboard

Challenge: Standard English and Malaysian English exhibit significant differences in morphosyntactic variations . existing datasets are not sufficient to enhance NLP tasks in Malaysian english .
Approach: They propose to use a Malaysian English news article dataset to refine NER models for Malaysian english.
Outcome: The proposed dataset can improve the performance of NER on Malaysian English.
RENOVI: A Benchmark Towards Remediating Norm Violations in Socio-Cultural Conversations (2024.findings-naacl)

Copied to clipboard

Challenge: Norm violations occur when individuals fail to conform to culturally accepted behaviors, which may lead to potential conflicts.
Approach: They propose to use a large corpus of 9,258 multi-turn dialogues annotated with social norms to equip AI systems with a remediation ability.
Outcome: The proposed system can understand and remediate norm violations step by step.
Hybrid Models for Aspects Extraction without Labelled Dataset (D19-66)

Copied to clipboard

Challenge: Existing methods to extract aspects from opinions focus on explicit aspects, but sentences do not state them explicitly.
Approach: They propose to use a dictionary-based approach to identify and extract aspects from opinions . they propose to combine topic modelling and dictionary--based method .
Outcome: The proposed models outperform baseline topic model and dictionary-based approach in 58.70% of the evaluations.
Document-Level Zero-Shot Relation Extraction with Entity Side Information (2026.eacl-long)

Copied to clipboard

Challenge: Existing approaches rely on Large Language Models (LLMs) to generate synthetic data for unseen labels.
Approach: They propose a document-level zero-shot relation extraction framework with Entity Side Information to solve existing problems.
Outcome: The proposed approach achieves an average improvement of 11.6% in the macro F1-Score compared to baseline models and existing benchmarks.
ACCESS : A Benchmark for Abstract Causal Event Discovery and Reasoning (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods for identifying event causality in NLP are limited in their scale and rely on lexical cues.
Approach: They propose a benchmark for identifying abstract causality from a large-scale dataset.
Outcome: The proposed benchmark can be leveraged for enhancing QA reasoning performance in LLMs.
LePREC: Reasoning as Classification over Structured Factors for Assessing Relevance of Legal Issues (2026.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have impressive reasoning capabilities, but their precision remains inadequate.
Approach: They propose a framework that integrates neural generation with statistical reasoning to improve the accuracy of large language models.
Outcome: The proposed framework achieves interpretability through transparent feature weighting while maintaining data efficiency through correlation-based statistical classification.
Who You Are, What You Say: Intra- and Inter- Context Personality for Emotion Recognition in Conversation (2026.findings-eacl)

Copied to clipboard

Challenge: Existing approaches to Emotion Recognition in conversation (ERC) focus on modeling speaker dynamics within dialogues.
Approach: They propose a personality-aware ERC framework that segregates conversational context into intra- and inter-speaker components and models static or dynamic personality traits to represent stable and evolving speaker dispositions.
Outcome: The proposed framework improves weighted F1 by 2.74% over non-LLM methods and 0.98% over recent LLM-based methods.

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