Papers by Weidong Xiao

6 papers
Distill, Fuse, Pre-train: Towards Effective Event Causality Identification with Commonsense-Aware Pre-trained Model (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods to detect causal relationships in unstructured texts ignore trivial knowledge which may prejudice performance.
Approach: They propose a pipeline to build a commonsense-aware pre-trained model which integrates reliable task-specific knowledge from commonsens graphs.
Outcome: The proposed pipeline integrates reliable task-specific knowledge from commonsense graphs.
Towards Better Representations for Multi-Label Text Classification with Multi-granularity Information (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing studies have shown that pre-trained language models generate word frequency-oriented text representations, causing texts with different labels to be closely distributed in a narrow region, which is difficult to classify.
Approach: They propose a framework to refine the text representation for multi-label text classification using contrastive learning and multi-task learning modules.
Outcome: The proposed framework improves the quality of the representations and yields stable and competitive improvements.
Extract-Select: A Span Selection Framework for Nested Named Entity Recognition with Generative Adversarial Training (2022.findings-acl)

Copied to clipboard

Challenge: Existing studies treat named entity recognition as a sequential labeling problem.
Approach: They propose a span selection framework for nested named entity recognition . they propose nesting entities with different input categories would be separately extracted .
Outcome: The proposed framework outperforms competing models on four benchmark datasets.
CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling (2026.acl-long)

Copied to clipboard

Challenge: a novel architecture that enables LLMs to handle arbitrarily long sequences with constant memory usage and linear time complexity is a major barrier to long-context processing.
Approach: They propose a novel architecture that enables LLMs to handle arbitrarily long sequences with constant memory usage and linear time complexity.
Outcome: The proposed architecture can handle arbitrarily long sequences with constant memory usage and linear time complexity.
T 2 -NER: A Two-Stage Span-Based Framework for Unified Named Entity Recognition with Templates (2023.tacl-1)

Copied to clipboard

Challenge: Named Entity Recognition (NER) has evolved from flat to overlapped and discontinuous . NER is a text recognition task that recognizes mentions that represent entities in text .
Approach: They propose a two-stage span-based framework to solve a unified NER task using two stages . they extract entity spans, classify over all entity span pairs and combine them to train two stages.
Outcome: The proposed framework beats all the current competitive baselines on eight benchmark datasets, obtaining the best performance of unified NER.
Joint Event Extraction with Hierarchical Policy Network (2020.coling-main)

Copied to clipboard

Challenge: Existing work on event extraction (EE) is pipelined or uses a joint structure but does not utilize information interactions among event triggers, event arguments, and argument roles.
Approach: They propose to exploit role information of arguments in an event and devise a Hierarchical Policy Network to perform joint EE.
Outcome: The proposed system outperforms existing methods and is more powerful for sentences with multiple events.

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