Papers by Weiguang Qu

5 papers
Construct a Sense-Frame Aligned Predicate Lexicon for Chinese AMR Corpus (2020.lrec-1)

Copied to clipboard

Challenge: Existing lexicons blur senses and frames of predicates, which needs to be refined to meet word sense disambiguation and event extraction tasks.
Approach: They propose to construct a predicate lexicon for Chinese AMR corpus with 14,389 senses and 10,800 frames of 8,470 words.
Outcome: The proposed lexicon includes 14,389 senses and 10,800 frames of 8,470 words.
An Element-aware Multi-representation Model for Law Article Prediction (2020.emnlp-main)

Copied to clipboard

Challenge: Existing studies have shown that using law articles as external knowledge can improve the performance of the Legal Judgment Prediction.
Approach: They propose a Law Article Element-aware Multi-representation Model which makes full use of law article information and can be used for multi-label samples.
Outcome: The proposed model improves the accuracy of 5.84%, macro F1 of 6.42%, and micro F1 by 4.28% compared with baseline models like TopJudge.
Event Detection as Graph Parsing (2021.findings-acl)

Copied to clipboard

Challenge: Existing approaches to event detection focus on using syntactic dependency structures or external knowledge to boost the performance.
Approach: They propose a graph parsing problem that explicitly models multiple event correlations and utilizes rich information conveyed by event type and subtype.
Outcome: The proposed model outperforms existing models on the public ACE2005 dataset by 4.2% on the dataset.
Automated Essay Scoring via Pairwise Contrastive Regression (2022.coling-1)

Copied to clipboard

Challenge: Existing approaches to automate essay scoring use regression or ranking objectives . a novel neural pairwise ranking model is developed to optimize both objectives based on the same loss .
Approach: They propose a novel Neural Pairwise Contrastive Regression model that optimizes both objectives simultaneously as a single loss.
Outcome: The proposed model outperforms previous methods on the public Automated Student Assessment Prize dataset.
Align-smatch: A Novel Evaluation Method for Chinese Abstract Meaning Representation Parsing based on Alignment of Concept and Relation (2022.lrec-1)

Copied to clipboard

Challenge: Abstract Meaning Representation abstracts the meaning of sentences into a single-rooted, acyclic and directed graph.
Approach: They propose to use a metric to evaluate concept alignment and relation alignment to improve Chinese AMR parsing evaluation methods.
Outcome: The proposed method is more robust and compatible with concept alignment and relation alignment and more robust in evaluating arcs.

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