Papers by Liang Guanqing

2 papers
Improving Model Generalization: A Chinese Named Entity Recognition Case Study (2021.acl-short)

Copied to clipboard

Challenge: Named Entity Recognition (NER) is a fundamental building block for various downstream natural language processing tasks due to the ambiguous word boundaries and complex composition.
Approach: They propose to resample entities within the same category to encourage a model to leverage both name and context knowledge in the training process.
Outcome: The proposed method significantly improves a model’s ability to detect unseen entities, especially for company, organization and position categories.
A Comparative Study of Faithfulness Metrics for Model Interpretability Methods (2022.acl-long)

Copied to clipboard

Challenge: Existing methods to reveal the reasoning processes of machine learning models are difficult to interpret due to their complexity.
Approach: They propose to use diagnosticity and complexity to assess faithfulness of machine learning models . they propose to apply posthoc interpretation methods to reveal reasoning behind models based on internal reasoning .
Outcome: The proposed interpretation metrics show conflicting preferences when comparing interpretations . sufficiency and comprehensiveness metrics have higher diagnosticity and lower complexity .

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