Papers by Mingzheng Li

2 papers
Unsupervised Domain Adaptation Method with Semantic-Structural Alignment for Dependency Parsing (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for dependency parsing are often of the pseudo-annotation type, but they fail to consider the change of model structure for domain adaptation.
Approach: They propose a method that accomplishes unsupervised cross-domain dependency parsing without using labeled data.
Outcome: The proposed method achieves consistent performance improvement on CODT1 and CTB9 domains.
Alleviating Performance Degradation Caused by Out-of-Distribution Issues in Embedding-Based Retrieval (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent studies reveal query out-of-distribution issues degrading ANN performance . a distribution regularizer is introduced into the encoder training objective to encourage alignment between query and base embeddings.
Approach: They introduce a distribution regularizer into the encoder training objective to encourage alignment between query and base embeddings.
Outcome: The proposed method consistently improves retrieval performance across multiple datasets.

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