Papers by Chandler May

5 papers
On Measuring Social Biases in Sentence Encoders (N19-1)

Copied to clipboard

Challenge: Word embeddings such as word2vec and GloVe exhibit human-like implicit biases based on gender, race, and other social constructs.
Approach: They propose a simple generaliza test to measure bias in word embeddings by comparing two sets of target-concept words to two sets .
Outcome: The proposed test shows that word2vec and word2Ve exhibit human-like implicit biases based on gender, race, and other social constructs.
LOME: Large Ontology Multilingual Extraction (2021.eacl-demos)

Copied to clipboard

Challenge: LOME is a system for performing multilingual information extraction with large ontologies.
Approach: They propose a system for multilingual information extraction with a framenet parser . LOME is available as a Docker container on Docker Hub and a lightweight version is available on the web .
Outcome: The proposed system outperforms or is competitive with the (monolingual) state-of-the-art . it can be used to build knowledge graphs with large ontologies and across multiple languages .
Adapting Coreference Resolution Models through Active Learning (2022.acl-long)

Copied to clipboard

Challenge: Neural coreference resolution models trained on one dataset may not transfer to new, low-resource domains.
Approach: They investigate how to actively label coreference by sampling a small subset of data for annotators to label.
Outcome: The proposed model can be more realistic when labeling spans within the same document than when annotating spans across documents.
CLAIMCHECK: How Grounded are LLM Critiques of Scientific Papers? (2025.findings-emnlp)

Copied to clipboard

Challenge: CLAIMCHECK is an annotated dataset of NeurIPS 2023 and 2024 submissions and reviews from OpenReview.
Approach: They annotate NeurIPS 2023 and 2024 submissions and reviews for weaknesses and dispute them for fine-grained labels of validity, objectivity, and type of the identified weaknesses.
Outcome: The proposed dataset is richly annotated by ML experts for weaknesses statements in the reviews and the claims that they dispute, as well as fine-grained labels of validity, objectivity, and type of the identified weaknesses.
How Grounded is Wikipedia? A Study on Structured Evidential Support and Retrieval (2026.findings-acl)

Copied to clipboard

Challenge: 22% of claims in Wikipedia *lead* sections are unsupported by the article body . 30% of annotated claims in the article *body* are unbacked by their (publicly accessible) sources .
Approach: They analyze Wikipedia's claim support annotations using a large-scale dataset . they find that 22% of Wikipedia claims are unsupported by the article body .
Outcome: The proposed dataset analyzes claims support annotations on biographical Wikipedia articles.

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