no code implementations • 1 Sep 2022 • Shiv Shankar, Laure Thompson, Madalina Fiterau
In this work, we present an iterative representation refinement approach, called Progressive Fusion, which mitigates the issues with late fusion representations.
no code implementations • NAACL 2022 • Shufan Wang, Fangyuan Xu, Laure Thompson, Eunsol Choi, Mohit Iyyer
We show that not only do state-of-the-art LFQA models struggle to generate relevant examples, but also that standard evaluation metrics such as ROUGE are insufficient to judge exemplification quality.
1 code implementation • EMNLP 2021 • Shufan Wang, Laure Thompson, Mohit Iyyer
Phrase representations derived from BERT often do not exhibit complex phrasal compositionality, as the model relies instead on lexical similarity to determine semantic relatedness.
no code implementations • 23 Oct 2020 • Laure Thompson, David Mimno
Clustering token-level contextualized word representations produces output that shares many similarities with topic models for English text collections.
1 code implementation • COLING 2018 • Laure Thompson, David Mimno
Most previous work in unsupervised semantic modeling in the presence of metadata has assumed that our goal is to make latent dimensions more correlated with metadata, but in practice the exact opposite is often true.
no code implementations • EMNLP 2017 • David Mimno, Laure Thompson
Despite their ubiquity, word embeddings trained with skip-gram negative sampling (SGNS) remain poorly understood.
no code implementations • EMNLP 2017 • Alex Schofield, ra, Laure Thompson, David Mimno
Duplicate documents are a pervasive problem in text datasets and can have a strong effect on unsupervised models.