Laura Burdick — accepted AI-conference papers

2022

Using Paraphrases to Study Properties of Contextual Embeddings

Laura Burdick, Jonathan K. Kummerfeld, Rada Mihalcea

NAACL 2022long

We use paraphrases as a unique source of data to analyze contextualized embeddings, with a particular focus on BERT. Because paraphrases naturally encode consistent word and phrase semantics, they provide a unique lens for investigating properties of embeddings. Using the Paraphrase Database’s align…

Cited by 6 Source ↗PDF ↗Scholar ↗

2021

Analyzing the Surprising Variability in Word Embedding Stability Across Languages

Laura Burdick, Jonathan K. Kummerfeld, Rada Mihalcea

EMNLP 2021main

Word embeddings are powerful representations that form the foundation of many natural language processing architectures, both in English and in other languages. To gain further insight into word embeddings, we explore their stability (e.g., overlap between the nearest neighbors of a word in differen…

Cited by 10 Source ↗PDF ↗code ↗Scholar ↗