Improving Synonym Recommendation Using Sentence Context

Conference · Wed Nov 10 04:00:00 EST 2021

OSTI ID:1830146

Glenski, Maria F. ^[1]; Sealy, William I. ^[1]; Miller, Kate ^[1]; Arendt, Dustin L. ^[1]

---

1. BATTELLE (PACIFIC NW LAB)

Traditional synonym recommendations often include ill-suited suggestions for writer's specific contexts. We propose a simple approach for contextual synonym recommendation by combining existing human-curated thesauri, e.g. WordNet, with pre-trained language models. We evaluate our technique by curating a set of word-sentence pairs balanced across corpora and parts of speech, then annotating each word-sentence pair with the contextually appropriate set of synonyms. We found that basic language model approaches have higher precision. Approaches leveraging sentence context have higher recall. Overall, the latter contextual approach had the highest F-score.

• Research Organization: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States)
• Sponsoring Organization: USDOE
• DOE Contract Number: AC05-76RL01830
• OSTI ID: 1830146
• Report Number(s): PNNL-SA-165392
• Country of Publication: United States
• Language: English