Making Sentence Embeddings Robust to User-Generated Content

1 code implementation • 25 Mar 2024 • Lydia Nishimwe, Benoît Sagot, Rachel Bawden

NLP models have been known to perform poorly on user-generated content (UGC), mainly because it presents a lot of lexical variations and deviates from the standard texts on which most of these models were trained.

Sentence Sentence Embedding +1