DefSent: Sentence Embeddings using Definition Sentences
| Autor: | Koichi Takeda, Hayato Tsukagoshi, Ryohei Sasano |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Computation and Language Computer science business.industry computer.software_genre Semantics Similarity (network science) Natural language inference Code (cryptography) Embedding Artificial intelligence business computer Computation and Language (cs.CL) Word (computer architecture) Natural language processing Sentence |
| Zdroj: | ACL/IJCNLP (2) |
| Popis: | Sentence embedding methods using natural language inference (NLI) datasets have been successfully applied to various tasks. However, these methods are only available for limited languages due to relying heavily on the large NLI datasets. In this paper, we propose DefSent, a sentence embedding method that uses definition sentences from a word dictionary, which performs comparably on unsupervised semantics textual similarity (STS) tasks and slightly better on SentEval tasks than conventional methods. Since dictionaries are available for many languages, DefSent is more broadly applicable than methods using NLI datasets without constructing additional datasets. We demonstrate that DefSent performs comparably on unsupervised semantics textual similarity (STS) tasks and slightly better on SentEval tasks to the methods using large NLI datasets. Our code is publicly available at https://github.com/hpprc/defsent . Accepted at ACL-IJCNLP 2021 main conference |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|