Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks
Autor: | Hyunjin Choi, Judong Kim, Seongho Joe, Youngjune Gwon |
---|---|
Rok vydání: | 2021 |
Předmět: |
FOS: Computer and information sciences
Scheme (programming language) Computer Science - Computation and Language Computer Science - Artificial Intelligence business.industry Computer science 02 engineering and technology computer.software_genre Semantics Artificial Intelligence (cs.AI) 020204 information systems Pattern recognition (psychology) 0202 electrical engineering electronic engineering information engineering Embedding 020201 artificial intelligence & image processing Language model Artificial intelligence Computational linguistics business Computation and Language (cs.CL) computer Natural language Natural language processing Sentence computer.programming_language |
Zdroj: | ICPR |
Popis: | Contextualized representations from a pre-trained language model are central to achieve a high performance on downstream NLP task. The pre-trained BERT and A Lite BERT (ALBERT) models can be fine-tuned to give state-ofthe-art results in sentence-pair regressions such as semantic textual similarity (STS) and natural language inference (NLI). Although BERT-based models yield the [CLS] token vector as a reasonable sentence embedding, the search for an optimal sentence embedding scheme remains an active research area in computational linguistics. This paper explores on sentence embedding models for BERT and ALBERT. In particular, we take a modified BERT network with siamese and triplet network structures called Sentence-BERT (SBERT) and replace BERT with ALBERT to create Sentence-ALBERT (SALBERT). We also experiment with an outer CNN sentence-embedding network for SBERT and SALBERT. We evaluate performances of all sentence-embedding models considered using the STS and NLI datasets. The empirical results indicate that our CNN architecture improves ALBERT models substantially more than BERT models for STS benchmark. Despite significantly fewer model parameters, ALBERT sentence embedding is highly competitive to BERT in downstream NLP evaluations. 6 pages, 2 figures, to be published in 25th International Conference on Pattern Recognition, ICPR2020 |
Databáze: | OpenAIRE |
Externí odkaz: |