2020
DOI: 10.48550/arxiv.2002.06652
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

SBERT-WK: A Sentence Embedding Method by Dissecting BERT-based Word Models

Abstract: Sentence embedding is an important research topic in natural language processing (NLP) since it can transfer knowledge to downstream tasks. Meanwhile, a contextualized word representation, called BERT, achieves the state-of-the-art performance in quite a few NLP tasks. Yet, it is an open problem to generate a high quality sentence representation from BERTbased word models. It was shown in previous study that different layers of BERT capture different linguistic properties. This allows us to fusion information … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
13
0

Year Published

2020
2020
2022
2022

Publication Types

Select...
6
2

Relationship

1
7

Authors

Journals

citations
Cited by 10 publications
(13 citation statements)
references
References 50 publications
0
13
0
Order By: Relevance
“…The probing tasks examine linguistic information at the surface-level (how well embeddings encode surface knowledge that does not require linguistic information); the syntactic-level (how well the embeddings encode the grammatical structure of a sentence; and the semantic-level (how well the embeddings encode the meaning and logistics behind the sentences). For evaluating on SentEval, we use the scripts provided by SBERT-WK (Wang and Kuo 2020). We use the "CLS" embedding method for BERT-base and XLNetbase, while "Ave last hidden" for the SBERT-base model and replicate the results with the original paper.…”
Section: Methodsmentioning
confidence: 99%
“…The probing tasks examine linguistic information at the surface-level (how well embeddings encode surface knowledge that does not require linguistic information); the syntactic-level (how well the embeddings encode the grammatical structure of a sentence; and the semantic-level (how well the embeddings encode the meaning and logistics behind the sentences). For evaluating on SentEval, we use the scripts provided by SBERT-WK (Wang and Kuo 2020). We use the "CLS" embedding method for BERT-base and XLNetbase, while "Ave last hidden" for the SBERT-base model and replicate the results with the original paper.…”
Section: Methodsmentioning
confidence: 99%
“…Moreover, we customize the NT-Xent loss (Chen et al, 2020), a contrastive learning objective widely used in computer vision, for better sentence representation learning with BERT. We demonstrate that our approach outperforms competitive baselines designed for building BERT sentence vectors (Li et al, 2020;Wang and Kuo, 2020) in various environments. With comprehensive analyses, we also show that our method is more computationally efficient than the baselines at inference in addition to being more robust to domain shifts.…”
Section: Introductionmentioning
confidence: 93%
“…Meanwhile, some other studies concentrate on more effectively leveraging the knowledge embedded in BERT to construct sentence embeddings without supervision. Specifically, Wang and Kuo (2020) propose a pooling method based on linear algebraic algorithms to draw sentence vectors from BERT's intermediate layers. Li et al (2020) suggest to learn a mapping from the average of the embeddings obtained from the last two layers of BERT to a spherical Gaussian distribution using a flow model, and to leverage the redistributed embeddings in place of the original BERT representations.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…For embedding into Euclidean spaces, a large body of work is based on Word2vec (Mikolov et al, 2013), where each word is represented as a vector in the Euclidean space. From these word embeddings one can further compute document and sentence embeddings using various models Ramos et al (2003), Arora et al (2017), Wang and Kuo (2020), Le and Mikolov (2014), Kiros et al (2015), Logeswaran and Lee (2018) for higher level NLP tasks.…”
Section: Introductionmentioning
confidence: 99%