Explaining and Improving BERT Performance on Lexical Semantic Change Detection

EACL 2021 · Severin Laicher, Sinan Kurtyigit, Dominik Schlechtweg, Jonas Kuhn, Sabine Schulte im Walde ·

Type- and token-based embedding architectures are still competing in lexical semantic change detection. The recent success of type-based models in SemEval-2020 Task 1 has raised the question why the success of token-based models on a variety of other NLP tasks does not translate to our field. We investigate the influence of a range of variables on clusterings of BERT vectors and show that its low performance is largely due to orthographic information on the target word, which is encoded even in the higher layers of BERT representations. By reducing the influence of orthography we considerably improve BERT's performance.

PDF Abstract EACL 2021 PDF EACL 2021 Abstract

Code

Add Remove Mark official

No code implementations yet. Submit your code now

Tasks

Add Remove

Change Detection

Datasets

Add Datasets introduced or used in this paper

Results from the Paper

Edit

Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods

Add Remove

Adam • Attention Dropout • BERT • Dense Connections • Dropout • GELU • Layer Normalization • Linear Layer • Linear Warmup With Linear Decay • Multi-Head Attention • Residual Connection • Scaled Dot-Product Attention • Softmax • Weight Decay • WordPiece

Edit Social Preview

Explaining and Improving BERT Performance on Lexical Semantic Change Detection

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove