Attention can reflect syntactic structure (if you let it)
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Documents
- Attention can reflect syntactic structure (if you let it)
Final published version, 6.3 MB, PDF document
Since the popularization of the Transformer as a general-purpose feature encoder for NLP, many studies have attempted to decode linguistic structure from its novel multi-head attention mechanism. However, much of such work focused almost exclusively on English - a language with rigid word order and a lack of inflectional morphology. In this study, we present decoding experiments for multilingual BERT across 18 languages in order to test the generalizability of the claim that dependency syntax is reflected in attention patterns. We show that full trees can be decoded above baseline accuracy from single attention heads, and that individual relations are often tracked by the same heads across languages. Furthermore, in an attempt to address recent debates about the status of attention as an explanatory mechanism, we experiment with fine-tuning mBERT on a supervised parsing objective while freezing different series of parameters. Interestingly, in steering the objective to learn explicit linguistic structure, we find much of the same structure represented in the resulting attention patterns, with interesting differences with respect to which parameters are frozen.
Original language | English |
---|---|
Title of host publication | EACL 2021 - 16th Conference of the European Chapter of the Association for Computational Linguistics, Proceedings of the Conference |
Publisher | Association for Computational Linguistics |
Publication date | 2021 |
Pages | 3031-3045 |
ISBN (Electronic) | 9781954085022 |
Publication status | Published - 2021 |
Event | 16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021 - Virtual, Online Duration: 19 Apr 2021 → 23 Apr 2021 |
Conference
Conference | 16th Conference of the European Chapter of the Associationfor Computational Linguistics, EACL 2021 |
---|---|
By | Virtual, Online |
Periode | 19/04/2021 → 23/04/2021 |
Sponsor | Babelscape, Bloomberg Engineering, Facebook AI, Grammarly, LegalForce |
Number of downloads are based on statistics from Google Scholar and www.ku.dk
ID: 285250503