Parsing as pretraining
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- Parsing as pretraining
Accepteret manuskript, 819 KB, PDF-dokument
Recent analyses suggest that encoders pretrained for language modeling capture certain morpho-syntactic structure. However, probing frameworks for word vectors still do not report results on standard setups such as constituent and dependency parsing. This paper addresses this problem and does full parsing (on English) relying only on pretraining architectures – and no decoding. We first cast constituent and dependency parsing as sequence tagging. We then use a single feed-forward layer to directly map word vectors to labels that encode a linearized tree. This is used to: (i) see how far we can reach on syntax modelling with just pretrained encoders, and (ii) shed some light about the syntax-sensitivity of different word vectors (by freezing the weights of the pretraining network during training). For evaluation, we use bracketing F1-score and las, and analyze in-depth differences across representations for span lengths and dependency displacements. The overall results surpass existing sequence tagging parsers on the ptb (93.5%) and end-to-end en-ewt ud (78.8%).
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2020) |
Forlag | AAAI Press |
Publikationsdato | 2020 |
Sider | 9114-9121. |
ISBN (Elektronisk) | 978-1-57735-835-0 |
DOI | |
Status | Udgivet - 2020 |
Begivenhed | Thirty-Forth AAAI Conference on Artificial Intelligence: AAAI 2020 - New York, USA Varighed: 7 feb. 2020 → 12 feb. 2020 https://aaai.org/Conferences/AAAI-20/ |
Konference
Konference | Thirty-Forth AAAI Conference on Artificial Intelligence |
---|---|
Land | USA |
By | New York |
Periode | 07/02/2020 → 12/02/2020 |
Internetadresse |
Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk
Ingen data tilgængelig
ID: 258333711