Sökning: WFRF:(de Lhoneux Miryam 1990 ) >
Deep Contextualized...
Deep Contextualized Word Embeddings in Transition-Based and Graph-Based Dependency Parsing – A Tale of Two Parsers Revisited
-
- Kulmizev, Artur (författare)
- Uppsala universitet,Institutionen för lingvistik och filologi
-
- de Lhoneux, Miryam, 1990- (författare)
- Uppsala universitet,Institutionen för lingvistik och filologi
-
- Gontrum, Johannes (författare)
- Uppsala universitet,Institutionen för lingvistik och filologi
-
visa fler...
-
- Fano, Elena (författare)
- Uppsala universitet,Institutionen för lingvistik och filologi
-
- Nivre, Joakim, 1962- (författare)
- Uppsala universitet,Institutionen för lingvistik och filologi
-
visa färre...
-
(creator_code:org_t)
- 2019
- 2019
- Engelska.
-
Ingår i: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). ; , s. 2755-2768
- Relaterad länk:
-
https://www.aclweb.o...
-
visa fler...
-
https://www.emnlp-ij...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- Transition-based and graph-based dependency parsers have previously been shown to have complementary strengths and weaknesses: transition-based parsers exploit rich structural features but suffer from error propagation, while graph-based parsers benefit from global optimization but have restricted feature scope. In this paper, we show that, even though some details of the picture have changed after the switch to neural networks and continuous representations, the basic trade-off between rich features and global optimization remains essentially the same. Moreover, we show that deep contextualized word embeddings, which allow parsers to pack information about global sentence structure into local feature representations, benefit transition-based parsers more than graph-based parsers, making the two approaches virtually equivalent in terms of both accuracy and error profile. We argue that the reason is that these representations help prevent search errors and thereby allow transitionbased parsers to better exploit their inherent strength of making accurate local decisions. We support this explanation by an error analysis of parsing experiments on 13 languages.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Språkteknologi (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Language Technology (hsv//eng)
Nyckelord
- Datorlingvistik
- Computational Linguistics
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)