Sökning: onr:"swepub:oai:DiVA.org:uu-395676" >
Recursive Subtree C...
Recursive Subtree Composition in LSTM-Based Dependency Parsing
-
- de Lhoneux, Miryam, 1990- (författare)
- Uppsala universitet,Institutionen för lingvistik och filologi,Computational Linguistics
-
- Ballesteros, Miguel (författare)
- IBM,IBM Research AI
-
- Nivre, Joakim, 1962- (författare)
- Uppsala universitet,Institutionen för lingvistik och filologi,Computational Linguistics
-
(creator_code:org_t)
- Stroudsburg : Association for Computational Linguistics, 2019
- 2019
- Engelska.
-
Ingår i: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics. - Stroudsburg : Association for Computational Linguistics. - 9781950737130 ; , s. 1566-1576
- Relaterad länk:
-
https://aclanthology...
-
visa fler...
-
https://urn.kb.se/re...
-
visa färre...
Abstract
Ämnesord
Stäng
- The need for tree structure modelling on top of sequence modelling is an open issue in neural dependency parsing. We investigate the impact of adding a tree layer on top of a sequential model by recursively composing subtree representations (composition) in a transition-based parser that uses features extracted by a BiLSTM. Composition seems superfluous with such a model, suggesting that BiLSTMs capture information about subtrees. We perform model ablations to tease out the conditions under which composition helps. When ablating the backward LSTM, performance drops and composition does not recover much of the gap. When ablating the forward LSTM, performance drops less dramatically and composition recovers a substantial part of the gap, indicating that a forward LSTM and composition capture similar information. We take the backward LSTM to be related to lookahead features and the forward LSTM to the rich history-based features both crucial for transition-based parsers. To capture history-based information, composition is better than a forward LSTM on its own, but it is even better to have a forward LSTM as part of a BiLSTM. We correlate results with language properties, showing that the improved lookahead of a backward LSTM is especially important for head-final languages.
Ämnesord
- HUMANIORA -- Språk och litteratur -- Jämförande språkvetenskap och allmän lingvistik (hsv//swe)
- HUMANITIES -- Languages and Literature -- General Language Studies and Linguistics (hsv//eng)
Nyckelord
- dependency parsing
- recursive neural networks
- recurrent neural networks
- long short-term memory networks
- Datorlingvistik
- Computational Linguistics
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas