Recursive Subtree Composition in LSTM-Based Dependency Parsing

de Lhoneux, Miryam,1990-Uppsala universitet,Institutionen för lingvistik och filologi,Computational Linguistics (författare)

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.

HUMANIORA Språk och litteratur Jämförande språkvetenskap och allmän lingvistik hsv//swe
HUMANITIES Languages and Literature General Language Studies and Linguistics hsv//eng
dependency parsing
recursive neural networks
recurrent neural networks
long short-term memory networks
Datorlingvistik
Computational Linguistics

Ballesteros, MiguelIBM,IBM Research AI (författare)
Nivre, Joakim,1962-Uppsala universitet,Institutionen för lingvistik och filologi,Computational Linguistics(Swepub:uu)joani384 (författare)
Uppsala universitetInstitutionen för lingvistik och filologi (creator_code:org_t)

Ingår i:Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational LinguisticsStroudsburg : Association for Computational Linguistics, s. 1566-15769781950737130

Av författaren/redakt...: de Lhoneux, Miry ...; Ballesteros, Mig ...; Nivre, Joakim, 1 ...

Om ämnet

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.