Till startsida
Webbkarta
Till innehåll Läs mer om hur kakor används på gu.se

Learning Syntactic Agreement with Deep Neural Networks

Konferensbidrag (offentliggjort, men ej förlagsutgivet)
Författare Jean-Philippe Bernardy
Shalom Lappin
Publicerad i Israel Seminar on Computational Linguistics, September 25, 2017
Publiceringsår 2017
Publicerad vid Institutionen för filosofi, lingvistik och vetenskapsteori
Språk en
Länkar clasp.gu.se/digitalAssets/1657/1657...
Ämnesord Deep Learning Syntactic Agreement
Ämneskategorier Elektroteknik och elektronik

Sammanfattning

We consider the extent to which different deep neural network (DNN) con- figurations can learn syntactic relations, by taking up Linzen et al.’s (2016) work on subject-verb agreement with LSTM RNNs. We test their methods on a much larger corpus than they used (a ∼24 million example part of the WaCky corpus, instead of their ∼1.35 million example corpus, both drawn from Wikipedia). We experiment with several different DNN architectures (LSTM RNNs, GRUs, and CNNs), and alternative parameter settings for these systems (vocabulary size, training to test ratio, number of layers, mem- ory size, drop out rate, and lexical embedding dimension size). We also try out our own unsupervised DNN language model. Our results are broadly compat- ible with those that Linzen et al. report. However, we discovered some inter- esting, and in some cases, surprising features of DNNs and language models in their performance of the agreement learning task. In particular, we found that DNNs require large vocabularies to form substantive lexical embeddings in order to learn structural patterns. This finding has significant consequences for our understanding of the way in which DNNs represent syntactic information.

Sidansvarig: Webbredaktion|Sidan uppdaterades: 2012-09-11
Dela:

På Göteborgs universitet använder vi kakor (cookies) för att webbplatsen ska fungera på ett bra sätt för dig. Genom att surfa vidare godkänner du att vi använder kakor.  Vad är kakor?