dc.contributor.author | Bernardy, J-P | en_US |
dc.contributor.author | Lappin, S | en_US |
dc.contributor.author | End-to-End Compositional Models of Vector-Based Semantics, 2022 (E2ECOMPVEC) | en_US |
dc.contributor.editor | Moortgat, M | en_US |
dc.contributor.editor | Wijnholds, G | en_US |
dc.date.accessioned | 2022-08-30T10:55:41Z | |
dc.date.available | 2022-07-18 | en_US |
dc.date.issued | 2022-08-10 | en_US |
dc.identifier.issn | 2075-2180 | en_US |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/80214 | |
dc.description.abstract | We show that both an LSTM and a unitary-evolution recurrent neural network (URN) can achieve encouraging accuracy on two types of syntactic patterns: context-free long distance agreement, and mildly context-sensitive cross serial dependencies. This work extends recent experiments on deeply nested context-free long distance dependencies, with similar results. URNs differ from LSTMs in that they avoid non-linear activation functions, and they apply matrix multiplication to word embeddings encoded as unitary matrices. This permits them to retain all information in the processing of an input string over arbitrary distances. It also causes them to satisfy strict compositionality. URNs constitute a significant advance in the search for explainable models in deep learning applied to NLP. | en_US |
dc.format.extent | 9 - 22 (14) | en_US |
dc.publisher | Open Publishing Association | en_US |
dc.rights | Attribution 3.0 United States | * |
dc.rights.uri | http://creativecommons.org/licenses/by/3.0/us/ | * |
dc.subject | Unitary matrix RNN | en_US |
dc.subject | Unitary matrix word embeddings | en_US |
dc.subject | compoisitionality | en_US |
dc.subject | transparent deep neural networks | en_US |
dc.title | Assessing the Unitary RNN as an End-to-End Compositional Model of Syntax | en_US |
dc.type | Conference Proceeding | |
dc.rights.holder | © 2022, The Author(s). Published by Open Publishing Association | |
dc.rights.holder | This item is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. | |
dc.identifier.doi | 10.4204/EPTCS.366.4 | en_US |
pubs.issue | 4 | en_US |
pubs.notes | Not known | en_US |
pubs.publication-status | Published | en_US |
pubs.volume | 366 | en_US |
dcterms.dateAccepted | 2022-07-18 | en_US |
rioxxterms.funder | Default funder | en_US |
rioxxterms.identifier.project | Default project | en_US |
qmul.funder | International Recruitment Grant::Swedish Research Council | en_US |