Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model

Steven Derby; Paul Miller; Brian Murphy; Barry Devereux

doi:10.18653/v1/W18-5449

Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model

Steven Derby, Paul Miller, Brian Murphy, Barry Devereux

Queen's University Belfast

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

2 Citations (Scopus)

37 Downloads (Pure)

Abstract

Performance in language modelling has been significantly improved by training recurrent neural networks on large corpora. This progress has come at the cost of interpretability and an understanding of how these architectures function, making principled development of better language models more difficult. We look inside a state-of-the-art neural language model to analyse how this model represents high-level lexico-semantic information. In particular, we investigate how the model represents words by extracting activation patterns where they occur in the text, and compare these representations directly to human semantic knowledge.

Original language	English
Title of host publication	Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
Publisher	Association for Computational Linguistics
Pages	362-364
Number of pages	3
ISBN (Electronic)	9781948087711
DOIs	https://doi.org/10.18653/v1/W18-5449
Publication status	Published - Nov 2018
Event	1st Workshop on BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, co-located with the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 - Brussels, Belgium Duration: 01 Nov 2018 → …

Publication series

Name	EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP,
Publisher	Association for Computational Linguistics

Conference

Conference	1st Workshop on BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, co-located with the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018
Country/Territory	Belgium
City	Brussels
Period	01/11/2018 → …

Bibliographical note

Funding Information:
This work was partly funded by a Microsoft Azure for Research Award.

Publisher Copyright:
© 2018 Association for Computational Linguistics

ASJC Scopus subject areas

Computer Science Applications
Computational Theory and Mathematics
Information Systems

Access to Document

10.18653/v1/W18-5449Licence: CC BY

Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model
Copyright 2018 the authors. This is an open access Creative Commons Attribution-NonCommercial License (https://creativecommons.org/licenses/by-nc/4.0/), which permits use, distribution and reproduction for non-commercial purposes, provided the author and source are cited.
Final published version, 166 KBLicence: CC BY

Interpretable semantic representations from neural language models and computer vision
Derby, S. (Author), Murphy, B. (Supervisor), Miller, P. (Supervisor) & Devereux, B. (Supervisor), Jul 2022
Student thesis: Doctoral Thesis › Doctor of Philosophy

File

Cite this

Derby, S., Miller, P., Murphy, B., & Devereux, B. (2018). Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP (pp. 362-364). (EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP,). Association for Computational Linguistics. https://doi.org/10.18653/v1/W18-5449

Derby, Steven ; Miller, Paul ; Murphy, Brian et al. / Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model. Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. Association for Computational Linguistics, 2018. pp. 362-364 (EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP,).

@inproceedings{71c2d08e943c41e4b4cac4b392e49991,

title = "Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model",

abstract = "Performance in language modelling has been significantly improved by training recurrent neural networks on large corpora. This progress has come at the cost of interpretability and an understanding of how these architectures function, making principled development of better language models more difficult. We look inside a state-of-the-art neural language model to analyse how this model represents high-level lexico-semantic information. In particular, we investigate how the model represents words by extracting activation patterns where they occur in the text, and compare these representations directly to human semantic knowledge.",

author = "Steven Derby and Paul Miller and Brian Murphy and Barry Devereux",

note = "Funding Information: This work was partly funded by a Microsoft Azure for Research Award. Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics; 1st Workshop on BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, co-located with the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 ; Conference date: 01-11-2018",

year = "2018",

month = nov,

doi = "10.18653/v1/W18-5449",

language = "English",

series = "EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP,",

publisher = "Association for Computational Linguistics",

pages = "362--364",

booktitle = "Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP",

}

Derby, S, Miller, P, Murphy, B & Devereux, B 2018, Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model. in Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, Association for Computational Linguistics, pp. 362-364, 1st Workshop on BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, co-located with the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018, Brussels, Belgium, 01/11/2018. https://doi.org/10.18653/v1/W18-5449

Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model. / Derby, Steven; Miller, Paul; Murphy, Brian et al.
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. Association for Computational Linguistics, 2018. p. 362-364 (EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP,).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model

AU - Derby, Steven

AU - Miller, Paul

AU - Murphy, Brian

AU - Devereux, Barry

PY - 2018/11

Y1 - 2018/11

N2 - Performance in language modelling has been significantly improved by training recurrent neural networks on large corpora. This progress has come at the cost of interpretability and an understanding of how these architectures function, making principled development of better language models more difficult. We look inside a state-of-the-art neural language model to analyse how this model represents high-level lexico-semantic information. In particular, we investigate how the model represents words by extracting activation patterns where they occur in the text, and compare these representations directly to human semantic knowledge.

AB - Performance in language modelling has been significantly improved by training recurrent neural networks on large corpora. This progress has come at the cost of interpretability and an understanding of how these architectures function, making principled development of better language models more difficult. We look inside a state-of-the-art neural language model to analyse how this model represents high-level lexico-semantic information. In particular, we investigate how the model represents words by extracting activation patterns where they occur in the text, and compare these representations directly to human semantic knowledge.

U2 - 10.18653/v1/W18-5449

DO - 10.18653/v1/W18-5449

M3 - Conference contribution

AN - SCOPUS:85082495948

T3 - EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP,

SP - 362

EP - 364

BT - Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP

PB - Association for Computational Linguistics

T2 - 1st Workshop on BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, co-located with the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018

Y2 - 1 November 2018

ER -

Derby S, Miller P, Murphy B, Devereux B. Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model. In Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP. Association for Computational Linguistics. 2018. p. 362-364. (EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP,). doi: 10.18653/v1/W18-5449

Representation of Word Meaning in the Intermediate Projection Layer of a Neural Language Model

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Access to Document

Fingerprint

Student theses

Interpretable semantic representations from neural language models and computer vision

Cite this