Cross-lingual Semantic Role Labelling with the Valpal database knowledge

Chinmay Choudhary; Colm O'Riordan

Cross-lingual Semantic Role Labelling with the Valpal database knowledge

Chinmay Choudhary
, Colm O'Riordan

Computer Science

University of Galway

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

1 Citation (Scopus)

Abstract

Cross-lingual Transfer Learning typically involves training a model on a high-resource source language and applying it to a low-resource target language. In this work we introduce a lexical database called Valency Patterns Leipzig (ValPal) which provides the argument pattern information about various verb-forms in multiple languages including low-resource languages. We also provide a framework to integrate the ValPal database knowledge into the state-of-the-art LSTM based model for cross-lingual semantic role labelling. Experimental results show that integrating such knowledge resulted in am improvement in performance of the model on all the target languages on which it is evaluated.

Original language	English
Title of host publication	DeeLIO 2022 - Deep Learning Inside Out
Subtitle of host publication	3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Proceedings of the Workshop
Editors	Eneko Agirre, Marianna Apidianaki, Ivan Vulic
Publisher	Association for Computational Linguistics (ACL)
Pages	1-10
Number of pages	10
ISBN (Electronic)	9781955917322
Publication status	Published - 2022
Event	Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, DeeLIO 2022 - Virtual, Dublin, Ireland Duration: 27 May 2022 → …

Publication series

Name	DeeLIO 2022 - Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Proceedings of the Workshop

Conference

Conference	Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, DeeLIO 2022
Country/Territory	Ireland
City	Virtual, Dublin
Period	27/05/22 → …

Cite this

Choudhary, C., & O'Riordan, C. (2022). Cross-lingual Semantic Role Labelling with the Valpal database knowledge. In E. Agirre, M. Apidianaki, & I. Vulic (Eds.), DeeLIO 2022 - Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Proceedings of the Workshop (pp. 1-10). (DeeLIO 2022 - Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Proceedings of the Workshop). Association for Computational Linguistics (ACL).

Choudhary, Chinmay ; O'Riordan, Colm. / Cross-lingual Semantic Role Labelling with the Valpal database knowledge. DeeLIO 2022 - Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Proceedings of the Workshop. editor / Eneko Agirre ; Marianna Apidianaki ; Ivan Vulic. Association for Computational Linguistics (ACL), 2022. pp. 1-10 (DeeLIO 2022 - Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Proceedings of the Workshop).

@inproceedings{834aa3a3d2d7402e9862342eb9747208,

title = "Cross-lingual Semantic Role Labelling with the Valpal database knowledge",

abstract = "Cross-lingual Transfer Learning typically involves training a model on a high-resource source language and applying it to a low-resource target language. In this work we introduce a lexical database called Valency Patterns Leipzig (ValPal) which provides the argument pattern information about various verb-forms in multiple languages including low-resource languages. We also provide a framework to integrate the ValPal database knowledge into the state-of-the-art LSTM based model for cross-lingual semantic role labelling. Experimental results show that integrating such knowledge resulted in am improvement in performance of the model on all the target languages on which it is evaluated.",

author = "Chinmay Choudhary and Colm O'Riordan",

note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, DeeLIO 2022 ; Conference date: 27-05-2022",

year = "2022",

language = "English",

series = "DeeLIO 2022 - Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Proceedings of the Workshop",

publisher = "Association for Computational Linguistics (ACL)",

pages = "1--10",

editor = "Eneko Agirre and Marianna Apidianaki and Ivan Vulic",

booktitle = "DeeLIO 2022 - Deep Learning Inside Out",

}

Choudhary, C & O'Riordan, C 2022, Cross-lingual Semantic Role Labelling with the Valpal database knowledge. in E Agirre, M Apidianaki & I Vulic (eds), DeeLIO 2022 - Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Proceedings of the Workshop. DeeLIO 2022 - Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Proceedings of the Workshop, Association for Computational Linguistics (ACL), pp. 1-10, Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, DeeLIO 2022, Virtual, Dublin, Ireland, 27/05/22.

Cross-lingual Semantic Role Labelling with the Valpal database knowledge. / Choudhary, Chinmay; O'Riordan, Colm.
DeeLIO 2022 - Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Proceedings of the Workshop. ed. / Eneko Agirre; Marianna Apidianaki; Ivan Vulic. Association for Computational Linguistics (ACL), 2022. p. 1-10 (DeeLIO 2022 - Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Proceedings of the Workshop).

Research output: Chapter in Book or Conference Publication/Proceeding › Conference Publication › peer-review

TY - GEN

T1 - Cross-lingual Semantic Role Labelling with the Valpal database knowledge

AU - Choudhary, Chinmay

AU - O'Riordan, Colm

PY - 2022

Y1 - 2022

N2 - Cross-lingual Transfer Learning typically involves training a model on a high-resource source language and applying it to a low-resource target language. In this work we introduce a lexical database called Valency Patterns Leipzig (ValPal) which provides the argument pattern information about various verb-forms in multiple languages including low-resource languages. We also provide a framework to integrate the ValPal database knowledge into the state-of-the-art LSTM based model for cross-lingual semantic role labelling. Experimental results show that integrating such knowledge resulted in am improvement in performance of the model on all the target languages on which it is evaluated.

AB - Cross-lingual Transfer Learning typically involves training a model on a high-resource source language and applying it to a low-resource target language. In this work we introduce a lexical database called Valency Patterns Leipzig (ValPal) which provides the argument pattern information about various verb-forms in multiple languages including low-resource languages. We also provide a framework to integrate the ValPal database knowledge into the state-of-the-art LSTM based model for cross-lingual semantic role labelling. Experimental results show that integrating such knowledge resulted in am improvement in performance of the model on all the target languages on which it is evaluated.

UR - https://www.scopus.com/pages/publications/85137689148

M3 - Conference Publication

AN - SCOPUS:85137689148

T3 - DeeLIO 2022 - Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Proceedings of the Workshop

SP - 1

EP - 10

BT - DeeLIO 2022 - Deep Learning Inside Out

A2 - Agirre, Eneko

A2 - Apidianaki, Marianna

A2 - Vulic, Ivan

PB - Association for Computational Linguistics (ACL)

T2 - Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, DeeLIO 2022

Y2 - 27 May 2022

ER -

Choudhary C, O'Riordan C. Cross-lingual Semantic Role Labelling with the Valpal database knowledge. In Agirre E, Apidianaki M, Vulic I, editors, DeeLIO 2022 - Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Proceedings of the Workshop. Association for Computational Linguistics (ACL). 2022. p. 1-10. (DeeLIO 2022 - Deep Learning Inside Out: 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures, Proceedings of the Workshop).

Cross-lingual Semantic Role Labelling with the Valpal database knowledge

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this