Hierarchical multi-task natural language understanding for cross-domain conversational AI: HERMIT NLU

Andrea Vanzo; Emanuele Bastianelli; Oliver Lemon

doi:10.18653/v1/W19-5931

Hierarchical multi-task natural language understanding for cross-domain conversational AI: HERMIT NLU

Andrea Vanzo, Emanuele Bastianelli, Oliver Lemon

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

12 Citations (Scopus)

10 Downloads (Pure)

Abstract

We present a new neural architecture for wide-coverage Natural Language Understanding in Spoken Dialogue Systems. We develop a hierarchical multi-task architecture, which delivers a multi-layer representation of sentence meaning (i.e., Dialogue Acts and Frame-like structures). The architecture is a hierarchy of self-attention mechanisms and BiLSTM encoders followed by CRF tagging layers. We describe a variety of experiments, showing that our approach obtains promising results on a dataset annotated with Dialogue Acts and Frame Semantics. Moreover, we demonstrate its applicability to a different, publicly available NLU dataset annotated with domain-specific intents and corresponding semantic roles, providing overall performance higher than state-of-the-art tools such as RASA, Dialogflow, LUIS, and Watson. For example, we show an average 4.45% improvement in entity tagging F-score over Rasa, Dialogflow and LUIS.

Original language	English
Title of host publication	Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
Publisher	Association for Computational Linguistics
Pages	254-263
Number of pages	10
ISBN (Electronic)	9781950737611
DOIs	https://doi.org/10.18653/v1/W19-5931
Publication status	Published - Sept 2019
Event	20th Annual Meeting of the Special Interest Group on Discourse and Dialogue 2019 - Stockholm, Sweden Duration: 11 Sept 2019 → 13 Sept 2019

Conference

Conference	20th Annual Meeting of the Special Interest Group on Discourse and Dialogue 2019
Abbreviated title	SIGDIAL 2019
Country/Territory	Sweden
City	Stockholm
Period	11/09/19 → 13/09/19

ASJC Scopus subject areas

Computer Graphics and Computer-Aided Design
Computer Vision and Pattern Recognition
Human-Computer Interaction
Modelling and Simulation

Access to Document

10.18653/v1/W19-5931Licence: CC BY

Download pdf
©2019 Association for Computational Linguistics
Final published version, 319 KBLicence: CC BY

Cite this

@inproceedings{a11abe8bb2d9432a8fc8a1fa21de1d57,

title = "Hierarchical multi-task natural language understanding for cross-domain conversational AI: HERMIT NLU",

abstract = "We present a new neural architecture for wide-coverage Natural Language Understanding in Spoken Dialogue Systems. We develop a hierarchical multi-task architecture, which delivers a multi-layer representation of sentence meaning (i.e., Dialogue Acts and Frame-like structures). The architecture is a hierarchy of self-attention mechanisms and BiLSTM encoders followed by CRF tagging layers. We describe a variety of experiments, showing that our approach obtains promising results on a dataset annotated with Dialogue Acts and Frame Semantics. Moreover, we demonstrate its applicability to a different, publicly available NLU dataset annotated with domain-specific intents and corresponding semantic roles, providing overall performance higher than state-of-the-art tools such as RASA, Dialogflow, LUIS, and Watson. For example, we show an average 4.45% improvement in entity tagging F-score over Rasa, Dialogflow and LUIS.",

author = "Andrea Vanzo and Emanuele Bastianelli and Oliver Lemon",

note = "Funding Information: This research was partially supported by the European Union{\textquoteright}s Horizon 2020 research and innovation programme under grant agreement No. 688147 (MuMMER project10). Publisher Copyright: {\textcopyright}2019 Association for Computational Linguistics; 20th Annual Meeting of the Special Interest Group on Discourse and Dialogue 2019, SIGDIAL 2019 ; Conference date: 11-09-2019 Through 13-09-2019",

year = "2019",

month = sep,

doi = "10.18653/v1/W19-5931",

language = "English",

pages = "254--263",

booktitle = "Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue",

publisher = "Association for Computational Linguistics",

}

Vanzo, A, Bastianelli, E & Lemon, O 2019, Hierarchical multi-task natural language understanding for cross-domain conversational AI: HERMIT NLU. in Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue. Association for Computational Linguistics, pp. 254-263, 20th Annual Meeting of the Special Interest Group on Discourse and Dialogue 2019, Stockholm, Sweden, 11/09/19. https://doi.org/10.18653/v1/W19-5931

Hierarchical multi-task natural language understanding for cross-domain conversational AI : HERMIT NLU. / Vanzo, Andrea; Bastianelli, Emanuele; Lemon, Oliver.

Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue. Association for Computational Linguistics, 2019. p. 254-263.

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

TY - GEN

T1 - Hierarchical multi-task natural language understanding for cross-domain conversational AI

T2 - 20th Annual Meeting of the Special Interest Group on Discourse and Dialogue 2019

AU - Vanzo, Andrea

AU - Bastianelli, Emanuele

AU - Lemon, Oliver

N1 - Funding Information: This research was partially supported by the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 688147 (MuMMER project10). Publisher Copyright: ©2019 Association for Computational Linguistics

PY - 2019/9

Y1 - 2019/9

N2 - We present a new neural architecture for wide-coverage Natural Language Understanding in Spoken Dialogue Systems. We develop a hierarchical multi-task architecture, which delivers a multi-layer representation of sentence meaning (i.e., Dialogue Acts and Frame-like structures). The architecture is a hierarchy of self-attention mechanisms and BiLSTM encoders followed by CRF tagging layers. We describe a variety of experiments, showing that our approach obtains promising results on a dataset annotated with Dialogue Acts and Frame Semantics. Moreover, we demonstrate its applicability to a different, publicly available NLU dataset annotated with domain-specific intents and corresponding semantic roles, providing overall performance higher than state-of-the-art tools such as RASA, Dialogflow, LUIS, and Watson. For example, we show an average 4.45% improvement in entity tagging F-score over Rasa, Dialogflow and LUIS.

AB - We present a new neural architecture for wide-coverage Natural Language Understanding in Spoken Dialogue Systems. We develop a hierarchical multi-task architecture, which delivers a multi-layer representation of sentence meaning (i.e., Dialogue Acts and Frame-like structures). The architecture is a hierarchy of self-attention mechanisms and BiLSTM encoders followed by CRF tagging layers. We describe a variety of experiments, showing that our approach obtains promising results on a dataset annotated with Dialogue Acts and Frame Semantics. Moreover, we demonstrate its applicability to a different, publicly available NLU dataset annotated with domain-specific intents and corresponding semantic roles, providing overall performance higher than state-of-the-art tools such as RASA, Dialogflow, LUIS, and Watson. For example, we show an average 4.45% improvement in entity tagging F-score over Rasa, Dialogflow and LUIS.

UR - http://www.scopus.com/inward/record.url?scp=85091558715&partnerID=8YFLogxK

U2 - 10.18653/v1/W19-5931

DO - 10.18653/v1/W19-5931

M3 - Conference contribution

AN - SCOPUS:85091558715

SP - 254

EP - 263

BT - Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue

PB - Association for Computational Linguistics

Y2 - 11 September 2019 through 13 September 2019

ER -

Hierarchical multi-task natural language understanding for cross-domain conversational AI: HERMIT NLU

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this