Dialogue-AMR: Abstract meaning representation for dialogue

Claire Bonial; Lucia Donatelli; Mitchell Abrams; Stephanie M. Lukin; Stephen Tratz; Matthew Marge; Ron Artstein; David Traum; Clare R. Voss

Dialogue-AMR: Abstract meaning representation for dialogue

Claire Bonial, Lucia Donatelli, Mitchell Abrams, Stephanie M. Lukin, Stephen Tratz, Matthew Marge, Ron Artstein, David Traum, Clare R. Voss

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

Abstract

© European Language Resources Association (ELRA), licensed under CC-BY-NCThis paper describes a schema that enriches Abstract Meaning Representation (AMR) in order to provide a semantic representation for facilitating Natural Language Understanding (NLU) in dialogue systems. AMR offers a valuable level of abstraction of the propositional content of an utterance; however, it does not capture the illocutionary force or speaker's intended contribution in the broader dialogue context (e.g., make a request or ask a question), nor does it capture tense or aspect. We explore dialogue in the domain of human-robot interaction, where a conversational robot is engaged in search and navigation tasks with a human partner. To address the limitations of standard AMR, we develop an inventory of speech acts suitable for our domain, and present “Dialogue-AMR”, an enhanced AMR that represents not only the content of an utterance, but the illocutionary force behind it, as well as tense and aspect. To showcase the coverage of the schema, we use both manual and automatic methods to construct the “DialAMR” corpus-a corpus of human-robot dialogue annotated with standard AMR and our enriched Dialogue-AMR schema. Our automated methods can be used to incorporate AMR into a larger NLU pipeline supporting human-robot dialogue.

Original language	English
Title of host publication	LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings
Editors	N. Calzolari, F. Bechet, P. Blache, K. Choukri, C. Cieri, T. Declerck, S. Goggi, H. Isahara, B. Maegaard, J. Mariani, H. Mazo, A. Moreno, J. Odijk, S. Piperidis
Publisher	European Language Resources Association (ELRA)
Pages	684-695
ISBN (Electronic)	9791095546344
Publication status	Published - 2020
Externally published	Yes
Event	12th International Conference on Language Resources and Evaluation, LREC 2020 - Marseille, France Duration: 11 May 2020 → 16 May 2020

Conference

Conference	12th International Conference on Language Resources and Evaluation, LREC 2020
Country/Territory	France
City	Marseille
Period	11/05/20 → 16/05/20

Funding

We are grateful to anonymous reviewersfor their feedback. The third author was sponsored by the U.S. Army Research Laboratory (ARL) under the AdvancedResearch Technology, Inc. contract number W911QX-18-F-0096; the seventh and eighth authors were sponsored by ARL under contract number W911NF-14-D-0005. We are grateful to anonymous reviewers for their feedback. The third author was sponsored by the U.S. Army Research Laboratory (ARL) under the Advanced Research Technology, Inc. contract number W911QX-18-F-0096; the seventh and eighth authors were sponsored by ARL under contract number W911NF-14-D-0005.

Funders	Funder number
Advanced Research Technology, Inc.
AdvancedResearch Technology, Inc.	W911QX-18-F-0096, W911NF-14-D-0005
Association of Research Libraries
Army Research Laboratory

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Persistent URL (handle)

Persistent link

Cite this

Bonial, C., Donatelli, L., Abrams, M., Lukin, S. M., Tratz, S., Marge, M., Artstein, R., Traum, D., & Voss, C. R. (2020). Dialogue-AMR: Abstract meaning representation for dialogue. In N. Calzolari, F. Bechet, P. Blache, K. Choukri, C. Cieri, T. Declerck, S. Goggi, H. Isahara, B. Maegaard, J. Mariani, H. Mazo, A. Moreno, J. Odijk, & S. Piperidis (Eds.), LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings (pp. 684-695). European Language Resources Association (ELRA).

Bonial, Claire ; Donatelli, Lucia ; Abrams, Mitchell et al. / Dialogue-AMR : Abstract meaning representation for dialogue. LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings. editor / N. Calzolari ; F. Bechet ; P. Blache ; K. Choukri ; C. Cieri ; T. Declerck ; S. Goggi ; H. Isahara ; B. Maegaard ; J. Mariani ; H. Mazo ; A. Moreno ; J. Odijk ; S. Piperidis. European Language Resources Association (ELRA), 2020. pp. 684-695

@inproceedings{ebbf42bd2e7743aba14f6bc9fc70aef3,

title = "Dialogue-AMR: Abstract meaning representation for dialogue",

abstract = "{\textcopyright} European Language Resources Association (ELRA), licensed under CC-BY-NCThis paper describes a schema that enriches Abstract Meaning Representation (AMR) in order to provide a semantic representation for facilitating Natural Language Understanding (NLU) in dialogue systems. AMR offers a valuable level of abstraction of the propositional content of an utterance; however, it does not capture the illocutionary force or speaker's intended contribution in the broader dialogue context (e.g., make a request or ask a question), nor does it capture tense or aspect. We explore dialogue in the domain of human-robot interaction, where a conversational robot is engaged in search and navigation tasks with a human partner. To address the limitations of standard AMR, we develop an inventory of speech acts suitable for our domain, and present “Dialogue-AMR”, an enhanced AMR that represents not only the content of an utterance, but the illocutionary force behind it, as well as tense and aspect. To showcase the coverage of the schema, we use both manual and automatic methods to construct the “DialAMR” corpus-a corpus of human-robot dialogue annotated with standard AMR and our enriched Dialogue-AMR schema. Our automated methods can be used to incorporate AMR into a larger NLU pipeline supporting human-robot dialogue.",

author = "Claire Bonial and Lucia Donatelli and Mitchell Abrams and Lukin, {Stephanie M.} and Stephen Tratz and Matthew Marge and Ron Artstein and David Traum and Voss, {Clare R.}",

year = "2020",

language = "English",

pages = "684--695",

editor = "N. Calzolari and F. Bechet and P. Blache and K. Choukri and C. Cieri and T. Declerck and S. Goggi and H. Isahara and B. Maegaard and J. Mariani and H. Mazo and A. Moreno and J. Odijk and S. Piperidis",

booktitle = "LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings",

publisher = "European Language Resources Association (ELRA)",

note = "12th International Conference on Language Resources and Evaluation, LREC 2020 ; Conference date: 11-05-2020 Through 16-05-2020",

}

Bonial, C, Donatelli, L, Abrams, M, Lukin, SM, Tratz, S, Marge, M, Artstein, R, Traum, D & Voss, CR 2020, Dialogue-AMR: Abstract meaning representation for dialogue. in N Calzolari, F Bechet, P Blache, K Choukri, C Cieri, T Declerck, S Goggi, H Isahara, B Maegaard, J Mariani, H Mazo, A Moreno, J Odijk & S Piperidis (eds), LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings. European Language Resources Association (ELRA), pp. 684-695, 12th International Conference on Language Resources and Evaluation, LREC 2020, Marseille, France, 11/05/20.

Dialogue-AMR: Abstract meaning representation for dialogue. / Bonial, Claire; Donatelli, Lucia; Abrams, Mitchell et al.
LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings. ed. / N. Calzolari; F. Bechet; P. Blache; K. Choukri; C. Cieri; T. Declerck; S. Goggi; H. Isahara; B. Maegaard; J. Mariani; H. Mazo; A. Moreno; J. Odijk; S. Piperidis. European Language Resources Association (ELRA), 2020. p. 684-695.

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Dialogue-AMR

T2 - 12th International Conference on Language Resources and Evaluation, LREC 2020

AU - Bonial, Claire

AU - Donatelli, Lucia

AU - Abrams, Mitchell

AU - Lukin, Stephanie M.

AU - Tratz, Stephen

AU - Marge, Matthew

AU - Artstein, Ron

AU - Traum, David

AU - Voss, Clare R.

PY - 2020

Y1 - 2020

N2 - © European Language Resources Association (ELRA), licensed under CC-BY-NCThis paper describes a schema that enriches Abstract Meaning Representation (AMR) in order to provide a semantic representation for facilitating Natural Language Understanding (NLU) in dialogue systems. AMR offers a valuable level of abstraction of the propositional content of an utterance; however, it does not capture the illocutionary force or speaker's intended contribution in the broader dialogue context (e.g., make a request or ask a question), nor does it capture tense or aspect. We explore dialogue in the domain of human-robot interaction, where a conversational robot is engaged in search and navigation tasks with a human partner. To address the limitations of standard AMR, we develop an inventory of speech acts suitable for our domain, and present “Dialogue-AMR”, an enhanced AMR that represents not only the content of an utterance, but the illocutionary force behind it, as well as tense and aspect. To showcase the coverage of the schema, we use both manual and automatic methods to construct the “DialAMR” corpus-a corpus of human-robot dialogue annotated with standard AMR and our enriched Dialogue-AMR schema. Our automated methods can be used to incorporate AMR into a larger NLU pipeline supporting human-robot dialogue.

AB - © European Language Resources Association (ELRA), licensed under CC-BY-NCThis paper describes a schema that enriches Abstract Meaning Representation (AMR) in order to provide a semantic representation for facilitating Natural Language Understanding (NLU) in dialogue systems. AMR offers a valuable level of abstraction of the propositional content of an utterance; however, it does not capture the illocutionary force or speaker's intended contribution in the broader dialogue context (e.g., make a request or ask a question), nor does it capture tense or aspect. We explore dialogue in the domain of human-robot interaction, where a conversational robot is engaged in search and navigation tasks with a human partner. To address the limitations of standard AMR, we develop an inventory of speech acts suitable for our domain, and present “Dialogue-AMR”, an enhanced AMR that represents not only the content of an utterance, but the illocutionary force behind it, as well as tense and aspect. To showcase the coverage of the schema, we use both manual and automatic methods to construct the “DialAMR” corpus-a corpus of human-robot dialogue annotated with standard AMR and our enriched Dialogue-AMR schema. Our automated methods can be used to incorporate AMR into a larger NLU pipeline supporting human-robot dialogue.

UR - http://www.scopus.com/inward/record.url?scp=85096605839&partnerID=8YFLogxK

M3 - Conference contribution

SP - 684

EP - 695

BT - LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings

A2 - Calzolari, N.

A2 - Bechet, F.

A2 - Blache, P.

A2 - Choukri, K.

A2 - Cieri, C.

A2 - Declerck, T.

A2 - Goggi, S.

A2 - Isahara, H.

A2 - Maegaard, B.

A2 - Mariani, J.

A2 - Mazo, H.

A2 - Moreno, A.

A2 - Odijk, J.

A2 - Piperidis, S.

PB - European Language Resources Association (ELRA)

Y2 - 11 May 2020 through 16 May 2020

ER -

Bonial C, Donatelli L, Abrams M, Lukin SM, Tratz S, Marge M et al. Dialogue-AMR: Abstract meaning representation for dialogue. In Calzolari N, Bechet F, Blache P, Choukri K, Cieri C, Declerck T, Goggi S, Isahara H, Maegaard B, Mariani J, Mazo H, Moreno A, Odijk J, Piperidis S, editors, LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings. European Language Resources Association (ELRA). 2020. p. 684-695

Dialogue-AMR: Abstract meaning representation for dialogue

Abstract

Conference

Funding

UN SDGs

Persistent URL (handle)

Other files and links

Fingerprint

Cite this