Querent intent in multi-sentence questions

Laurie Burchell; Jie Chi; Tom Hosking; Nina Markl; Bonnie Webber

Querent intent in multi-sentence questions

Laurie Burchell, Jie Chi, Tom Hosking, Nina Markl, Bonnie Webber

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

Abstract / Description of output

Multi-sentence questions (MSQs) are sequences of questions connected by relations which, unlike sequences of standalone questions, need to be answered as a unit. Following Rhetorical Structure Theory (RST), we recognise that different "question discourse relations'' between the subparts of MSQs reflect different speaker intents, and consequently elicit different answering strategies. Correctly identifying these relations is therefore a crucial step in automatically answering MSQs. We identify five different types of MSQs in English, and define five novel relations to describe them. We extract over 162,000 MSQs from Stack Exchange to enable future research. Finally, we implement a high-precision baseline classifier based on surface features.

Original language	English
Title of host publication	Proceedings of the 14th Linguistic Annotation Workshop
Editors	Stefanie Dipper, Amir Zeldes
Place of Publication	Barcelona, Spain
Publisher	Association for Computational Linguistics
Pages	138-147
Number of pages	10
ISBN (Electronic)	9781952148330
Publication status	Published - 1 Dec 2020
Event	The 14th Linguistic Annotation Workshop - Barcelona, Spain Duration: 12 Dec 2020 → 12 Dec 2020 Conference number: 14 https://sigann.github.io/LAW-XIV-2020/

Workshop

Workshop	The 14th Linguistic Annotation Workshop
Abbreviated title	LAW XIV
Country/Territory	Spain
City	Barcelona
Period	12/12/20 → 12/12/20
Internet address	https://sigann.github.io/LAW-XIV-2020/

Access to Document

Querent Intent_BURCHELL_DOA08102020_VOR_CC-BYFinal published version, 422 KBLicence: Creative Commons: Attribution (CC-BY)

https://aclanthology.org/2020.law-1.13Licence: Creative Commons: Attribution (CC-BY)

Cite this

@inproceedings{6fa83039786942cd9ad2b43e4bc6fd2d,

title = "Querent intent in multi-sentence questions",

abstract = "Multi-sentence questions (MSQs) are sequences of questions connected by relations which, unlike sequences of standalone questions, need to be answered as a unit. Following Rhetorical Structure Theory (RST), we recognise that different {"}question discourse relations'' between the subparts of MSQs reflect different speaker intents, and consequently elicit different answering strategies. Correctly identifying these relations is therefore a crucial step in automatically answering MSQs. We identify five different types of MSQs in English, and define five novel relations to describe them. We extract over 162,000 MSQs from Stack Exchange to enable future research. Finally, we implement a high-precision baseline classifier based on surface features.",

author = "Laurie Burchell and Jie Chi and Tom Hosking and Nina Markl and Bonnie Webber",

year = "2020",

month = dec,

day = "1",

language = "English",

pages = "138--147",

editor = "Stefanie Dipper and Amir Zeldes",

booktitle = "Proceedings of the 14th Linguistic Annotation Workshop",

publisher = "Association for Computational Linguistics",

note = "The 14th Linguistic Annotation Workshop, LAW XIV ; Conference date: 12-12-2020 Through 12-12-2020",

url = "https://sigann.github.io/LAW-XIV-2020/",

}

Burchell, L, Chi, J, Hosking, T, Markl, N & Webber, B 2020, Querent intent in multi-sentence questions. in S Dipper & A Zeldes (eds), Proceedings of the 14th Linguistic Annotation Workshop. Association for Computational Linguistics, Barcelona, Spain, pp. 138-147, The 14th Linguistic Annotation Workshop, Barcelona, Spain, 12/12/20. <https://aclanthology.org/2020.law-1.13>

TY - GEN

T1 - Querent intent in multi-sentence questions

AU - Burchell, Laurie

AU - Chi, Jie

AU - Hosking, Tom

AU - Markl, Nina

AU - Webber, Bonnie

N1 - Conference code: 14

PY - 2020/12/1

Y1 - 2020/12/1

N2 - Multi-sentence questions (MSQs) are sequences of questions connected by relations which, unlike sequences of standalone questions, need to be answered as a unit. Following Rhetorical Structure Theory (RST), we recognise that different "question discourse relations'' between the subparts of MSQs reflect different speaker intents, and consequently elicit different answering strategies. Correctly identifying these relations is therefore a crucial step in automatically answering MSQs. We identify five different types of MSQs in English, and define five novel relations to describe them. We extract over 162,000 MSQs from Stack Exchange to enable future research. Finally, we implement a high-precision baseline classifier based on surface features.

AB - Multi-sentence questions (MSQs) are sequences of questions connected by relations which, unlike sequences of standalone questions, need to be answered as a unit. Following Rhetorical Structure Theory (RST), we recognise that different "question discourse relations'' between the subparts of MSQs reflect different speaker intents, and consequently elicit different answering strategies. Correctly identifying these relations is therefore a crucial step in automatically answering MSQs. We identify five different types of MSQs in English, and define five novel relations to describe them. We extract over 162,000 MSQs from Stack Exchange to enable future research. Finally, we implement a high-precision baseline classifier based on surface features.

M3 - Conference contribution

SP - 138

EP - 147

BT - Proceedings of the 14th Linguistic Annotation Workshop

A2 - Dipper, Stefanie

A2 - Zeldes, Amir

PB - Association for Computational Linguistics

CY - Barcelona, Spain

T2 - The 14th Linguistic Annotation Workshop

Y2 - 12 December 2020 through 12 December 2020

ER -

Querent intent in multi-sentence questions

Abstract / Description of output

Workshop

Access to Document

Fingerprint

Cite this