Event versus entity co-reference: Effects of context and form of referring expression

Sharid Loáiciga; Luca Bevacqua; Hannah Rohde; Christian Hardmeier

doi:10.18653/v1/W18-0711

Event versus entity co-reference: Effects of context and form of referring expression

Sharid Loáiciga, Luca Bevacqua, Hannah Rohde, Christian Hardmeier

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

Abstract / Description of output

Anaphora resolution systems require both an enumeration of possible candidate antecedents and an identification process of the antecedent. This paper focuses on (i) the impact of the form of referring expression on entity-vs-event preferences and (ii) how properties of the passage interact with referential form. Two crowd-sourced story-continuation experiments were conducted, using constructed and naturally-occurring passages, to see how participants interpret It and This pronouns following a context sentence that makes available event and entity referents. Our participants show a strong, but not categorical, bias to use This to refer to events and It to refer to entities. However, these preferences vary with passage characteristics such as verb class (a proxy in our constructed examples for the number of explicit and implicit entities) and more subtle author intentions regarding subsequent re-mention (the original event-vs-entity re-mention of our corpus items).

Original language	English
Title of host publication	Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference
Place of Publication	New Orleans, Louisiana
Publisher	Association for Computational Linguistics
Pages	97-103
Number of pages	7
ISBN (Electronic)	978-1-948087-13-1
DOIs	https://doi.org/10.18653/v1/W18-0711
Publication status	Published - 1 Jun 2018
Event	16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Hyatt Regency New Orleans Hotel, New Orleans, United States Duration: 1 Jun 2018 → 6 Jun 2018 http://naacl2018.org/

Conference

Conference	16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Abbreviated title	NAACL HLT 2018
Country/Territory	United States
City	New Orleans
Period	1/06/18 → 6/06/18
Internet address	http://naacl2018.org/

Access to Document

10.18653/v1/W18-0711Licence: Creative Commons: Attribution (CC-BY)

Event versus entity_LOAICIGA_DOA17112017_VOR_CC-BYFinal published version, 145 KBLicence: Creative Commons: Attribution (CC-BY)

https://www.aclweb.org/anthology/W18-0711Licence: Creative Commons: Attribution (CC-BY)

Cite this

@inproceedings{bb47575fa96a442e903bc9f1fb452477,

title = "Event versus entity co-reference: Effects of context and form of referring expression",

abstract = "Anaphora resolution systems require both an enumeration of possible candidate antecedents and an identification process of the antecedent. This paper focuses on (i) the impact of the form of referring expression on entity-vs-event preferences and (ii) how properties of the passage interact with referential form. Two crowd-sourced story-continuation experiments were conducted, using constructed and naturally-occurring passages, to see how participants interpret It and This pronouns following a context sentence that makes available event and entity referents. Our participants show a strong, but not categorical, bias to use This to refer to events and It to refer to entities. However, these preferences vary with passage characteristics such as verb class (a proxy in our constructed examples for the number of explicit and implicit entities) and more subtle author intentions regarding subsequent re-mention (the original event-vs-entity re-mention of our corpus items).",

author = "Sharid Lo{\'a}iciga and Luca Bevacqua and Hannah Rohde and Christian Hardmeier",

year = "2018",

month = jun,

day = "1",

doi = "10.18653/v1/W18-0711",

language = "English",

pages = "97--103",

booktitle = "Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference",

publisher = "Association for Computational Linguistics",

note = "16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 ; Conference date: 01-06-2018 Through 06-06-2018",

url = "http://naacl2018.org/",

}

Loáiciga, S, Bevacqua, L, Rohde, H & Hardmeier, C 2018, Event versus entity co-reference: Effects of context and form of referring expression. in Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference. Association for Computational Linguistics, New Orleans, Louisiana, pp. 97-103, 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, Louisiana, United States, 1/06/18. https://doi.org/10.18653/v1/W18-0711

Event versus entity co-reference: Effects of context and form of referring expression. / Loáiciga, Sharid; Bevacqua, Luca; Rohde, Hannah et al.
Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference. New Orleans, Louisiana: Association for Computational Linguistics, 2018. p. 97-103.

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

TY - GEN

T1 - Event versus entity co-reference: Effects of context and form of referring expression

AU - Loáiciga, Sharid

AU - Bevacqua, Luca

AU - Rohde, Hannah

AU - Hardmeier, Christian

PY - 2018/6/1

Y1 - 2018/6/1

N2 - Anaphora resolution systems require both an enumeration of possible candidate antecedents and an identification process of the antecedent. This paper focuses on (i) the impact of the form of referring expression on entity-vs-event preferences and (ii) how properties of the passage interact with referential form. Two crowd-sourced story-continuation experiments were conducted, using constructed and naturally-occurring passages, to see how participants interpret It and This pronouns following a context sentence that makes available event and entity referents. Our participants show a strong, but not categorical, bias to use This to refer to events and It to refer to entities. However, these preferences vary with passage characteristics such as verb class (a proxy in our constructed examples for the number of explicit and implicit entities) and more subtle author intentions regarding subsequent re-mention (the original event-vs-entity re-mention of our corpus items).

AB - Anaphora resolution systems require both an enumeration of possible candidate antecedents and an identification process of the antecedent. This paper focuses on (i) the impact of the form of referring expression on entity-vs-event preferences and (ii) how properties of the passage interact with referential form. Two crowd-sourced story-continuation experiments were conducted, using constructed and naturally-occurring passages, to see how participants interpret It and This pronouns following a context sentence that makes available event and entity referents. Our participants show a strong, but not categorical, bias to use This to refer to events and It to refer to entities. However, these preferences vary with passage characteristics such as verb class (a proxy in our constructed examples for the number of explicit and implicit entities) and more subtle author intentions regarding subsequent re-mention (the original event-vs-entity re-mention of our corpus items).

U2 - 10.18653/v1/W18-0711

DO - 10.18653/v1/W18-0711

M3 - Conference contribution

SP - 97

EP - 103

BT - Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference

PB - Association for Computational Linguistics

CY - New Orleans, Louisiana

T2 - 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Y2 - 1 June 2018 through 6 June 2018

ER -

Event versus entity co-reference: Effects of context and form of referring expression

Abstract / Description of output

Conference

Access to Document

Fingerprint

Cite this