What is it? Disambiguating the different readings of the pronoun 'it'

Sharid Loáiciga; Liane Guillou; Christian Hardmeier

doi:10.18653/v1/D17-1137

What is it? Disambiguating the different readings of the pronoun 'it'

Sharid Loáiciga
, Liane Guillou
, Christian Hardmeier

Uppsala University
University of Edinburgh

Research output: Conference Article in Proceeding or Book/Report chapter › Article in proceedings › Research › peer-review

Abstract

In this paper, we address the problem of predicting one of three functions for the English pronoun `it': anaphoric, event reference or pleonastic. This disambiguation is valuable in the context of machine translation and coreference resolution. We present experiments using a MAXENT classifier trained on gold-standard data and self-training experiments of an RNN trained on silver-standard data, annotated using the MAXENT classifier. Lastly, we report on an analysis of the strengths of these two models.

Original language	English
Title of host publication	Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
Number of pages	7
Publication date	1 Sept 2017
Pages	1325–1331
ISBN (Print)	978-1-945626-97-5
DOIs	https://doi.org/10.18653/v1/D17-1137
Publication status	Published - 1 Sept 2017
Externally published	Yes

Keywords

anaphora resolution
pleonastic it
coreference resolution
maximum entropy classifier
self-training

Access to Document

10.18653/v1/D17-1137

Cite this

@inproceedings{58063a65dfba4f9688db4b46f5dc0631,

title = "What is it? Disambiguating the different readings of the pronoun 'it'",

abstract = "In this paper, we address the problem of predicting one of three functions for the English pronoun `it': anaphoric, event reference or pleonastic. This disambiguation is valuable in the context of machine translation and coreference resolution. We present experiments using a MAXENT classifier trained on gold-standard data and self-training experiments of an RNN trained on silver-standard data, annotated using the MAXENT classifier. Lastly, we report on an analysis of the strengths of these two models.",

keywords = "anaphora resolution, pleonastic it, coreference resolution, maximum entropy classifier, self-training",

author = "Sharid Lo{\'a}iciga and Liane Guillou and Christian Hardmeier",

year = "2017",

month = sep,

day = "1",

doi = "10.18653/v1/D17-1137",

language = "English",

isbn = "978-1-945626-97-5",

pages = "1325–1331",

booktitle = "Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing",

}

TY - GEN

T1 - What is it? Disambiguating the different readings of the pronoun 'it'

AU - Loáiciga, Sharid

AU - Guillou, Liane

AU - Hardmeier, Christian

PY - 2017/9/1

Y1 - 2017/9/1

N2 - In this paper, we address the problem of predicting one of three functions for the English pronoun `it': anaphoric, event reference or pleonastic. This disambiguation is valuable in the context of machine translation and coreference resolution. We present experiments using a MAXENT classifier trained on gold-standard data and self-training experiments of an RNN trained on silver-standard data, annotated using the MAXENT classifier. Lastly, we report on an analysis of the strengths of these two models.

AB - In this paper, we address the problem of predicting one of three functions for the English pronoun `it': anaphoric, event reference or pleonastic. This disambiguation is valuable in the context of machine translation and coreference resolution. We present experiments using a MAXENT classifier trained on gold-standard data and self-training experiments of an RNN trained on silver-standard data, annotated using the MAXENT classifier. Lastly, we report on an analysis of the strengths of these two models.

KW - anaphora resolution

KW - pleonastic it

KW - coreference resolution

KW - maximum entropy classifier

KW - self-training

U2 - 10.18653/v1/D17-1137

DO - 10.18653/v1/D17-1137

M3 - Article in proceedings

SN - 978-1-945626-97-5

SP - 1325

EP - 1331

BT - Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

ER -

What is it? Disambiguating the different readings of the pronoun 'it'

Abstract

Keywords

Access to Document

Fingerprint

Cite this