@inproceedings{kurfali-wiren-2020-zero,
title = "Zero-shot cross-lingual identification of direct speech using distant supervision",
author = "Kurfal{\i}, Murathan and
Wir{\'e}n, Mats",
editor = "DeGaetano, Stefania and
Kazantseva, Anna and
Reiter, Nils and
Szpakowicz, Stan",
booktitle = "Proceedings of the 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature",
month = dec,
year = "2020",
address = "Online",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.latechclfl-1.12",
pages = "105--111",
abstract = "Prose fiction typically consists of passages alternating between the narrator{'}s telling of the story and the characters{'} direct speech in that story. Detecting direct speech is crucial for the downstream analysis of narrative structure, and may seem easy at first thanks to quotation marks. However, typographical conventions vary across languages, and as a result, almost all approaches to this problem have been monolingual. In contrast, the aim of this paper is to provide a multilingual method for identifying direct speech. To this end, we created a training corpus by using a set of heuristics to automatically find texts where quotation marks appear sufficiently consistently. We then removed the quotation marks and developed a sequence classifier based on multilingual-BERT which classifies each token as belonging to narration or speech. Crucially, by training the classifier with the quotation marks removed, it was forced to learn the linguistic characteristics of direct speech rather than the typography of quotation marks. The results in the zero-shot setting of the proposed model are comparable to the strong supervised baselines, indicating that this is a feasible approach.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kurfali-wiren-2020-zero">
<titleInfo>
<title>Zero-shot cross-lingual identification of direct speech using distant supervision</title>
</titleInfo>
<name type="personal">
<namePart type="given">Murathan</namePart>
<namePart type="family">Kurfalı</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mats</namePart>
<namePart type="family">Wirén</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">DeGaetano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kazantseva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Szpakowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Prose fiction typically consists of passages alternating between the narrator’s telling of the story and the characters’ direct speech in that story. Detecting direct speech is crucial for the downstream analysis of narrative structure, and may seem easy at first thanks to quotation marks. However, typographical conventions vary across languages, and as a result, almost all approaches to this problem have been monolingual. In contrast, the aim of this paper is to provide a multilingual method for identifying direct speech. To this end, we created a training corpus by using a set of heuristics to automatically find texts where quotation marks appear sufficiently consistently. We then removed the quotation marks and developed a sequence classifier based on multilingual-BERT which classifies each token as belonging to narration or speech. Crucially, by training the classifier with the quotation marks removed, it was forced to learn the linguistic characteristics of direct speech rather than the typography of quotation marks. The results in the zero-shot setting of the proposed model are comparable to the strong supervised baselines, indicating that this is a feasible approach.</abstract>
<identifier type="citekey">kurfali-wiren-2020-zero</identifier>
<location>
<url>https://aclanthology.org/2020.latechclfl-1.12</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>105</start>
<end>111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Zero-shot cross-lingual identification of direct speech using distant supervision
%A Kurfalı, Murathan
%A Wirén, Mats
%Y DeGaetano, Stefania
%Y Kazantseva, Anna
%Y Reiter, Nils
%Y Szpakowicz, Stan
%S Proceedings of the 4th Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Online
%F kurfali-wiren-2020-zero
%X Prose fiction typically consists of passages alternating between the narrator’s telling of the story and the characters’ direct speech in that story. Detecting direct speech is crucial for the downstream analysis of narrative structure, and may seem easy at first thanks to quotation marks. However, typographical conventions vary across languages, and as a result, almost all approaches to this problem have been monolingual. In contrast, the aim of this paper is to provide a multilingual method for identifying direct speech. To this end, we created a training corpus by using a set of heuristics to automatically find texts where quotation marks appear sufficiently consistently. We then removed the quotation marks and developed a sequence classifier based on multilingual-BERT which classifies each token as belonging to narration or speech. Crucially, by training the classifier with the quotation marks removed, it was forced to learn the linguistic characteristics of direct speech rather than the typography of quotation marks. The results in the zero-shot setting of the proposed model are comparable to the strong supervised baselines, indicating that this is a feasible approach.
%U https://aclanthology.org/2020.latechclfl-1.12
%P 105-111
Markdown (Informal)
[Zero-shot cross-lingual identification of direct speech using distant supervision](https://aclanthology.org/2020.latechclfl-1.12) (Kurfalı & Wirén, LaTeCHCLfL 2020)
ACL