@inproceedings{rohanian-etal-2017-using,
title = "Using Gaze Data to Predict Multiword Expressions",
author = "Rohanian, Omid and
Taslimipoor, Shiva and
Yaneva, Victoria and
Ha, Le An",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference Recent Advances in Natural Language Processing, {RANLP} 2017",
month = sep,
year = "2017",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://doi.org/10.26615/978-954-452-049-6_078",
doi = "10.26615/978-954-452-049-6_078",
pages = "601--609",
abstract = "In recent years gaze data has been increasingly used to improve and evaluate NLP models due to the fact that it carries information about the cognitive processing of linguistic phenomena. In this paper we conduct a preliminary study towards the automatic identification of multiword expressions based on gaze features from native and non-native speakers of English. We report comparisons between a part-of-speech (POS) and frequency baseline to: i) a prediction model based solely on gaze data and ii) a combined model of gaze data, POS and frequency. In spite of the challenging nature of the task, best performance was achieved by the latter. Furthermore, we explore how the type of gaze data (from native versus non-native speakers) affects the prediction, showing that data from the two groups is discriminative to an equal degree for the task. Finally, we show that late processing measures are more predictive than early ones, which is in line with previous research on idioms and other formulaic structures.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rohanian-etal-2017-using">
<titleInfo>
<title>Using Gaze Data to Predict Multiword Expressions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Omid</namePart>
<namePart type="family">Rohanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiva</namePart>
<namePart type="family">Taslimipoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Le</namePart>
<namePart type="given">An</namePart>
<namePart type="family">Ha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years gaze data has been increasingly used to improve and evaluate NLP models due to the fact that it carries information about the cognitive processing of linguistic phenomena. In this paper we conduct a preliminary study towards the automatic identification of multiword expressions based on gaze features from native and non-native speakers of English. We report comparisons between a part-of-speech (POS) and frequency baseline to: i) a prediction model based solely on gaze data and ii) a combined model of gaze data, POS and frequency. In spite of the challenging nature of the task, best performance was achieved by the latter. Furthermore, we explore how the type of gaze data (from native versus non-native speakers) affects the prediction, showing that data from the two groups is discriminative to an equal degree for the task. Finally, we show that late processing measures are more predictive than early ones, which is in line with previous research on idioms and other formulaic structures.</abstract>
<identifier type="citekey">rohanian-etal-2017-using</identifier>
<identifier type="doi">10.26615/978-954-452-049-6_078</identifier>
<part>
<date>2017-09</date>
<extent unit="page">
<start>601</start>
<end>609</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Gaze Data to Predict Multiword Expressions
%A Rohanian, Omid
%A Taslimipoor, Shiva
%A Yaneva, Victoria
%A Ha, Le An
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
%D 2017
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F rohanian-etal-2017-using
%X In recent years gaze data has been increasingly used to improve and evaluate NLP models due to the fact that it carries information about the cognitive processing of linguistic phenomena. In this paper we conduct a preliminary study towards the automatic identification of multiword expressions based on gaze features from native and non-native speakers of English. We report comparisons between a part-of-speech (POS) and frequency baseline to: i) a prediction model based solely on gaze data and ii) a combined model of gaze data, POS and frequency. In spite of the challenging nature of the task, best performance was achieved by the latter. Furthermore, we explore how the type of gaze data (from native versus non-native speakers) affects the prediction, showing that data from the two groups is discriminative to an equal degree for the task. Finally, we show that late processing measures are more predictive than early ones, which is in line with previous research on idioms and other formulaic structures.
%R 10.26615/978-954-452-049-6_078
%U https://doi.org/10.26615/978-954-452-049-6_078
%P 601-609
Markdown (Informal)
[Using Gaze Data to Predict Multiword Expressions](https://doi.org/10.26615/978-954-452-049-6_078) (Rohanian et al., RANLP 2017)
ACL
- Omid Rohanian, Shiva Taslimipoor, Victoria Yaneva, and Le An Ha. 2017. Using Gaze Data to Predict Multiword Expressions. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 601–609, Varna, Bulgaria. INCOMA Ltd..