@inproceedings{prabhu-etal-2019-incorporating,
title = "Incorporating Sub-Word Level Information in Language Invariant Neural Event Detection",
author = "Prabhu, Suhan and
Goel, Pranav and
Debnath, Alok and
Shrivastava, Manish",
editor = "Sharma, Dipti Misra and
Bhattacharya, Pushpak",
booktitle = "Proceedings of the 16th International Conference on Natural Language Processing",
month = dec,
year = "2019",
address = "International Institute of Information Technology, Hyderabad, India",
publisher = "NLP Association of India",
url = "https://aclanthology.org/2019.icon-1.5",
pages = "36--44",
abstract = "Detection of TimeML events in text have traditionally been done on corpora such as TimeBanks. However, deep learning methods have not been applied to these corpora, because these datasets seldom contain more than 10,000 event mentions. Traditional architectures revolve around highly feature engineered, language specific statistical models. In this paper, we present a Language Invariant Neural Event Detection (ALINED) architecture. ALINED uses an aggregation of both sub-word level features as well as lexical and structural information. This is achieved by combining convolution over character embeddings, with recurrent layers over contextual word embeddings. We find that our model extracts relevant features for event span identification without relying on language specific features. We compare the performance of our language invariant model to the current state-of-the-art in English, Spanish, Italian and French. We outperform the F1-score of the state of the art in English by 1.65 points. We achieve F1-scores of 84.96, 80.87 and 74.81 on Spanish, Italian and French respectively which is comparable to the current states of the art for these languages. We also introduce the automatic annotation of events in Hindi, a low resource language, with an F1-Score of 77.13.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="prabhu-etal-2019-incorporating">
<titleInfo>
<title>Incorporating Sub-Word Level Information in Language Invariant Neural Event Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Suhan</namePart>
<namePart type="family">Prabhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranav</namePart>
<namePart type="family">Goel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alok</namePart>
<namePart type="family">Debnath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manish</namePart>
<namePart type="family">Shrivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Conference on Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="given">Misra</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushpak</namePart>
<namePart type="family">Bhattacharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India</publisher>
<place>
<placeTerm type="text">International Institute of Information Technology, Hyderabad, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Detection of TimeML events in text have traditionally been done on corpora such as TimeBanks. However, deep learning methods have not been applied to these corpora, because these datasets seldom contain more than 10,000 event mentions. Traditional architectures revolve around highly feature engineered, language specific statistical models. In this paper, we present a Language Invariant Neural Event Detection (ALINED) architecture. ALINED uses an aggregation of both sub-word level features as well as lexical and structural information. This is achieved by combining convolution over character embeddings, with recurrent layers over contextual word embeddings. We find that our model extracts relevant features for event span identification without relying on language specific features. We compare the performance of our language invariant model to the current state-of-the-art in English, Spanish, Italian and French. We outperform the F1-score of the state of the art in English by 1.65 points. We achieve F1-scores of 84.96, 80.87 and 74.81 on Spanish, Italian and French respectively which is comparable to the current states of the art for these languages. We also introduce the automatic annotation of events in Hindi, a low resource language, with an F1-Score of 77.13.</abstract>
<identifier type="citekey">prabhu-etal-2019-incorporating</identifier>
<location>
<url>https://aclanthology.org/2019.icon-1.5</url>
</location>
<part>
<date>2019-12</date>
<extent unit="page">
<start>36</start>
<end>44</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Incorporating Sub-Word Level Information in Language Invariant Neural Event Detection
%A Prabhu, Suhan
%A Goel, Pranav
%A Debnath, Alok
%A Shrivastava, Manish
%Y Sharma, Dipti Misra
%Y Bhattacharya, Pushpak
%S Proceedings of the 16th International Conference on Natural Language Processing
%D 2019
%8 December
%I NLP Association of India
%C International Institute of Information Technology, Hyderabad, India
%F prabhu-etal-2019-incorporating
%X Detection of TimeML events in text have traditionally been done on corpora such as TimeBanks. However, deep learning methods have not been applied to these corpora, because these datasets seldom contain more than 10,000 event mentions. Traditional architectures revolve around highly feature engineered, language specific statistical models. In this paper, we present a Language Invariant Neural Event Detection (ALINED) architecture. ALINED uses an aggregation of both sub-word level features as well as lexical and structural information. This is achieved by combining convolution over character embeddings, with recurrent layers over contextual word embeddings. We find that our model extracts relevant features for event span identification without relying on language specific features. We compare the performance of our language invariant model to the current state-of-the-art in English, Spanish, Italian and French. We outperform the F1-score of the state of the art in English by 1.65 points. We achieve F1-scores of 84.96, 80.87 and 74.81 on Spanish, Italian and French respectively which is comparable to the current states of the art for these languages. We also introduce the automatic annotation of events in Hindi, a low resource language, with an F1-Score of 77.13.
%U https://aclanthology.org/2019.icon-1.5
%P 36-44
Markdown (Informal)
[Incorporating Sub-Word Level Information in Language Invariant Neural Event Detection](https://aclanthology.org/2019.icon-1.5) (Prabhu et al., ICON 2019)
ACL