@inproceedings{popov-sikos-2019-graph,
title = "Graph Embeddings for Frame Identification",
author = "Popov, Alexander and
Sikos, Jennifer",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)",
month = sep,
year = "2019",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://aclanthology.org/R19-1109",
doi = "10.26615/978-954-452-056-4_109",
pages = "939--948",
abstract = "Lexical resources such as WordNet (Miller, 1995) and FrameNet (Baker et al., 1998) are organized as graphs, where relationships between words are made explicit via the structure of the resource. This work explores how structural information from these lexical resources can lead to gains in a downstream task, namely frame identification. While much of the current work in frame identification uses various neural architectures to predict frames, those neural architectures only use representations of frames based on annotated corpus data. We demonstrate how incorporating knowledge directly from the FrameNet graph structure improves the performance of a neural network-based frame identification system. Specifically, we construct a bidirectional LSTM with a loss function that incorporates various graph- and corpus-based frame embeddings for learning and ultimately achieves strong performance gains with the graph-based embeddings over corpus-based embeddings alone.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="popov-sikos-2019-graph">
<titleInfo>
<title>Graph Embeddings for Frame Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Popov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jennifer</namePart>
<namePart type="family">Sikos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)</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>Lexical resources such as WordNet (Miller, 1995) and FrameNet (Baker et al., 1998) are organized as graphs, where relationships between words are made explicit via the structure of the resource. This work explores how structural information from these lexical resources can lead to gains in a downstream task, namely frame identification. While much of the current work in frame identification uses various neural architectures to predict frames, those neural architectures only use representations of frames based on annotated corpus data. We demonstrate how incorporating knowledge directly from the FrameNet graph structure improves the performance of a neural network-based frame identification system. Specifically, we construct a bidirectional LSTM with a loss function that incorporates various graph- and corpus-based frame embeddings for learning and ultimately achieves strong performance gains with the graph-based embeddings over corpus-based embeddings alone.</abstract>
<identifier type="citekey">popov-sikos-2019-graph</identifier>
<identifier type="doi">10.26615/978-954-452-056-4_109</identifier>
<location>
<url>https://aclanthology.org/R19-1109</url>
</location>
<part>
<date>2019-09</date>
<extent unit="page">
<start>939</start>
<end>948</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Graph Embeddings for Frame Identification
%A Popov, Alexander
%A Sikos, Jennifer
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
%D 2019
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F popov-sikos-2019-graph
%X Lexical resources such as WordNet (Miller, 1995) and FrameNet (Baker et al., 1998) are organized as graphs, where relationships between words are made explicit via the structure of the resource. This work explores how structural information from these lexical resources can lead to gains in a downstream task, namely frame identification. While much of the current work in frame identification uses various neural architectures to predict frames, those neural architectures only use representations of frames based on annotated corpus data. We demonstrate how incorporating knowledge directly from the FrameNet graph structure improves the performance of a neural network-based frame identification system. Specifically, we construct a bidirectional LSTM with a loss function that incorporates various graph- and corpus-based frame embeddings for learning and ultimately achieves strong performance gains with the graph-based embeddings over corpus-based embeddings alone.
%R 10.26615/978-954-452-056-4_109
%U https://aclanthology.org/R19-1109
%U https://doi.org/10.26615/978-954-452-056-4_109
%P 939-948
Markdown (Informal)
[Graph Embeddings for Frame Identification](https://aclanthology.org/R19-1109) (Popov & Sikos, RANLP 2019)
ACL
- Alexander Popov and Jennifer Sikos. 2019. Graph Embeddings for Frame Identification. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 939–948, Varna, Bulgaria. INCOMA Ltd..