@inproceedings{yang-etal-2019-embedding,
title = "Embedding Imputation with Grounded Language Information",
author = "Yang, Ziyi and
Zhu, Chenguang and
Sachidananda, Vin and
Darve, Eric",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1326/",
doi = "10.18653/v1/P19-1326",
pages = "3356--3361",
abstract = "Due to the ubiquitous use of embeddings as input representations for a wide range of natural language tasks, imputation of embeddings for rare and unseen words is a critical problem in language processing. Embedding imputation involves learning representations for rare or unseen words during the training of an embedding model, often in a post-hoc manner. In this paper, we propose an approach for embedding imputation which uses grounded information in the form of a knowledge graph. This is in contrast to existing approaches which typically make use of vector space properties or subword information. We propose an online method to construct a graph from grounded information and design an algorithm to map from the resulting graphical structure to the space of the pre-trained embeddings. Finally, we evaluate our approach on a range of rare and unseen word tasks across various domains and show that our model can learn better representations. For example, on the Card-660 task our method improves Pearson`s and Spearman`s correlation coefficients upon the state-of-the-art by 11{\%} and 17.8{\%} respectively using GloVe embeddings."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2019-embedding">
<titleInfo>
<title>Embedding Imputation with Grounded Language Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ziyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenguang</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vin</namePart>
<namePart type="family">Sachidananda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Darve</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Due to the ubiquitous use of embeddings as input representations for a wide range of natural language tasks, imputation of embeddings for rare and unseen words is a critical problem in language processing. Embedding imputation involves learning representations for rare or unseen words during the training of an embedding model, often in a post-hoc manner. In this paper, we propose an approach for embedding imputation which uses grounded information in the form of a knowledge graph. This is in contrast to existing approaches which typically make use of vector space properties or subword information. We propose an online method to construct a graph from grounded information and design an algorithm to map from the resulting graphical structure to the space of the pre-trained embeddings. Finally, we evaluate our approach on a range of rare and unseen word tasks across various domains and show that our model can learn better representations. For example, on the Card-660 task our method improves Pearson‘s and Spearman‘s correlation coefficients upon the state-of-the-art by 11% and 17.8% respectively using GloVe embeddings.</abstract>
<identifier type="citekey">yang-etal-2019-embedding</identifier>
<identifier type="doi">10.18653/v1/P19-1326</identifier>
<location>
<url>https://aclanthology.org/P19-1326/</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>3356</start>
<end>3361</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Embedding Imputation with Grounded Language Information
%A Yang, Ziyi
%A Zhu, Chenguang
%A Sachidananda, Vin
%A Darve, Eric
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F yang-etal-2019-embedding
%X Due to the ubiquitous use of embeddings as input representations for a wide range of natural language tasks, imputation of embeddings for rare and unseen words is a critical problem in language processing. Embedding imputation involves learning representations for rare or unseen words during the training of an embedding model, often in a post-hoc manner. In this paper, we propose an approach for embedding imputation which uses grounded information in the form of a knowledge graph. This is in contrast to existing approaches which typically make use of vector space properties or subword information. We propose an online method to construct a graph from grounded information and design an algorithm to map from the resulting graphical structure to the space of the pre-trained embeddings. Finally, we evaluate our approach on a range of rare and unseen word tasks across various domains and show that our model can learn better representations. For example, on the Card-660 task our method improves Pearson‘s and Spearman‘s correlation coefficients upon the state-of-the-art by 11% and 17.8% respectively using GloVe embeddings.
%R 10.18653/v1/P19-1326
%U https://aclanthology.org/P19-1326/
%U https://doi.org/10.18653/v1/P19-1326
%P 3356-3361
Markdown (Informal)
[Embedding Imputation with Grounded Language Information](https://aclanthology.org/P19-1326/) (Yang et al., ACL 2019)
ACL
- Ziyi Yang, Chenguang Zhu, Vin Sachidananda, and Eric Darve. 2019. Embedding Imputation with Grounded Language Information. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3356–3361, Florence, Italy. Association for Computational Linguistics.