@inproceedings{mahalunkar-kelleher-2019-multi,
title = "Multi-Element Long Distance Dependencies: Using {SP}k Languages to Explore the Characteristics of Long-Distance Dependencies",
author = "Mahalunkar, Abhijit and
Kelleher, John",
editor = "Eisner, Jason and
Gall{\'e}, Matthias and
Heinz, Jeffrey and
Quattoni, Ariadna and
Rabusseau, Guillaume",
booktitle = "Proceedings of the Workshop on Deep Learning and Formal Languages: Building Bridges",
month = aug,
year = "2019",
address = "Florence",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-3904",
doi = "10.18653/v1/W19-3904",
pages = "34--43",
abstract = "In order to successfully model Long Distance Dependencies (LDDs) it is necessary to under-stand the full-range of the characteristics of the LDDs exhibited in a target dataset. In this paper, we use Strictly k-Piecewise languages to generate datasets with various properties. We then compute the characteristics of the LDDs in these datasets using mutual information and analyze the impact of factors such as (i) k, (ii) length of LDDs, (iii) vocabulary size, (iv) forbidden strings, and (v) dataset size. This analysis reveal that the number of interacting elements in a dependency is an important characteristic of LDDs. This leads us to the challenge of modelling multi-element long-distance dependencies. Our results suggest that attention mechanisms in neural networks may aide in modeling datasets with multi-element long-distance dependencies. However, we conclude that there is a need to develop more efficient attention mechanisms to address this issue.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mahalunkar-kelleher-2019-multi">
<titleInfo>
<title>Multi-Element Long Distance Dependencies: Using SPk Languages to Explore the Characteristics of Long-Distance Dependencies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhijit</namePart>
<namePart type="family">Mahalunkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Kelleher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Deep Learning and Formal Languages: Building Bridges</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Eisner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Gallé</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeffrey</namePart>
<namePart type="family">Heinz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ariadna</namePart>
<namePart type="family">Quattoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Rabusseau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In order to successfully model Long Distance Dependencies (LDDs) it is necessary to under-stand the full-range of the characteristics of the LDDs exhibited in a target dataset. In this paper, we use Strictly k-Piecewise languages to generate datasets with various properties. We then compute the characteristics of the LDDs in these datasets using mutual information and analyze the impact of factors such as (i) k, (ii) length of LDDs, (iii) vocabulary size, (iv) forbidden strings, and (v) dataset size. This analysis reveal that the number of interacting elements in a dependency is an important characteristic of LDDs. This leads us to the challenge of modelling multi-element long-distance dependencies. Our results suggest that attention mechanisms in neural networks may aide in modeling datasets with multi-element long-distance dependencies. However, we conclude that there is a need to develop more efficient attention mechanisms to address this issue.</abstract>
<identifier type="citekey">mahalunkar-kelleher-2019-multi</identifier>
<identifier type="doi">10.18653/v1/W19-3904</identifier>
<location>
<url>https://aclanthology.org/W19-3904</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>34</start>
<end>43</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Element Long Distance Dependencies: Using SPk Languages to Explore the Characteristics of Long-Distance Dependencies
%A Mahalunkar, Abhijit
%A Kelleher, John
%Y Eisner, Jason
%Y Gallé, Matthias
%Y Heinz, Jeffrey
%Y Quattoni, Ariadna
%Y Rabusseau, Guillaume
%S Proceedings of the Workshop on Deep Learning and Formal Languages: Building Bridges
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence
%F mahalunkar-kelleher-2019-multi
%X In order to successfully model Long Distance Dependencies (LDDs) it is necessary to under-stand the full-range of the characteristics of the LDDs exhibited in a target dataset. In this paper, we use Strictly k-Piecewise languages to generate datasets with various properties. We then compute the characteristics of the LDDs in these datasets using mutual information and analyze the impact of factors such as (i) k, (ii) length of LDDs, (iii) vocabulary size, (iv) forbidden strings, and (v) dataset size. This analysis reveal that the number of interacting elements in a dependency is an important characteristic of LDDs. This leads us to the challenge of modelling multi-element long-distance dependencies. Our results suggest that attention mechanisms in neural networks may aide in modeling datasets with multi-element long-distance dependencies. However, we conclude that there is a need to develop more efficient attention mechanisms to address this issue.
%R 10.18653/v1/W19-3904
%U https://aclanthology.org/W19-3904
%U https://doi.org/10.18653/v1/W19-3904
%P 34-43
Markdown (Informal)
[Multi-Element Long Distance Dependencies: Using SPk Languages to Explore the Characteristics of Long-Distance Dependencies](https://aclanthology.org/W19-3904) (Mahalunkar & Kelleher, ACL 2019)
ACL