@inproceedings{ebner-etal-2019-bag,
title = "Bag-of-Words Transfer: Non-Contextual Techniques for Multi-Task Learning",
author = "Ebner, Seth and
Wang, Felicity and
Van Durme, Benjamin",
editor = "Cherry, Colin and
Durrett, Greg and
Foster, George and
Haffari, Reza and
Khadivi, Shahram and
Peng, Nanyun and
Ren, Xiang and
Swayamdipta, Swabha",
booktitle = "Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6105",
doi = "10.18653/v1/D19-6105",
pages = "40--46",
abstract = "Many architectures for multi-task learning (MTL) have been proposed to take advantage of transfer among tasks, often involving complex models and training procedures. In this paper, we ask if the sentence-level representations learned in previous approaches provide significant benefit beyond that provided by simply improving word-based representations. To investigate this question, we consider three techniques that ignore sequence information: a syntactically-oblivious pooling encoder, pre-trained non-contextual word embeddings, and unigram generative regularization. Compared to a state-of-the-art MTL approach to textual inference, the simple techniques we use yield similar performance on a universe of task combinations while reducing training time and model size.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ebner-etal-2019-bag">
<titleInfo>
<title>Bag-of-Words Transfer: Non-Contextual Techniques for Multi-Task Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Seth</namePart>
<namePart type="family">Ebner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Felicity</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Van Durme</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Colin</namePart>
<namePart type="family">Cherry</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="family">Foster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Reza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nanyun</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many architectures for multi-task learning (MTL) have been proposed to take advantage of transfer among tasks, often involving complex models and training procedures. In this paper, we ask if the sentence-level representations learned in previous approaches provide significant benefit beyond that provided by simply improving word-based representations. To investigate this question, we consider three techniques that ignore sequence information: a syntactically-oblivious pooling encoder, pre-trained non-contextual word embeddings, and unigram generative regularization. Compared to a state-of-the-art MTL approach to textual inference, the simple techniques we use yield similar performance on a universe of task combinations while reducing training time and model size.</abstract>
<identifier type="citekey">ebner-etal-2019-bag</identifier>
<identifier type="doi">10.18653/v1/D19-6105</identifier>
<location>
<url>https://aclanthology.org/D19-6105</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>40</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bag-of-Words Transfer: Non-Contextual Techniques for Multi-Task Learning
%A Ebner, Seth
%A Wang, Felicity
%A Van Durme, Benjamin
%Y Cherry, Colin
%Y Durrett, Greg
%Y Foster, George
%Y Haffari, Reza
%Y Khadivi, Shahram
%Y Peng, Nanyun
%Y Ren, Xiang
%Y Swayamdipta, Swabha
%S Proceedings of the 2nd Workshop on Deep Learning Approaches for Low-Resource NLP (DeepLo 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F ebner-etal-2019-bag
%X Many architectures for multi-task learning (MTL) have been proposed to take advantage of transfer among tasks, often involving complex models and training procedures. In this paper, we ask if the sentence-level representations learned in previous approaches provide significant benefit beyond that provided by simply improving word-based representations. To investigate this question, we consider three techniques that ignore sequence information: a syntactically-oblivious pooling encoder, pre-trained non-contextual word embeddings, and unigram generative regularization. Compared to a state-of-the-art MTL approach to textual inference, the simple techniques we use yield similar performance on a universe of task combinations while reducing training time and model size.
%R 10.18653/v1/D19-6105
%U https://aclanthology.org/D19-6105
%U https://doi.org/10.18653/v1/D19-6105
%P 40-46
Markdown (Informal)
[Bag-of-Words Transfer: Non-Contextual Techniques for Multi-Task Learning](https://aclanthology.org/D19-6105) (Ebner et al., 2019)
ACL