@inproceedings{pate-johnson-2016-grammar,
title = "Grammar induction from (lots of) words alone",
author = "Pate, John K and
Johnson, Mark",
editor = "Matsumoto, Yuji and
Prasad, Rashmi",
booktitle = "Proceedings of {COLING} 2016, the 26th International Conference on Computational Linguistics: Technical Papers",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/C16-1003",
pages = "23--32",
abstract = "Grammar induction is the task of learning syntactic structure in a setting where that structure is hidden. Grammar induction from words alone is interesting because it is similiar to the problem that a child learning a language faces. Previous work has typically assumed richer but cognitively implausible input, such as POS tag annotated data, which makes that work less relevant to human language acquisition. We show that grammar induction from words alone is in fact feasible when the model is provided with sufficient training data, and present two new streaming or mini-batch algorithms for PCFG inference that can learn from millions of words of training data. We compare the performance of these algorithms to a batch algorithm that learns from less data. The minibatch algorithms outperform the batch algorithm, showing that cheap inference with more data is better than intensive inference with less data. Additionally, we show that the harmonic initialiser, which previous work identified as essential when learning from small POS-tag annotated corpora (Klein and Manning, 2004), is not superior to a uniform initialisation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pate-johnson-2016-grammar">
<titleInfo>
<title>Grammar induction from (lots of) words alone</title>
</titleInfo>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Pate</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Johnson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuji</namePart>
<namePart type="family">Matsumoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grammar induction is the task of learning syntactic structure in a setting where that structure is hidden. Grammar induction from words alone is interesting because it is similiar to the problem that a child learning a language faces. Previous work has typically assumed richer but cognitively implausible input, such as POS tag annotated data, which makes that work less relevant to human language acquisition. We show that grammar induction from words alone is in fact feasible when the model is provided with sufficient training data, and present two new streaming or mini-batch algorithms for PCFG inference that can learn from millions of words of training data. We compare the performance of these algorithms to a batch algorithm that learns from less data. The minibatch algorithms outperform the batch algorithm, showing that cheap inference with more data is better than intensive inference with less data. Additionally, we show that the harmonic initialiser, which previous work identified as essential when learning from small POS-tag annotated corpora (Klein and Manning, 2004), is not superior to a uniform initialisation.</abstract>
<identifier type="citekey">pate-johnson-2016-grammar</identifier>
<location>
<url>https://aclanthology.org/C16-1003</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>23</start>
<end>32</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grammar induction from (lots of) words alone
%A Pate, John K.
%A Johnson, Mark
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F pate-johnson-2016-grammar
%X Grammar induction is the task of learning syntactic structure in a setting where that structure is hidden. Grammar induction from words alone is interesting because it is similiar to the problem that a child learning a language faces. Previous work has typically assumed richer but cognitively implausible input, such as POS tag annotated data, which makes that work less relevant to human language acquisition. We show that grammar induction from words alone is in fact feasible when the model is provided with sufficient training data, and present two new streaming or mini-batch algorithms for PCFG inference that can learn from millions of words of training data. We compare the performance of these algorithms to a batch algorithm that learns from less data. The minibatch algorithms outperform the batch algorithm, showing that cheap inference with more data is better than intensive inference with less data. Additionally, we show that the harmonic initialiser, which previous work identified as essential when learning from small POS-tag annotated corpora (Klein and Manning, 2004), is not superior to a uniform initialisation.
%U https://aclanthology.org/C16-1003
%P 23-32
Markdown (Informal)
[Grammar induction from (lots of) words alone](https://aclanthology.org/C16-1003) (Pate & Johnson, COLING 2016)
ACL
- John K Pate and Mark Johnson. 2016. Grammar induction from (lots of) words alone. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 23–32, Osaka, Japan. The COLING 2016 Organizing Committee.