@inproceedings{shi-etal-2020-role,
title = "On the Role of Supervision in Unsupervised Constituency Parsing",
author = "Shi, Haoyue and
Livescu, Karen and
Gimpel, Kevin",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.614",
doi = "10.18653/v1/2020.emnlp-main.614",
pages = "7611--7621",
abstract = "We analyze several recent unsupervised constituency parsing models, which are tuned with respect to the parsing F1 score on the Wall Street Journal (WSJ) development set (1,700 sentences). We introduce strong baselines for them, by training an existing supervised parsing model (Kitaev and Klein, 2018) on the same labeled examples they access. When training on the 1,700 examples, or even when using only 50 examples for training and 5 for development, such a few-shot parsing approach can outperform all the unsupervised parsing methods by a significant margin. Few-shot parsing can be further improved by a simple data augmentation method and self-training. This suggests that, in order to arrive at fair conclusions, we should carefully consider the amount of labeled data used for model development. We propose two protocols for future work on unsupervised parsing: (i) use fully unsupervised criteria for hyperparameter tuning and model selection; (ii) use as few labeled examples as possible for model development, and compare to few-shot parsing trained on the same labeled examples.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shi-etal-2020-role">
<titleInfo>
<title>On the Role of Supervision in Unsupervised Constituency Parsing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoyue</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karen</namePart>
<namePart type="family">Livescu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Gimpel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We analyze several recent unsupervised constituency parsing models, which are tuned with respect to the parsing F1 score on the Wall Street Journal (WSJ) development set (1,700 sentences). We introduce strong baselines for them, by training an existing supervised parsing model (Kitaev and Klein, 2018) on the same labeled examples they access. When training on the 1,700 examples, or even when using only 50 examples for training and 5 for development, such a few-shot parsing approach can outperform all the unsupervised parsing methods by a significant margin. Few-shot parsing can be further improved by a simple data augmentation method and self-training. This suggests that, in order to arrive at fair conclusions, we should carefully consider the amount of labeled data used for model development. We propose two protocols for future work on unsupervised parsing: (i) use fully unsupervised criteria for hyperparameter tuning and model selection; (ii) use as few labeled examples as possible for model development, and compare to few-shot parsing trained on the same labeled examples.</abstract>
<identifier type="citekey">shi-etal-2020-role</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.614</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.614</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>7611</start>
<end>7621</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the Role of Supervision in Unsupervised Constituency Parsing
%A Shi, Haoyue
%A Livescu, Karen
%A Gimpel, Kevin
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F shi-etal-2020-role
%X We analyze several recent unsupervised constituency parsing models, which are tuned with respect to the parsing F1 score on the Wall Street Journal (WSJ) development set (1,700 sentences). We introduce strong baselines for them, by training an existing supervised parsing model (Kitaev and Klein, 2018) on the same labeled examples they access. When training on the 1,700 examples, or even when using only 50 examples for training and 5 for development, such a few-shot parsing approach can outperform all the unsupervised parsing methods by a significant margin. Few-shot parsing can be further improved by a simple data augmentation method and self-training. This suggests that, in order to arrive at fair conclusions, we should carefully consider the amount of labeled data used for model development. We propose two protocols for future work on unsupervised parsing: (i) use fully unsupervised criteria for hyperparameter tuning and model selection; (ii) use as few labeled examples as possible for model development, and compare to few-shot parsing trained on the same labeled examples.
%R 10.18653/v1/2020.emnlp-main.614
%U https://aclanthology.org/2020.emnlp-main.614
%U https://doi.org/10.18653/v1/2020.emnlp-main.614
%P 7611-7621
Markdown (Informal)
[On the Role of Supervision in Unsupervised Constituency Parsing](https://aclanthology.org/2020.emnlp-main.614) (Shi et al., EMNLP 2020)
ACL