@inproceedings{vastl-etal-2020-predicting,
title = "Predicting Typological Features in {WALS} using Language Embeddings and Conditional Probabilities: {{\'U}FAL} Submission to the {SIGTYP} 2020 Shared Task",
author = "Vastl, Martin and
Zeman, Daniel and
Rosa, Rudolf",
editor = "Vylomova, Ekaterina and
Ponti, Edoardo M. and
Grossman, Eitan and
McCarthy, Arya D. and
Berzak, Yevgeni and
Dubossarsky, Haim and
Vuli{\'c}, Ivan and
Reichart, Roi and
Korhonen, Anna and
Cotterell, Ryan",
booktitle = "Proceedings of the Second Workshop on Computational Research in Linguistic Typology",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.sigtyp-1.4/",
doi = "10.18653/v1/2020.sigtyp-1.4",
pages = "29--35",
abstract = "We present our submission to the SIGTYP 2020 Shared Task on the prediction of typological features. We submit a constrained system, predicting typological features only based on the WALS database. We investigate two approaches. The simpler of the two is a system based on estimating correlation of feature values within languages by computing conditional probabilities and mutual information. The second approach is to train a neural predictor operating on precomputed language embeddings based on WALS features. Our submitted system combines the two approaches based on their self-estimated confidence scores. We reach the accuracy of 70.7{\%} on the test data and rank first in the shared task."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vastl-etal-2020-predicting">
<titleInfo>
<title>Predicting Typological Features in WALS using Language Embeddings and Conditional Probabilities: ÚFAL Submission to the SIGTYP 2020 Shared Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Vastl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Zeman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rudolf</namePart>
<namePart type="family">Rosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Computational Research in Linguistic Typology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Ponti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eitan</namePart>
<namePart type="family">Grossman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arya</namePart>
<namePart type="given">D</namePart>
<namePart type="family">McCarthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yevgeni</namePart>
<namePart type="family">Berzak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haim</namePart>
<namePart type="family">Dubossarsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present our submission to the SIGTYP 2020 Shared Task on the prediction of typological features. We submit a constrained system, predicting typological features only based on the WALS database. We investigate two approaches. The simpler of the two is a system based on estimating correlation of feature values within languages by computing conditional probabilities and mutual information. The second approach is to train a neural predictor operating on precomputed language embeddings based on WALS features. Our submitted system combines the two approaches based on their self-estimated confidence scores. We reach the accuracy of 70.7% on the test data and rank first in the shared task.</abstract>
<identifier type="citekey">vastl-etal-2020-predicting</identifier>
<identifier type="doi">10.18653/v1/2020.sigtyp-1.4</identifier>
<location>
<url>https://aclanthology.org/2020.sigtyp-1.4/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>29</start>
<end>35</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predicting Typological Features in WALS using Language Embeddings and Conditional Probabilities: ÚFAL Submission to the SIGTYP 2020 Shared Task
%A Vastl, Martin
%A Zeman, Daniel
%A Rosa, Rudolf
%Y Vylomova, Ekaterina
%Y Ponti, Edoardo M.
%Y Grossman, Eitan
%Y McCarthy, Arya D.
%Y Berzak, Yevgeni
%Y Dubossarsky, Haim
%Y Vulić, Ivan
%Y Reichart, Roi
%Y Korhonen, Anna
%Y Cotterell, Ryan
%S Proceedings of the Second Workshop on Computational Research in Linguistic Typology
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F vastl-etal-2020-predicting
%X We present our submission to the SIGTYP 2020 Shared Task on the prediction of typological features. We submit a constrained system, predicting typological features only based on the WALS database. We investigate two approaches. The simpler of the two is a system based on estimating correlation of feature values within languages by computing conditional probabilities and mutual information. The second approach is to train a neural predictor operating on precomputed language embeddings based on WALS features. Our submitted system combines the two approaches based on their self-estimated confidence scores. We reach the accuracy of 70.7% on the test data and rank first in the shared task.
%R 10.18653/v1/2020.sigtyp-1.4
%U https://aclanthology.org/2020.sigtyp-1.4/
%U https://doi.org/10.18653/v1/2020.sigtyp-1.4
%P 29-35
Markdown (Informal)
[Predicting Typological Features in WALS using Language Embeddings and Conditional Probabilities: ÚFAL Submission to the SIGTYP 2020 Shared Task](https://aclanthology.org/2020.sigtyp-1.4/) (Vastl et al., SIGTYP 2020)
ACL