@inproceedings{pajkossy-zseder-2016-hunvec,
title = "The hunvec framework for {NN}-{CRF}-based sequential tagging",
author = "Pajkossy, Katalin and
Zs{\'e}der, Attila",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1678",
pages = "4278--4281",
abstract = "In this work we present the open source hunvec framework for sequential tagging, built upon Theano and Pylearn2. The underlying statistical model, which connects linear CRF-s with neural networks, was used by Collobert and co-workers, and several other researchers. For demonstrating the flexibility of our tool, we describe a set of experiments on part-of-speech and named-entity-recognition tasks, using English and Hungarian datasets, where we modify both model and training parameters, and illustrate the usage of custom features. Model parameters we experiment with affect the vectorial word representations used by the model; we apply different word vector initializations, defined by Word2vec and GloVe embeddings and enrich the representation of words by vectors assigned trigram features. We extend training methods by using their regularized (l2 and dropout) version. When testing our framework on a Hungarian named entity corpus, we find that its performance reaches the best published results on this dataset, with no need for language-specific feature engineering. Our code is available at \url{http://github.com/zseder/hunvec}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pajkossy-zseder-2016-hunvec">
<titleInfo>
<title>The hunvec framework for NN-CRF-based sequential tagging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katalin</namePart>
<namePart type="family">Pajkossy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Attila</namePart>
<namePart type="family">Zséder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this work we present the open source hunvec framework for sequential tagging, built upon Theano and Pylearn2. The underlying statistical model, which connects linear CRF-s with neural networks, was used by Collobert and co-workers, and several other researchers. For demonstrating the flexibility of our tool, we describe a set of experiments on part-of-speech and named-entity-recognition tasks, using English and Hungarian datasets, where we modify both model and training parameters, and illustrate the usage of custom features. Model parameters we experiment with affect the vectorial word representations used by the model; we apply different word vector initializations, defined by Word2vec and GloVe embeddings and enrich the representation of words by vectors assigned trigram features. We extend training methods by using their regularized (l2 and dropout) version. When testing our framework on a Hungarian named entity corpus, we find that its performance reaches the best published results on this dataset, with no need for language-specific feature engineering. Our code is available at http://github.com/zseder/hunvec</abstract>
<identifier type="citekey">pajkossy-zseder-2016-hunvec</identifier>
<location>
<url>https://aclanthology.org/L16-1678</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4278</start>
<end>4281</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The hunvec framework for NN-CRF-based sequential tagging
%A Pajkossy, Katalin
%A Zséder, Attila
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F pajkossy-zseder-2016-hunvec
%X In this work we present the open source hunvec framework for sequential tagging, built upon Theano and Pylearn2. The underlying statistical model, which connects linear CRF-s with neural networks, was used by Collobert and co-workers, and several other researchers. For demonstrating the flexibility of our tool, we describe a set of experiments on part-of-speech and named-entity-recognition tasks, using English and Hungarian datasets, where we modify both model and training parameters, and illustrate the usage of custom features. Model parameters we experiment with affect the vectorial word representations used by the model; we apply different word vector initializations, defined by Word2vec and GloVe embeddings and enrich the representation of words by vectors assigned trigram features. We extend training methods by using their regularized (l2 and dropout) version. When testing our framework on a Hungarian named entity corpus, we find that its performance reaches the best published results on this dataset, with no need for language-specific feature engineering. Our code is available at http://github.com/zseder/hunvec
%U https://aclanthology.org/L16-1678
%P 4278-4281
Markdown (Informal)
[The hunvec framework for NN-CRF-based sequential tagging](https://aclanthology.org/L16-1678) (Pajkossy & Zséder, LREC 2016)
ACL
- Katalin Pajkossy and Attila Zséder. 2016. The hunvec framework for NN-CRF-based sequential tagging. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 4278–4281, Portorož, Slovenia. European Language Resources Association (ELRA).