Back to first pageBack to first page Centre for Artificial Intelligence of UNL
Browse our site
You are here:

Publication details

Go back
Publication details
Main information
Neuro-Symbolic Word Tagging
December 2007
mbrh07
Part-of-speech tagging (POS) assigns grammatical tags (like noun, verb, etc.) to a word depending on its definition and its context. This is a first step before parsing may be applied. POS tagging and more generically word tagging, plays an important role in computational linguistics and in many information retrieval and text mining tasks. Neither pure rule based, nor machine learning approaches give satisfying results: rule based systems can not adapt well to existing samples; machine learning systems ignore available background knowledge. A combination of both is needed. In particular, we show some cases where the initialization of a neural network based tagger with background knowledge obtains better results. In this preliminary work we study some implications of embedding background knowledge for POS and word tagging problems. Preliminary results show that the combined system outperforms a purely machine learning system when only limited samples are available.
In proceedings
Nuno Marques, Sebastian Bader, Vitor Rocio, Steffen Hölldobler
José Neves, Manuel Filipe Santos, José Machado
New Trends in Artificial Intelligence
-
Associação Portuguesa para a Inteligência Artificial (APPIA)
Guimarães. Portugal
-
-
ISBN-13 978-989-9561
-
-
http://ssdi.di.fct.unl.pt/~nmm/MyPapers/MBRH07.pdf
Export formats
Nuno Marques and Sebastian Bader and Vitor Rocio and Steffen Hölldobler, Neuro-Symbolic Word Tagging, in: José Neves and Manuel Filipe Santos and José Machado (eds), New Trends in Artificial Intelligence, Associação Portuguesa para a Inteligência Artificial (APPIA), Guimarães. Portugal, ISBN ISBN-13 978-989-9561, (http://ssdi.di.fct.unl.pt/~nmm/MyPapers/MBRH07.pdf), December 2007.
<a href="/people/members/view.php?code=9ac1f1682cb91b20d9fbfb8e659b0819" class="author">Nuno Marques</a>, Sebastian Bader, Vitor Rocio and Steffen Hölldobler, <b>Neuro-Symbolic Word Tagging</b>, in: José Neves, Manuel Filipe Santos and José Machado (eds), <u>New Trends in Artificial Intelligence</u>, <a href="http://www.appia.pt/" title="Link to external entity..." target="_blank" class="publisher">Associação Portuguesa para a Inteligência Artificial (APPIA)</a>, Guimarães. Portugal, ISBN ISBN-13 978-989-9561, (<a href="http://ssdi.di.fct.unl.pt/~nmm/MyPapers/MBRH07.pdf" target="_blank">url</a>), December 2007.
@inproceedings {mbrh07, author = {Nuno Marques and Sebastian Bader and Vitor Rocio and Steffen H\"olldobler}, editor = {Jos{\'e} Neves and Manuel Filipe Santos and Jos{\'e} Machado}, title = {Neuro-Symbolic Word Tagging}, booktitle = {New Trends in Artificial Intelligence}, publisher = {Associa\c{c}{\~a}o Portuguesa para a Intelig{\^e}ncia Artificial (APPIA)}, address = {Guimar{\~a}es. Portugal}, isbn = {ISBN-13 978-989-9561}, url = {http://ssdi.di.fct.unl.pt/~nmm/MyPapers/MBRH07.pdf}, abstract = {Part-of-speech tagging (POS) assigns grammatical tags (like noun, verb, etc.) to a word depending on its definition and its context. This is a first step before parsing may be applied. POS tagging and more generically word tagging, plays an important role in computational linguistics and in many information retrieval and text mining tasks. Neither pure rule based, nor machine learning approaches give satisfying results: rule based systems can not adapt well to existing samples; machine learning systems ignore available background knowledge. A combination of both is needed. In particular, we show some cases where the initialization of a neural network based tagger with background knowledge obtains better results. In this preliminary work we study some implications of embedding background knowledge for POS and word tagging problems. Preliminary results show that the combined system outperforms a purely machine learning system when only limited samples are available.}, month = {December}, year = {2007}, }
Publication's urls
/publications/view.php?code=f8b5165920cc6fe6f32f66c13ec57f34
/publications/view.php?code=mbrh07
Go back
Centre for Artificial Intelligence of UNL
Departamento de Informática, FCT/UNL
Quinta da Torre 2829-516 CAPARICA - Portugal
Tel. (+351) 21 294 8536 FAX (+351) 21 294 8541

Fundacao_FCT