Normal view MARC view ISBD view

Combining available datasets for building named entity recognition models of Croatian and Slovene / Nikola Ljubešić ; Marija Stupar ; Tereza Jurić ; Željko Agić.

By: Ljubešić, Nikola, informatičar.
Contributor(s): Stupar, Marija [aut] | Jurić, Tereza [aut] | Agić, Željko [aut].
Material type: ArticleArticlePublisher: 2013Description: 35-57 str.Other title: Combining Available Datasets for Building Named Entity Recognition Models of Croatian and Slovene [Naslov na engleskom:].Subject(s): 5.04 | 2.09 | named entity recognition; distributional similarity; Croatian language; Slovene language | named entity recognition; distributional similarity; Croatian language; Slovene languageOnline resources: Click here to access online In: Slovenščina 2.0: empirical, applied and interdisciplinary research 2 (2013) ; str. 35-57Summary: The paper presents efforts in developing freely available models for named entity recognition and classification in Croatian and Slovene text. Our experiments focus on the most informative set of linguistic features taking into account the availability of language tools and resources for the languages in question. Besides the classic linguistic features, distributional similarity features calculated from large unannotated monolingual corpora are exploited as well. We performed two batches on experiments, the first one on a self-built dataset on which the optimal set of features is sought, and a second batch with additional, much larger datasets obtained at a later point on which we verify the findings from the first batch. On the initial dataset using distributional information improves the results for 7-8 points in F1 while adding morphological information improves the results for additional 3-4 points in both languages. The second batch of experiments shows that morphosyntactic and distributional information lose importance as the dataset size significantly increases. The best performing models that use distributional information only, along with test sets for comparison with existing and future systems are made publicly available for both academic and non-academic use.
Tags from this library: No tags from this library for this title. Log in to add tags.
No physical items for this record

The paper presents efforts in developing freely available models for named entity recognition and classification in Croatian and Slovene text. Our experiments focus on the most informative set of linguistic features taking into account the availability of language tools and resources for the languages in question. Besides the classic linguistic features, distributional similarity features calculated from large unannotated monolingual corpora are exploited as well. We performed two batches on experiments, the first one on a self-built dataset on which the optimal set of features is sought, and a second batch with additional, much larger datasets obtained at a later point on which we verify the findings from the first batch. On the initial dataset using distributional information improves the results for 7-8 points in F1 while adding morphological information improves the results for additional 3-4 points in both languages. The second batch of experiments shows that morphosyntactic and distributional information lose importance as the dataset size significantly increases. The best performing models that use distributional information only, along with test sets for comparison with existing and future systems are made publicly available for both academic and non-academic use.

Projekt MZOS projekt

ENG

There are no comments for this item.

Log in to your account to post a comment.

Powered by Koha

//