The Prague Dependency Treebank

Böhmová, Alena; Hajič, Jan; Hajičová, Eva; Hladká, Barbora

doi:10.1007/978-94-010-0201-1_7

Cited by 132 publications

(41 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Additionally, we also report preliminary results on the Prague style conversion of HamleDT, which loosely follows the style of the Prague Dependency Treebank of Böhmová et al (2003) Table 2 contains the results of our methods both on the test languages and the development languages. 7 We tuned the choice of the similarity measure, POS ngram length, and the way of turning KL cpos 3 into KL −4 cpos 3 .…”

Section: Other Datasetsmentioning

confidence: 99%

KLcpos3 - a Language Similarity Measure for Delexicalized Parser Transfer

Rosa¹,

Žabokrtský²

2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

View full text Add to dashboard Cite

We present KL cpos 3 , a language similarity measure based on Kullback-Leibler divergence of coarse part-of-speech tag trigram distributions in tagged corpora. It has been designed for multilingual delexicalized parsing, both for source treebank selection in single-source parser transfer, and for source treebank weighting in multi-source transfer. In the selection task, KL cpos 3 identifies the best source treebank in 8 out of 18 cases. In the weighting task, it brings +4.5% UAS absolute, compared to unweighted parse tree combination.

show abstract

Section: Other Datasetsmentioning

confidence: 99%

KLcpos3 - a Language Similarity Measure for Delexicalized Parser Transfer

Rosa¹,

Žabokrtský²

2015

Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Confere

View full text Add to dashboard Cite

show abstract

“…We augment the original five datasets with four new sets: Dutch verbs from the CELEX lexical database (Baayen et al, 1995), French verbs from Verbiste, an online French conjugation dictionary 2 , and Czech nouns and verbs from the Prague Dependency Treebank (Böhmová et al, 2003 these sets, the training data is restricted to 80% of the inflection tables listed in Table 1, with 10% each for development and testing. Each lemma inflects to a finite number of forms that vary by part-of-speech and language (Table 1); German nouns inflect for number and case (Table 2), while French, Spanish, German, and Dutch verbs inflect for number, person, mood, and tense.…”

Section: Inflection Datamentioning

confidence: 99%

Inflection Generation as Discriminative String Transduction

Nicolai

Cherry

Kondrak

2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

We approach the task of morphological inflection generation as discriminative string transduction. Our supervised system learns to generate word-forms from lemmas accompanied by morphological tags, and refines them by referring to the other forms within a paradigm.Results of experiments on six diverse languages with varying amounts of training data demonstrate that our approach improves the state of the art in terms of predicting inflected word-forms.

show abstract

“…Obviously, in MT, when one has parsers for both the source and target language. Systems for "deep" analysis and generation might wish to learn mappings between deep and surface trees (Böhmová et al, 2001) or between syntax and semantics (Shieber and Schabes, 1990). Systems for summarization or paraphrase could also be trained on tree pairs (Knight and Marcu, 2000).…”

Section: Introduction: Tree-to-tree Mappingsmentioning

confidence: 99%