A flexemic tagset for Polish

Przepiórkowski, Adam; Woliński, Marcin

doi:10.3115/1613200.1613205

Cited by 30 publications

(14 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many Polish wordforms historically derived as gerunds or participles, such as "oświece-nie", possess two meanings: one closer to a noun/adjective ("oświecenie" = enlightenment) and one closer to a verb ("oświecenie" = illumination). In the adopted annotation scheme [6], such a distinction exists for any Polish gerund or participle even if one can hardly figure out the noun-like meaning. Both human anotators and the tagger get confused, which is reflected in the high error rate on the attributes of aspect and negation (definite for verbal and indefinite for non-verbal forms).…”

Section: Preliminary Resultsmentioning

confidence: 99%

“…Contextually valid tags T 1:n = (T 1 , T 2 , ..., T n ) can be determined by humans for sufficiently long W 1;n = (W 1 , W 2 , ..., W n ) (almost) uniquely but the dependence between these two strings is very complex. The automatic computation of T 1 , T 2 , ..., T n can be made efficient if some error rate is allowed (even humans disagree for about 3% of tokens in the annotation scheme proposed in [6]). One of heuristic approaches which appears unexpectedly fruitful is trigram model and its modifications.…”

Section: The Modelmentioning

confidence: 99%

See 1 more Smart Citation

Trigram morphosyntactic tagger for Polish

Dębowski

2004

Intelligent Information Processing and Web Mining

View full text Add to dashboard Cite

Abstract.We introduce an implementation of a plain trigram part-of-speech tagger which appears to work well on Polish texts. At this moment the tagger achieves 9.4% error rate, which makes it signficantly better than our previous stochastic disambiguator. Since the trigram model for Polish behaves similarly to Czech, we hope to reach Czech state-of-art error rate when the quality of the training data improves.

show abstract

Section: Preliminary Resultsmentioning

confidence: 99%

Section: The Modelmentioning

confidence: 99%

Trigram morphosyntactic tagger for Polish

Dębowski

2004

Intelligent Information Processing and Web Mining

View full text Add to dashboard Cite

show abstract

“…The notations for cases are as in the IPI PAN Corpus tagset: nom(inative), gen(itive), dat(ive), acc(usative), inst(rumental), loc(ative), and voc(ative), cf. Przepiórkowski and Woliński (2003) or http://korpus.pl/. For simplicity, it is assumed that no argument type can be repeated in a single valence frame.…”

Section: The Formalism Of Co-occurrence Matricesmentioning

confidence: 99%

Valence extraction using EM selection and co-occurrence matrices

Dębowski

2009

Lang Resources & Evaluation

View full text Add to dashboard Cite

This paper discusses two new procedures for extracting verb valences from raw texts, with an application to the Polish language. The first novel technique, the EM selection algorithm, performs unsupervised disambiguation of valence frame forests, obtained by applying a non-probabilistic deep grammar parser and some post-processing to the text. The second new idea concerns filtering of incorrect frames detected in the parsed text and is motivated by an observation that verbs which take similar arguments tend to have similar frames. This phenomenon is described in terms of newly introduced co-occurrence matrices. Using co-occurrence matrices, we split filtering into two steps. The list of valid arguments is first determined for each verb, whereas the pattern according to which the arguments are combined into frames is computed in the following stage. Our best extracted dictionary reaches an $F$-score of 45%, compared to an $F$-score of 39% for the standard frame-based BHT filtering.Comment: 24 pages, 3 table

show abstract

“…The morphosyntactic specifications are based on the flexemic tagset for Polish (Przepiórkowski and Woliński 2003), used e.g. for the annotation of the IPI PAN corpus of Polish (Przepiórkowski 2006), and this corpus was also taken as the source for constructing the MULTEXT-East lexicon.…”

Section: Multext-east By Languagementioning

confidence: 99%

MULTEXT-East: morphosyntactic resources for Central and Eastern European languages

Erjavec

2011

Lang Resources & Evaluation

View full text Add to dashboard Cite

The paper presents the MULTEXT-East language resources, a multilingual dataset for language engineering research, focused on the morphosyntactic level of linguistic description. The MULTEXT-East dataset includes the morphosyntactic specifications, morphosyntactic lexica, and a parallel corpus, the novel ''1984'' by George Orwell, which is sentence aligned and contains hand-validated morphosyntactic descriptions and lemmas. The resources are uniformly encoded in XML, using the Text Encoding Initiative Guidelines, TEI P5, and cover 16 languages, mainly from Central and Eastern Europe: Bulgarian, Croatian, Czech, English, Estonian, Hungarian, Macedonian, Persian, Polish, Resian, Romanian, Russian, Serbian, Slovak, Slovene, and Ukrainian. This dataset, unique in terms of languages covered and the wealth of encoding, is extensively documented, and freely available for research purposes. The paper overviews the MULTEXT-East resources by type and language and gives some conclusions and directions for further work.

show abstract

A flexemic tagset for Polish

Cited by 30 publications

References 1 publication

Trigram morphosyntactic tagger for Polish

Trigram morphosyntactic tagger for Polish

Valence extraction using EM selection and co-occurrence matrices

MULTEXT-East: morphosyntactic resources for Central and Eastern European languages

Contact Info

Product

Resources

About