Thorsten Brants. 2000. TnT - A Statistical Part-ofSpeech Tagger. In Proceedings of ANLP-NAACL, pages 224--231. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
An Unsupervised Semantic Tagger Applied to German - Buitelaar, Alexandersson.. (2001) (Correct)
.... first annotates all words with part ofspeech (to find all content words: noun, verb, adjective) and morphological information (to look up the lemma in GermaNet) For the experiments reported on in this paper we have used the TnT tagger for German, trained with the Stuttgart Tbinger POS tag set (Brants 2000). For morphological analysis, an implementation of the Mmorph algorithm is used, which has been developed within the context of the Multext project (Petitpierre and Russell 1995) As in Resniks approach, our system treats all synsets and their hypernyms as semantic classes to which a word may ....
Brants, T. 2000. TnT - A Statistical Part-ofSpeech Tagger. In: Proceedings of the 6 th Applied Natural Language Processing Conference, Seattle, WA.
Ranking and Selecting Synsets by Domain Relevance - Buitelaar, Sacaleanu (2001) (Correct)
....ranking of synsets according to domain relevance. 2.1 Preprocessing The system first annotates all words with part ofspeech and morphological information. This allows us to extract noun stems that are used as terms in further processing (to look up the lemma in GermaNet) We used the TnT package (Brants, 2000) for part of speech tagging, trained on a general corpus in order to make it unbiased to any of the domain specific corpora used in the experiments. For morphological analysis we used the MMORPH package (Petitpierre and Russel, 1995) An important aspect of this, specifically for a highly ....
Brants, T. 2000. TnT - A Statistical Part-ofSpeech Tagger. In: Proceedings of 6 th ANLP Conference, Seattle, WA.
Enriching the Knowledge Sources Used in a Maximum Entropy.. - Toutanova, Manning (2000) (3 citations) (Correct)
....on the Penn Treebank is 96.86 overall, and 86.91 on previously unseen words. Introduction 1 There are now numerous systems for automatic assignment of parts of speech ( tagging ) employing many different machine learning methods. Among recent top performing methods are Hidden Markov Models (Brants 2000), maximum entropy approaches (Ratnaparkhi 1996) and transformation based learning (Brill 1994) An overview of these and other approaches can be found in Manning and Schtze (1999, ch. 10) However, all these methods use largely the same information sources for tagging, and often almost the same ....
Brants, Thorsten. 2000. TnT -- A Statistical Part-ofSpeech Tagger. In Proceedings of the Sixth Applied Natural Language Processing Conference (ANLP 2000), Seattle, WA, pp. 224--231.
A Linguistically Interpreted Corpus of German Newspaper.. - Skut, Brants, Krenn.. (1993) (9 citations) Self-citation (Thorsten) (Correct)
....of semiautomatic annotation. Currently, these separate programs are a part of speech tagger, a tagger for grammatical functions and phrasal categories and an NP PP chunker. The part of speech tagger is a trigram part ofspeech tagger that is trainable for a wide variety of languages and tagsets (Brants, 1996). We trained it on all previously annotated material in our corpus, using the Stuttgart Tbingen tagset, and it currently achieves an accuracy of 96 on new, unseen text. In our project, annotation is an interactive task. After the annotator has specified a partial structure, the tool ....
....are also supported by psycholinguistic experiments. For investigations on statistics based collocation extraction, various portions of the Frankfurter Rundschau Corpus have been automatically annotated with parts of speech and phrase chunks like NP, PP, AP. The part of speech tagger (Brants, 1996) and the chunker (Skut and Brants, 1998b) have been trained on the annotated and handcorrected corpus. Although error rates of 10 to 15 occur at the stage of chunking, collocation extraction benefits from structurally annotated corpora because of the accessibility of syntactic information (1) ....
Brants, Thorsten. 1996. Tnt -- a statistical part-ofspeech tagger. Technical report, Universitat des Saarlandes, Computational Linguistics.
A Resource-light Approach to Russian Morphology: Tagging.. - Hana, Feldman, Brew (2004) (2 citations) (Correct)
No context found.
Thorsten Brants. 2000. TnT - A Statistical Part-ofSpeech Tagger. In Proceedings of ANLP-NAACL, pages 224--231.
Tagging Portuguese with a Spanish Tagger Using Cognates - Hana, Feldman, Brew, Amaral (2006) (Correct)
No context found.
Brants, T. (2000). TnT -- A Statistical Partof -Speech Tagger. In Proceedings of ANLPNAACL, pp. 224--231.
From Detecting Errors to Automatically Correcting Them - Markus Dickinson Department (2006) (Correct)
No context found.
Thorsten Brants. 2000. TnT -- a statistical part-ofspeech tagger. In Proceedings of ANLP-2000, pages 224--231, Seattle, WA.
A Core-Tools Statistical NLP Course - Klein (2005) (Correct)
No context found.
Thorsten Brants. 2000. TnT -- a statistical part-ofspeech tagger. In ANLP 6, pages 224--231.
Synther -- A New M-Gram Pos Tagger - David Undermann And (2003) (Correct)
No context found.
T. Brants. 2000. TnT -- A Statistical Part-ofSpeech Tagger. In Proc. of the ANLP'00.
Statistical Corpus-Based Word Sense Disambiguation: Pseudowords.. - Gaustad (2001) (2 citations) (Correct)
No context found.
Thorsten Brants. 2000. TnT---a statistical part-ofspeech tagger. In Proceedings of the 6th Applied Natural Language Processing Conference ANLP2000, Seattle, WA, April 29-May 3.
Using Induced Rules as Complex Features in Memory-Based.. - van den Bosch (2000) (Correct)
No context found.
Thorsten Brants. 2000. TnT -- a statistical part-ofspeech tagger. In Proceedings of the Sixth Applied Natural Language Processing (ANLP-2000), Seattle, WA.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC