A. Voutilainen. A syntax-based part-of-speech analyzer. In Proceedings of the Seventh Conference of the European Chapter of the Association of Computational Linguistics, Dublin, Ireland, 1995.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....parser should confront. Ambiguity has been already tackled at a remarkable level of success in low level parsing problems, as for instance Part Of Speech (POS) tagging, where several systems report results of a 95 correct assignment of the appropriate tag in context for unrestricted text [GLS87, Kup92, Elw93, Vou95]. However, in higher levels of analysis there is plenty of room for development, and the substantial advances achieved in POS tagging permit to expect that robust parsing techniques may be improved in the short medium term. The achievement of 10 Penn Treebank Corpus is being collected by the ....

....get more perspicuous. Therefore the algorithm may need several passes in order to apply rules that maybe could not be applied before. This approach has mainly been developed around the Constraint Based framework. The grammars constructed to date may vary from 75 rules as in [CT95] to 1. 200 as in [Vou95]. There are also some hybrid systems that combine the advantages of probabilistic and rule based approaches. In some works [MT94, LGB94, TV94, TJ94] linguistically motivated rule based patterns are combined with other rules (or collocation matrices) automatically derived from corpora. Brill s ....

[Article contains additional citation context not shown here]

A. Voutilainen. A syntax-based part-of-speech analyzer. In Proc. 7th EACL (1995) [Pro95a].

....POS disambiguation. Recently, rule based approaches are re studied to cope with the limitations of statistical approaches by learning the tagging rules automatically from the corpus [Brill, 1992, Brill, 1994] Some systems even perform the POS tagging as part of syntactic analysis process [Voutilainen, 1995]. However, the rule based approaches alone are in general not robust to handle the unknown words, and is not flexible to adjust to the new tag sets and languages. Also the performance is usually no better than the statistical counterparts [Brill, 1992] To gain flexibility and robustness and also ....

A. Voutilainen. A syntax-based part-of-speech analyzer. In Proceedings of the seventh conference of the European chapter of the association for computational linguitics (EACL-95), 1995.

....parsers may be classified into four groups: phrasal parsers (or spotters) co occurrence parsers, fragmental parsers and constraintbased parsers. See [Rib95, ACFG95] for detailed information about recent tendencies in the robust parsing of unrestricted text. 2 The Constraint Grammar Framework [KTV92, TJ94, Vou94, Vou95] constitutes one of the possible approaches to partial parsing. In this approach only shallow analysis are produced: each word is furnished with its corresponding part of speech tag plus a syntactic tag indicating a surface syntactic function. This representation seeks to be expressive enough for ....

Voutilainen, A. A Syntax-Based Part-of-Speech Analyzer. In Proceedings of the 7th EACL, 1995. 31

....morphological phenomena. Recently, rule based approaches are re studied to cope with the limitations of statistical approaches by learning symbolic tagging rules automatically from a corpus [ Brill, 1992; 1994 ] Some systems even perform the POS tagging as part of syntactic analysis process [ Voutilainen, 1995 ] However, rule based approaches alone, in general, are not very robust, and not portable enough to be adjusted to new tag sets and new languages. Also the performance is usually no better than the statistical counterparts [ Brill, 1992 ] To gain the portability and robustness and also to ....

A. Voutilainen. A syntax-based part-of-speech analyzer. In Proceedings of the seventh conference of the European chapter of the association for computational linguitics (EACL-95), pages 157-- 164, 1995.

.... et al. 5] DeRose [6] or a constraint based approach which employs a large number of hand crafted linguistic constraints that are used to eliminate impossible tags or morphological parses for a given word in a given context, recently most prominently exemplified by the Constraint Grammar work [7, 11, 12, 13]. Brill [1, 2, 3] has presented a transformation based learning approach, which induces tagging rules from tagged corpora. This paper presents a novel approach to constraint based tagging which relieves the rule developer from worrying about conflicting rule ordering requirements and constraints. ....

Atro Voutilainen. A syntax-based part-of-speech analyzer. In Proceedings of the Seventh Conference of the European Chapter of the Association of Computational Linguistics, Dublin, Ireland, 1995.

.... tagging systems have used ei ther a statistical approach where a large corpora has been used to train a probabilistic model (e.g. Church [5] Cutting et al. 6] DeRose [7] or a rule based or constraintbased approach, recently most prominently exemplified by the Constraint Grammar work [9, 14, 15, 16], where a large number of hand crafted linguistic constraints are used to eliminate impossible tags or morphological parses for a given word in a given context. Brill [1, 2, 3] has presented a transformation based learning approach, which induces rules from tagged corpora. Recently he has extended ....

A. Voutilainen. A syntax-based part-of-speech analyzer. In Proceedings of the Seventh Conference of the European Chapter of the Association of Computational Linguistics, Dublin, Ireland, 1995.

....disambiguated a word sense disambiguation is needed, and that is an even harder problem [1] Part of speech taggers can be constructed in various ways, and different types of taggers have different advantages. Taggers can be based on stochastic models (for example [2, 3, 4, 5, 6, 7] on rules ([8, 9]) or on neural networks ( 10] In a recent paper, Samuelsson and Voutilainen claim that rule based taggers can give higher tagging accuracy than plain stochastic taggers on correct texts [11] But hybrids between rule based taggers and stochastic taggers might be even better [12] Some different ....

A. Voutilainen. A syntax-based part-of-speech analyzer. In 7th Conf. European Chapter Assoc. Comp. Linguistics, pages 157--164. ACL, 1995.

....used to train a statistical model which then has been used to tag new text, assigning the most likely tag for a given word in a given context (e.g. Church [7] Cutting et. al [9] DeRose [10] or a constraint based approach, recently most prominently exemplified by the Constraint Grammar work [15, 28, 29, 30], where a large number of hand crafted linguistic constraints are used to eliminate impossible tags or morphological parses for a given word in a given context. Using the constraint grammar, it is claimed that an English text can be morphologically disambiguated with 99.77 recall and 95.54 ....

....with totally unrelated roots and morphological features, as will be exemplified in the next chapter. The previous approach to tagging and morphological disambiguation for Turkish text had employed a constraint based approach [24, 19] along the general lines of similar previous work for English [15, 26, 27, 28, 29, 30]. Although the results obtained there were reasonable, the fact that all constraint rules were hand crafted, posed a rather serious impediment to the generality and improvement of the system. This thesis presents the morphological disambiguation of a Turkish text, based on constraints. The tokens, ....

[Article contains additional citation context not shown here]

A. Voutilainen. A syntax-based part-of-speech analyzer. In Proceedings of the Seventh Conference of the European Chapter of the Association of Computational Linguistics, Dublin, Ireland, 1995.

.... which then has been used to tag new text, assigning the most likely tag for a given word in a given context (e.g. Church [4] Cutting et al. 5] DeRose [6] Another approach is the rule based or constraint based approach, recently most prominently exemplified by the Constraint Grammar work [8, 15, 16, 17], where a large number of hand crafted linguistic constraints are used to eliminate impossible tags or morphological parses for a given word in a given context. Brill [1, 2] has presented a transformation based learning approach, which induces rules from tagged corpora. Recently he has extended ....

A. Voutilainen. A syntax-based part-of-speech analyzer. In Proceedings of the Seventh Conference of the European Chapter of the Association of Computational Linguistics, Dublin, Ireland, 1995.

No context found.

A. Voutilainen. A syntax-based part-of-speech analyzer. In Proceedings of the Seventh Conference of the European Chapter of the Association of Computational Linguistics, Dublin, Ireland, 1995.

No context found.

Voutilainen, Atro. 1995b. A syntax-based part-of-speech analyzer. In Proceedings of the Seventh Conference of the European Chapter of the Association of Computational Linguistics, Dublin, Ireland.

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