disambiguation in morphological parsing

Ngày tải lên: 18/03/2014, 02:20

... total of 71 machine learning features per word. We specify a window of two words preceding and following the current word, using all 71 features for each word in this 5-word window. In addition, ... +y ‘my’). In our approach, tokenizing and morphologically tagging (including part-of-speech tagging) are the same operation, which consists of three phases. First, we obtain from our morphological ... support vector machines which includes Viterbi decoding. 6 As training features, we use two sets. These sets are based on the ten morphological features in Fig- ure 2, plus four other “hidden” morphological...

Ngày tải lên: 20/02/2014, 15:20

Ngày tải lên: 17/03/2014, 00:20

Ngày tải lên: 31/03/2014, 01:20

... training speed of discrimina- tive parsing. Our discriminative parsing method has no generative component, yet surpasses a generative baseline on con- stituent parsing, and does so with mini- mal ... & Norvig, 1995). 3 Training Method 3.1 General Setting Our training set I consists of candidate inferences from the parse trees in the training data. From each training inference i ∈ I we generate ... development set as training progressed. Even though the baseline training made progress more quickly than the kitchen sink, the kitchen sink’s F 1 surpassed the baseline’s F 1 early in training, and at 6.3K...

Ngày tải lên: 08/03/2014, 02:21

Ngày tải lên: 08/03/2014, 05:21

... but nothing hinges on this decision; indeed, as we point out below, we will ultimately want a left-to-right parsing algorithm so that the phonological and syntactic parsing can be interleaved. ... necessary to provide a principled way of dealing with certain morphological processes, but such an approach to phonological processing is crucial for any interface of current parsing systems with ... correspondences. However, in our model, phonological rules are defined for particular domains of application rather than continuously applying as in the KIMMO parser for Finnish. For example, Warlpiri...

Ngày tải lên: 08/03/2014, 18:20

Ngày tải lên: 08/03/2014, 21:20

Ngày tải lên: 18/03/2014, 02:20

Ngày tải lên: 30/03/2014, 17:20

Ngày tải lên: 30/03/2014, 21:20

Ngày tải lên: 31/03/2014, 17:20

Ngày tải lên: 31/03/2014, 17:20

Ngày tải lên: 01/04/2014, 00:20

... dependency pars- ing that the algorithm in Figure 4 does not generate every pair of bunsetsus. 3 4 Active Learning for Parsing Most of the methods of active learning for parsing in previous work ... Fernando Pereira. 2005. Online large-margin training of de- pendency parsers. In Proc. of ACL-2005, pages 523–530. Joakim Nivre. 2003. An efficient algorithm for pro- jective dependency parsing. In Proc. of ... analysis using cascaded chunking. In Proc. of CoNLL-2002, pages 63–69. Sadao Kurohashi and Makoto Nagao. 1998. Building a Japanese parsed corpus while improving the parsing system. In Proc. of...

Ngày tải lên: 20/02/2014, 04:20

... Dan Klein, 2010. Painless unsu- pervised learning with features. In Proc. of NAACL. Taylor Berg-Kirkpatrick and Dan Klein, 2010. Phyloge- netic Grammar Induction. In Proc. of ACL. Cristina Bosco ... conversion schemes in Ger- man supervised constituency parsing and found one to have positive in uence on parsing quality. Dependency Model with Valence (DMV). DMV (Klein and Manning, 2004) defines ... shown in Figure 4. In this case, the sec- ond corpus is obtained from the gold standard by replacing each prepositional phrase in the gold standard withthe corresponding 670 model prefers setting...

Ngày tải lên: 20/02/2014, 04:20

... deterministic dependency parsing. In Proceedings of the Work- shop on Incremental Parsing: Bringing Engineering and Cognition Together (ACL), pages 50–57. Joakim Nivre. 2006. Constraints on non-projective ... dependency parsing. In Proceedings of IWPT, pages 122–131. Ryan McDonald, Koby Crammer, and Fernando Pereira. 2005a. Online large-margin training of de- pendency parsers. In Proceedings of ACL, ... Marinov. 2006. Labeled pseudo-projective dependency parsing with support vector machines. In Proceedings of CoNLL, pages 221–225. Joakim Nivre. 2004. Incrementality in deterministic dependency parsing. ...

Ngày tải lên: 20/02/2014, 07:20

... 4.8 +mechanismsubjlink +mechanismsubjlink + currencyobjlink 10.2 mechanismsubjlink 3.4 +European Monetary Systemsubjlink 0 +currencyobjlink +Systemsubjlink +currencyobjlink 0 European Monetary Systemsubjlink 0 Systemsubjlink ... 0 Systemsubjlink 0 +systemsubjlink +currencyobjlink 0 systemsubjlink 1.2 +companysubjlink +currencyobjlink 0 companysubjlink -1.1 empty 3 Table 3: Queries f or computing high attach- ment ... Unlabeled Data in Ma- chine Learning and Data Mining, ICML. Mark Johnson and Stefan Riezler. 2000. Ex- ploiting auxiliary distributions in stochastic unification-based grammars. In NAACL. David...

Ngày tải lên: 20/02/2014, 12:20

... modeling the end of supervised parsing has come in sight. 1 Introduction A major challenge in natural language parsing is the unsupervised induction of syntactic structure. While most parsing ... strings (we will come back to word strings in section 5). Each corpus was divided into 10 training/test set splits of 90%/10% (n-fold testing), and each training set was randomly divided into ... believe that our result is quite promising for the future of unsupervised parsing. In putting our best f-score in table 4 into perspective, it should be kept in mind that the gold standard trees...

Ngày tải lên: 20/02/2014, 12:20

... previously seen in the training corpus, and therefore their overall coverage is not 100%. Starting with an annotated corpus consisting of all annotated files in SemCor, a separate training data set is ... Min- imally supervised word sense disambiguation for all words in open text. In Proceedings of ACL/SIGLEX Senseval-3, Barcelona, Spain, July. R. Mihalcea and D. Moldovan. 2002. Pattern learning and ... sense disambiguation algorithm, in that it uses a relatively small data set for training purposes, and generalizes the concepts learned from the training data to disambiguate the words in the...

Ngày tải lên: 20/02/2014, 15:20