Báo cáo khoa học: "PARSING A FREE-WORD ORDER LANGUAGE: WARLPIRI" doc

... Form MacKay and Peto (1995) show that based on Dirich- let priors a reasonable form for a smoothed distribu- tion can be expressed as α(c|ab) = C(abc) C(ab∗) + A (8) γ(ab) = A C(ab∗) + A The parameter ... The interpolated form is: α(c|ab) = max(0, C(abc) − D) C(ab∗) (4) γ(ab) = N(ab∗)D C(ab∗) The ∗ represents a wildcard matching any word and C(ab∗) is the total count of n-grams th...

Ngày tải lên: 20/02/2014, 09:20

... a par- ticular free-word order language, Warlpiri, an aboriginal language of central Australia. The parser is explicitly de- signed to transparently mirror the principles of GB. The operation ... for dative case. Once co-projected, the dative case-marker may then mark its selected sibling for dative case. Because ku is also a case- assigner, and because kurdu has already b...

Ngày tải lên: 17/03/2014, 20:20

... mental) karaka of 'kAta' (cut). G.I rAma Pala KAkara mohana ko bulAtA hE. Ram fruit having-eaten Mohan -ko calls (Having eaten fruit, Ram calls Mohan. ) G.2 rAma ne Pala kAtakara KAyA. ... karta.~5 ~arma rAma Pala (~ruit) KA (eat) rAma Pala kAta (cut) (fruit) karta . karma rAma Pala le (take) kart/~arma~~urpos e vaha cAkU kAta (cut) (he) (knife) /a karta rma...

Ngày tải lên: 08/03/2014, 07:20

... any significant difference in meaning (leaving aside questions of context and pragmatics) in any the six possible permutations: Paolo ama Maria, Paolo Maria ama, Maria ama Paolo, Maria Paolo ... Paolo ama, ama Paolo Maria, ama Maria Paolo. Although Subject-Verb-Object is a statistically prevalent construction, all variations in word order can occur inside a component, and they may...

Ngày tải lên: 18/03/2014, 02:20

... Switzerland pfister@tik.ee.ethz.ch Abstract We propose a language model based on a precise, linguistically motivated grammar (a hand-crafted Head-driven Phrase Structure Grammar) and a statistical model estimating the probability ... linguistically motivated grammar, and we have successfully applied it to a difficult broad-domain task. It is a well-known fact that natural language...

Ngày tải lên: 17/03/2014, 02:20

... grammars that generate finite languages. In natural language process- ing, this problem arises in several areas of application, including natural language generation, speech recognition and ma- chine ... symbols that are not accessed during a subcomputation. As an exam- ple, the shaded area labelled III represents segment , for certain stack symbols , and , and this abstracts away from the s...

Ngày tải lên: 17/03/2014, 08:20

... described above in the so-called cross-domain language model adaptation paradigm, where we adapt a model trained on one domain (which we call the 228 background domain) to a different domain (adap- tation ... data for each do- main. We created the training samples for discrimi- native learning as follows. For each phonetic string A in adaptation training data, we pro- duced a la...

Ngày tải lên: 17/03/2014, 04:20

... syntactic analysis of substantial fragments of natural language. These developments also demonstrate that if natural language processing systems are to be able to handle the grammatical and ... to domain knowledge already encoded in the knowledge base of a limited domain natural language application such as a database query system. Given a hand-coded hierarchical organization of...

Ngày tải lên: 22/02/2014, 09:20

... HLT-NAACL 2004: Main Proceedings, pages 249–256, Boston, Massachusetts, USA, May 2 - May 7. Association for Computational Linguistics. Mengqiu Wang, Kenji Sagae, and Teruko Mitamura. 2006. A fast, ... Language Processing, pages 133–143, Sapporo, Japan, July. Association for Computational Linguis- tics. Richard Sproat, William Gale, Chilin Shih, and Nancy Chang. 1996. A stochastic finite-st...

Ngày tải lên: 17/03/2014, 00:20

... Tsubouchi H, Naka D, Takahashi K, Okigaki M, Arakaki N, Nakayama H, Hirono S, Sakiy- ama O, Takahashi K et al. (1989) Molecular cloning and sequence analysis of cDNA for human hepatocyte growth factor. ... Yokohama, Japan 2 Advanced Medical Research Laboratory, Mitsubishi Tanabe Pharma Corporation, Kamoshida-cho, Aoba-ku, Yokohama, Japan Introduction Type II transmembrane serine proteases (TT...

Ngày tải lên: 15/02/2014, 01:20