Tài liệu Báo cáo khoa học: "Deterministic Parsing of Syntactic Non-fluencies" docx

... corpus of over twenty hours of transcribed speech, in the process of using the parser to search for various syntactic constructions. Tht~ transcripts are of sociolinguistic interviews of the ... understanding of the differences in the kinds of non-fluencies that occur, we are left with a kind of grab bag of grammatical deviation that can never be analyzed except by s...

Ngày tải lên: 21/02/2014, 20:20

... the set of all nodes in the left (right) portion of some tree in IuA. Note that the three sets Middle-nodes, Left-nodes and Right-nodes constitute a partition of the set of all nodes of trees ... 1985)). TAGs can cope with various kinds of unbounded dependencies in a direct way because of their extended domain of locality; in fact, the elementary trees of TAGs are...

Ngày tải lên: 22/02/2014, 10:20

... tions of the languages involved and on an adequate statement of equivalences. Translation is conceived of as a three-step process: recognition of the structure of the incoming text in terms of ... considera- tion of a number of factors. Foremost among these is the necessity of breaking down a prob- lem as complex as that of mechanical transla- tion into a number of...

Ngày tải lên: 19/02/2014, 19:20

... of the head daughter of i-th item from the top of the stack Snw(i) … head word of the non-head daughter of i-th item from the top of the stack Snp(i) … head POS of the non-head daughter of ... top of the stack Ssy(i) … symbol of phrase category of the i-th item from the top of the stack Shsy(i) … symbol of phrase category of the head daughter of the i-th...

Ngày tải lên: 22/02/2014, 02:20

... i th child of the parent produced by rule m. Aside from ensuring the grammaticality of the generated MR, rules of this type also model the probability of the MR, con- ditioning the probability of a ... percentage of sentences with correct answers), as well as F1: the harmonic mean of precision (the proportion of correct answers out of sentences with a parse) and recall (the...

Ngày tải lên: 19/02/2014, 19:20

... Large-scale Parsing Systems, pages 37–42, Luxembourg. Anoop Sarkar. 2001. Applying co-training methods to statistical parsing. In Proceedings of the Second Meeting of the North American Chapter of the ... volumes of text and detailed syntactic information are both critical for high performance. To avoid a trade- off between these two, we need to increase parsing speed, but with...

Ngày tải lên: 20/02/2014, 04:20

... approach described here makes use of a trans- form on a tree-annotated corpus to build a syntactic model of speech repair which takes advantage of the structure of speech repairs as described above, ... dual of a left- corner transform. It transforms all right recursive sequences in each tree into left recursive sequences of symbols of the form A 1 /A 2 , denoting an incom- pl...

Ngày tải lên: 20/02/2014, 09:20

Ngày tải lên: 20/02/2014, 18:20

... of the form A[a] + ~. A T is just a derivation (proof tree) of lZ~n ,.o parse and its probability like that of any derivation we find is defined as the product of the prob- abilities of ... Among items of the same width, those of type A should be considered last. The algorithm requires space proportional to the number of possible items, which is at most na]VDI 2. E...

Ngày tải lên: 20/02/2014, 19:20

... pro- vide state -of- the-art performance across multiple languages. However, the parsing algorithms re- quire that the score of a dependency tree factors as a sum of the scores of its edges. This ... non- projective parsing algorithm. of dependents have been gathered. T his allows for the collection of pairs of adjacent dependents in a single stage, which allows for the incorp...

Ngày tải lên: 22/02/2014, 02:20