Báo cáo khoa học: "Computing Optimal Descriptions for Optimality Theory Grammars with Context-Free Position Structures" docx

Báo cáo khoa học: "Computing Optimal Descriptions for Optimality Theory Grammars with Context-Free Position Structures" docx

Báo cáo khoa học: "Computing Optimal Descriptions for Optimality Theory Grammars with Context-Free Position Structures" docx

... Computing Optimal Descriptions for Optimality Theory Grammars with Context-Free Position Structures Bruce Tesar The Rutgers Center for Cognitive Science / The Linguistics ... edu Abstract This paper describes an algorithm for computing optimal structural descriptions for Optimality Theory grammars with context-free position structures. This algo...
Ngày tải lên : 31/03/2014, 06:20
  • 7
  • 203
  • 0
Báo cáo khoa học: "Computing Confidence Scores for All Sub Parse Trees" pot

Báo cáo khoa học: "Computing Confidence Scores for All Sub Parse Trees" pot

... classifier with all the selected fea- tures, we reached an annotation error rate of 26.0% in the SWBD corpus, compared with a subtree error rate of 41.91%, a closely related benchmark with the ... phrase “a rock song,” the confidence scores for each word, the artist name “Cher,” and the whole sentence would not be enough. For tasks of information extraction, when extracted con...
Ngày tải lên : 17/03/2014, 02:20
  • 4
  • 186
  • 0
Tài liệu Báo cáo khoa học: "Translation Model Adaptation for Statistical Machine Translation with Monolingual Topic Information" doc

Tài liệu Báo cáo khoa học: "Translation Model Adaptation for Statistical Machine Translation with Monolingual Topic Information" doc

... context in- formation at the sentence level, we adopt the topical context information in our method for the following reasons: (1) the topic informa- tion captures the context information beyond the ... 8-14 July 2012. c 2012 Association for Computational Linguistics Translation Model Adaptation for Statistical Machine Translation with Monolingual Topic Information ∗ Jinsong Su 1,2 ,...
Ngày tải lên : 19/02/2014, 19:20
  • 10
  • 533
  • 0
Tài liệu Báo cáo khoa học: "A rich environment for experimentation unification grammars" potx

Tài liệu Báo cáo khoa học: "A rich environment for experimentation unification grammars" potx

... illustration• without entering into discussion of the under- lying complexity, for which we unfortunately do not have space here, we give an exter- nal form of a lexical entry for some of ... all the infor- mation necessary for mapping - 186- instances of verbs with vp or pp complements to a situation schema (Fenstad, Halvorsen, Langholm and van Benthem, 1987). Here, fo...
Ngày tải lên : 22/02/2014, 10:20
  • 8
  • 367
  • 0
Báo cáo khoa học: "Community Answer Summarization for Multi-Sentence Question with Group L1 Regularization" pdf

Báo cáo khoa học: "Community Answer Summarization for Multi-Sentence Question with Group L1 Regularization" pdf

... length of the sentence in the answers with the stop words removed. It seems that a long sentence may contain more information. 2. Position: The sentence’s position within the answer. If a sentence ... features of (Shen et al., 2007) for fair- ness. For the thresholds used in the contextual fac- tors, we enforce τ lq to be equal to τ ls and τ uq equal to τ us for the purpose of simp...
Ngày tải lên : 07/03/2014, 18:20
  • 10
  • 331
  • 0
Báo cáo khoa học: " New Ranking Algorithms for Parsing and Tagging: Kernels over Discrete Structures, and the Voted Perceptron" docx

Báo cáo khoa học: " New Ranking Algorithms for Parsing and Tagging: Kernels over Discrete Structures, and the Voted Perceptron" docx

... many possibilities for . An obvious example for parse trees is to have one component of for each rule in a context-free grammar that underlies the trees. This is the representation used by Stochastic Context-Free ... structures with similar feature vectors will have high values for . More formally, it has been observed that many algorithms can be implemented using inner products...
Ngày tải lên : 23/03/2014, 20:20
  • 8
  • 346
  • 0
Báo cáo khoa học: "Modeling Semantic Relevance for Question-Answer Pairs in Web Social Communities" docx

Báo cáo khoa học: "Modeling Semantic Relevance for Question-Answer Pairs in Web Social Communities" docx

... divergence 25.30 51.40 DBN (without FT) 41.45 59.64 DBN (with FT) 45.00 62.03 Table 1: Results on Forum Dataset We have also investigated the reasons for the un- satisfying performance of the baseline ... stands for the hid- den feature vector for reconstructing the questions. w i j is a symmetric interaction term between word i and hidden feature j, b i stands for the bias of the mo...
Ngày tải lên : 30/03/2014, 21:20
  • 9
  • 259
  • 0
Báo cáo khoa học: "Comprehension and Compilation in Optimality Theory∗" ppt

Báo cáo khoa học: "Comprehension and Compilation in Optimality Theory∗" ppt

... 21218-2691 jason@cs.jhu.edu Abstract This paper ties up some loose ends in finite-state Optimality Theory. First, it discusses how to perform comprehension un- der Optimality Theory grammars consisting of finite-state con- straints. ... underlying (“deep”) form to a surface form. Optimality Theory or OT (Prince and Smolensky, 1993) proposes to describe phonological production as an...
Ngày tải lên : 08/03/2014, 07:20
  • 8
  • 321
  • 0
Báo cáo khoa học: "Efficient Generation in Primitive Optimality Theory" pot

Báo cáo khoa học: "Efficient Generation in Primitive Optimality Theory" pot

... Ellison) unless the CFG contains recursive productions. 2 Primitive Optimality Theory Primitive Optimality Theory. or OTP. is a formal- ization of OT featuring a homogeneous output repre- sentation, ... factors (> 2 4°) for real grammars. Even if a fixed grammar can somehow be compiled into a fast form for use with many inputs, the compilation itself will have to dea...
Ngày tải lên : 17/03/2014, 23:20
  • 8
  • 255
  • 0
Báo cáo khoa học: "Computing and Evaluating Syntactic Complexity Features for Automated Scoring of Spontaneous Non-Native Speech" pot

Báo cáo khoa học: "Computing and Evaluating Syntactic Complexity Features for Automated Scoring of Spontaneous Non-Native Speech" pot

... parsing results where the parser is provided with one sentence at a time. By applying the same selec- tion criteria as before, except for allowing for cor- relations above 0.1 and giving preference ... 3, we have one training set (N=137 speakers with all of their responses combined) for model building and five testing sets (N=52 for each of them) for evalu- ation. The publ...
Ngày tải lên : 07/03/2014, 22:20
  • 10
  • 453
  • 0

Xem thêm

Từ khóa: