Báo cáo khoa học: "Adapting Self-training for Semantic Role Labeling" pdf

... Association for Computational Linguistics Joint Learning Improves Semantic Role Labeling Kristina Toutanova Dept of Computer Science Stanford University Stanford, CA, 94305 kristina@cs.stanford.edu Aria ... Computer Science Stanford University Stanford, CA, 94305 aria42@stanford.edu Christopher D. Manning Dept of Computer Science Stanford University Stanford, CA, 94305 manning@cs.stanfo...

Ngày tải lên: 08/03/2014, 04:22

... and 0.47 for the complete task. 1 Introduction Semantic role labeling (SRL), the process of auto- matically identifying arguments of a predicate in a sentence and assigning them semantic roles, ... instances for the start classifier, 500,000 for the end classifier, and 272,000 for the role classifier. The features used by the classifiers are described in Subsec- tion 3.2, and the...

Ngày tải lên: 20/02/2014, 12:20

... difl'erent form of disjunction, OR: (~OR formulal formula2). In terms of implementation, think of this as inferring formula1 in all possible ways and then asserting the dis- junction of the formula,s ... refereuts for "'it" (probability rule 4). (One derivation has it that since one pays for what one is shopping for, and Jack is shopping for milk, he mdst...

Ngày tải lên: 21/02/2014, 20:20

... Data-Oriented Semantic Analysis To use the DOP method not just for syntactic anal- ysis, but also for semantic interpretation, four steps must be taken: 1. decide on a formalism for representing ... the semantic formulas of its daughter nodes. Using this convention, the semantic annotation of the corpus trees is indicated as follows: • For every meaningful lexical node...

Ngày tải lên: 22/02/2014, 03:20

... transform syntactic as well as morphological variations of names into a normalized name form. Basic trans- formations can be achieved via pattern match- ing (regular expressions) while for more ... of information are represented as ??. This way, the semantic representation provides all the information about the chemical structure that is given by the name. Thus, it is an ideal basis for...

Ngày tải lên: 08/03/2014, 01:20

... of the Association for Computational Linguistics, pages 316–324, Uppsala, Sweden, 11-16 July 2010. c 2010 Association for Computational Linguistics Discriminative Pruning for Discriminative ... ITG. For instance, there are two parses for three consecutive word pairs, viz. [/ [/ / ] ] and [[/ /] /] . The problem of re- dundancy is fixed by adopting ITG normal for...

Ngày tải lên: 20/02/2014, 04:20

... applications. Grishman (1995) and Hobbs et al. (1995) use phrasal information in information extraction. Alshawi (1996) uses dependency information in a machine translation system. The need to impose ... supertagging may be employed in informa- tion retrieval. Furthermore, given a sentence aligned parallel corpus of two languages and al- most parse information for the sentences of on...

Ngày tải lên: 08/03/2014, 21:20

... covering 38 semantic roles out of 52 roles present in the total training set. We use one unlabeled training set (U) for in- domain and another for out-of-domain experi- ments. The former is the ... pages 91–96, Uppsala, Sweden, 13 July 2010. c 2010 Association for Computational Linguistics Adapting Self-training for Semantic Role Labeling Rasoul Samad Zadeh Kaljahi...

Ngày tải lên: 07/03/2014, 22:20

... without substitution. In this pa- per, we call a tuple of semantic frame and semantic role a semantic signature. Two phrase pairs with the same semantic signature are considered valid substi- tutions ... can be unaligned only if they are inside the semantic role constituent. Utilizing these rules, we can perform the sentence generation process. For each semantic structure of...

Ngày tải lên: 20/02/2014, 04:20

... similarity perform comparably when used for the task of short answer grading. However, since the corpus- based measures can be improved by account- ing for domain and corpus size, the highest per- formance ... improve the performance of the system by integrating automatic feedback from the student answers. Overall, our system significantly and consistently out- performs other unsupervised...

Ngày tải lên: 22/02/2014, 02:20