Báo cáo khoa học: "Generalizing over Lexical Features: Selectional Preferences for Semantic Role Classification" docx

... 73–76, Suntec, Singapore, 4 August 2009. c 2009 ACL and AFNLP Generalizing over Lexical Features: Selectional Preferences for Semantic Role Classification Be ˜ nat Zapirain, Eneko Agirre Ixa Taldea University ... out-of-domain data. Our findings suggest that selectional pref- erences have potential for improving a full system for Semantic Role Labeling. 1 Introduction...

Ngày tải lên: 23/03/2014, 17:20

... either a semantic argu- ment or a non-argument while semantic role classi- fication involves classifying each semantic argument identified into a specific semantic role. This paper focuses on semantic ... Temporal, Manner, and Cause, etc. Generally, semantic role identification and classification are regarded as two key steps in semantic role labeling. Semantic ro...

Ngày tải lên: 23/03/2014, 18:20

... beforehand. The motivation for leaving aside segmenting were both practical – previous discourse parsing efforts (Soricut and Marcu, 2003; LeThanh et al., 2004) already provide alternatives for ... (SPADE) Penn Treebank Tokenized EDUs EDUs Lexicalized Syntax Trees Syntax Parsing (Charniak's nlparse) Syntax Trees Lexicalization Lexicalization Lexicalized Syntax Trees Syntax Trees...

Ngày tải lên: 30/03/2014, 23:20

... not know a priori what lexical fea- tures are used in her language, there are two sources for acquiring this information: semantic and syntactic cues. A learner using semantic cues could recognize ... from this deduce the lexical features: noun, verb and adjective. Pinker [Pinker 89] proposes that a combination of semantic cues and innate semantic primitives could account...

Ngày tải lên: 17/03/2014, 08:20

... on lexical features alone is not sufficient for finding salient indexing terms. Indeed, we must classify terms that are not en- countered while training. Therefore, we hypoth- esize that non -lexical ... research/ vocabularies/aat/ F.2 Semantic Type (nominal): The concept’s se- mantic categorization. There are currently 132 different semantic types 7 in the UMLS Metathesaurus. For ex...

Ngày tải lên: 17/03/2014, 22:20

... improve- ments over models that focus on a single goal. (Goldberg and Zhu, 2006) adapt semi-supervised graph-based methods for sentiment analysis but do not incorporate lexical prior knowledge in the form ... determining the extent to which to enforce the feature labels, to be 1/2, and β, the corresponding parameter for enforcing document labels, to be 1. 6.2 Sentiment Analysis with...

Ngày tải lên: 30/03/2014, 23:20

... words') are lexical items that signal the kind of coherence relation holding between adjacent text spans; for exam- ple, because, since, and for this reason are dif- ferent markers for causal ... grammar rather than to the lexicon. But for a single discourse relation there is often a set of similar markers, allowing for a range of para- phrases for expressing the...

Ngày tải lên: 20/02/2014, 18:20

... sir for how many people please" Figure 3: Structure for (1) 3.2 Splitting input into well-formed parts and ill-formed parts Item (C) splits input into well-formed parts and ill-formed ... com- paring the splitting performance for some values, and are effective only for the present TDMT system. 424 Table 1: Effect of splitting on translation performance output rate (%) p...

Ngày tải lên: 08/03/2014, 05:21

... (MT, henceforth) are a common and well-understood data struc- ture for describing hierarchical linguistic information. With the availability of large treebanks, retrieval techniques for highly ... DB A g C TG(t, h)}, which lists for each treegram g of height h every database tree that contains g. We compute the desired result set R = {t C DBIq ___ t} for a given query tree q...

Ngày tải lên: 17/03/2014, 23:20

... drops by 8.3% for Forward and by almost 6% for Perf- Match and EdgeCover. Nevertheless, both Perf- Match and EdgeCover outperform the local For- ward model. PerfMatch is the best performing model ... earlier semantic role projection framework in two impor- tant ways. First, we formalise constituent projec- tion as the search for a minimum weight edge cover in a weighted bipartite...

Ngày tải lên: 31/03/2014, 01:20