Báo cáo khoa học: "Making Tree Kernels practical for Natural Language Learning" potx

Tài liệu Báo cáo khoa học: "A Terminological Simplification Transformation for Natural Language Question-Answering Systems" doc

... Simplification Transformation for Natural Language Question-Answering Systems David G. Stallard BBN Laboratories Inc. I0 Moulton St. Cambridge, MA. 02238 Abstract A new method is presented for simplifying ... issues for natural- language systems which serve as interfaces to a database: the problems that arise in a module which maps the meaning representation to a second logical language for expressing ... exists for physician SPECIALTIES, we can nonetheless give a rule for this predicate in way that is uniform with the rule given for the predicate PATIENTS. 2This term, while a standard one in formal...

Báo cáo khoa học: "Edit Tree Distance alignments for Semantic Role Labelling" ppt

... data; Adapt the trees for the tree distance algorithm; foreach sentence (training & testing data) do obtain each minimal sub -tree for each pre-dicate; end foreach sub -tree T from the ... training sample sub -tree which contains labels for all the arguments of the predicate. It is expected for tree distances to be smaller than other sub-trees that do not have information to label ... all the nodes of the sub tree for the ―rose‖ predicate. The dotted double arrows between the nodes of both sentences represent the tree distance alignment for both sub-trees. In this particular...

Tài liệu Báo cáo khoa học: "Exploiting Non-local Features for Spoken Language Understanding" pptx

... improve performance on thestatistical spoken language understanding(SLU) problem. The statistical natural language parsers trained on text performunreliably to encode non-local informa-tion ... models in vari-ous natural language tasks. Thus, we need newmethods to import non-local information into se-quential models.There are two types of method for using non-local information. One ... over the base local model.1 Introduction For most sequential labeling problems in natural language processing (NLP), a decision is madebased on local information. However, processingthat relies...

Tài liệu Báo cáo khoa học: "AN ECLECTIC APPROACH TO BUILDING NATURAL LANGUAGE INTERFACES" pptx

... methodology can be used for any application whose sublanguage can be stated in the prescribed grammar formalism. Tereisias (Davis, 1977) provides a natural language environment for debugging a knowledge ... Rules for diagnosing problems in the circuit | IND led-2 COND[ STATE on [ FORM <sta~(O IND FORM), (t STATE FORM))> CNCL [ DEV tr~i,~torol7 t FORM <s~u.¢((, DEV), fa~ed)> t FORM ... formal language developed by this process. Two of the design constraints we find it advisable to impose are that the language be unambigu- ous (in the formal sense of a unique derivation for...

Báo cáo khoa học: " a Movie Dialogue Corpus for Research and Development" potx

... Association for Computational Linguistics, pages 203–207,Jeju, Republic of Korea, 8-14 July 2012.c2012 Association for Computational LinguisticsMovie-DiC: a Movie Dialogue Corpus for Research ... most common spatial distribution of the aforementioned information elements. It is important to mention that a lot of different variants to the format presented in Figure 1 can be actually ... dialogue sys-tem is targeted for. In some specific domains, in which human-human dialogue applications already exists, data collection is generally straight forward, while in some other cases,...

Báo cáo khoa học: "An exponential translation model for target language morphology" pptx

... number.• For verbs, generated forms had to match theoriginal form for tense and negation.• For adjectives, generated forms had to matchthe original form for degree of comparison andnegation.• For ... The forms pro-duced by the tool from the lemma of an observed in-ﬂected word form were subjected to several restric-tions:• For nouns, generated forms had to match theoriginal form for number.• ... generated forms had to matchthe original form for number, case, and gender.• Non-standard inﬂection forms for all POS wereexcluded.The following criteria were used to select rules for which...

Báo cáo khoa học: "Extracting Social Power Relationships from Natural Language" potx

... Association for Computational Linguistics, pages 773–782,Portland, Oregon, June 19-24, 2011.c2011 Association for Computational Linguistics Extracting Social Power Relationships from Natural Language ... extent to which speak-ers modify their language for a social context amounts to an identifiable variation on language, which we call a lect. Lect is a backformation from words such as dialect ... in-dicative the overall set is. Therefore, we experi-mented with filtering out sets which had a negligible information gain. Information gain is an information theoretic concept measuring...

Báo cáo khoa học: "An Earley Parsing Algorithm for Range Concatenation Grammars" potx

... received agrowing interest in natural language processing(Søgaard, 2008; Sagot, 2005; Kallmeyer et al.,2008; Maier and Søgaard, 2008). RCGs gener-ate exactly the class of languages parsable in de-terministic ... predicate ofthe form Ai(α1, . . . , αdim(Ai)) with Ai∈ N andαj∈ (T ∪ V )∗ for 1 ≤ j ≤ dim(Ai).Central to RCGs is the notion of ranges onstrings.Deﬁnition 2. For every w = w1. ... to instantiate a clause of the grammar,we need to ﬁnd ranges for all variables in theclause and for all occurrences of terminals. For convenience, we assume the variables in a clauseand the...

Tài liệu Báo cáo khoa học: "Exploring Syntactic Structural Features for Sub-Tree Alignment using Bilingual Tree Kernels" docx

... Association for Computational Linguistics Exploring Syntactic Structural Features for Sub -Tree Alignment using Bilingual Tree Kernels Jun Sun1,2 Min Zhang1 Chew Lim Tan2 1 Institute for ... the source sub -tree rooted at VP*. 3.2 Root directed Subset Tree Monolingual Tree kernels achieve decent perfor-mance using the SSTs due to the rich exploration of syntactic information. However, ... that the struc-tural features embedded in a bilingual parse tree pair are very effective for sub -tree alignment and the bilingual tree kernels can well capture such features. The experimental...

Tài liệu Báo cáo khoa học: "Automatic clustering of collocation for detecting practical sense boundary" ppt

... semantic information. The collocation for ambiguous words also contains semantic information about multiple senses for this ambiguous word. This paper uses the ambiguity of collocation for the ... overall process for this purpose. Figure 1 Processing for detecting sense boundary 3 Automatic clustering of collocation For extracting practical senses, the contextual words for a central ... existing thesaurus. Applied corpus for the experiments for English and Korean is Penn tree bank3 corpus and KAIST4 corpus. 3 http://www.cis.upenn.edu/~treebank/home.html 4 http://kibs.kaist.ac.kr...

Xem thêm