| other,2-2-H92-1026,bq | </term> incorporates <term> lexical , syntactic , | semantic | , and structural information </term> from | #18925 HBG incorporates lexical, syntactic, semantic, and structural information from the parse tree into the disambiguation process in a novel way. |
| tech,25-2-H01-1041,bq | meaning representation </term> called a <term> | semantic | frame </term> . The key features of the <term> | #436 The CCLINC Korean-to-English translation system consists of two core modules, language understanding and generation modules mediated by a language neutral meaning representation called asemantic frame. |
| other,8-5-T78-1031,bq | rules </term> can be constructed in a <term> | semantic | network </term> using a variant of a <term> | #12137 Node-based inference rules can be constructed in asemantic network using a variant of a predicate calculus notation. |
| other,1-4-P82-1035,bq | being described . These <term> syntactic and | semantic | expectations </term> can be used to figure | #13058 These syntactic and semantic expectations can be used to figure out unknown words from context, constrain the possible word-senses of words with multiple meanings (ambiguity), fill in missing words (elllpsis), and resolve referents (anaphora). |
| other,6-2-P03-1068,bq | backbone of the <term> annotation </term> are <term> | semantic | roles </term> in the <term> frame semantics | #4969 The backbone of the annotation aresemantic roles in the frame semantics paradigm. |
| other,6-3-C94-1052,bq | experiments , corresponding to rather <term> closed | semantic | domains </term> , have been developed in | #20796 Several experiments, corresponding to rather closed semantic domains, have been developed in order to generate lexical cross-relations between English and Spanish. |
| tech,13-4-P03-1068,bq | </term> and <term> ambiguity </term> in <term> | semantic | annotation </term> . We investigate the <term> | #5004 On this basis, we discuss the problems of vagueness and ambiguity insemantic annotation. |
| other,6-1-T78-1031,bq | performing <term> inference </term> in <term> | semantic | networks </term> are presented and compared | #12056 Two styles of performing inference insemantic networks are presented and compared. |
| other,10-1-P03-1009,bq | <term> clustering </term> in inducing <term> | semantic | verb classes </term> from undisambiguated | #3894 Previous research has demonstrated the utility of clustering in inducingsemantic verb classes from undisambiguated corpus data. |
| other,1-3-P84-1047,bq | </term> are grouped together . Like <term> | semantic | grammar </term> , this allows easy exploitation | #13351 Likesemantic grammar, this allows easy exploitation of limited domain semantics. |
| other,3-1-C90-3063,bq | defeasibility </term> . Manual acquisition of <term> | semantic | constraints </term> in broad domains is very | #16607 Manual acquisition ofsemantic constraints in broad domains is very expensive. |
| other,31-1-C90-3045,bq | </term> , for instance , to the task of <term> | semantic | interpretation </term> or <term> automatic | #16456 The unique properties of tree-adjoining grammars (TAG) present a challenge for the application of TAGs beyond the limited confines of syntax, for instance, to the task ofsemantic interpretation or automatic translation of natural language. |
| other,8-3-N04-1024,bq | </term> of <term> sentences </term> based on <term> | semantic | similarity measures </term> and <term> discourse | #6698 This system identifies features of sentences based onsemantic similarity measures and discourse structure. |
| measure(ment),19-3-H01-1058,bq | performance </term> ( typically , <term> word or | semantic | error rate </term> ) from a list of <term> | #1091 The oracle knows the reference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word strings, where each word string has been obtained by using a different LM. |
| other,25-2-I05-5003,bq | <term> classifiers </term> to predict <term> | semantic | equivalence </term> and <term> entailment </term> | #8362 This paper investigates the utility of applying standard MT evaluation methods (BLEU, NIST, WER and PER) to building classifiers to predictsemantic equivalence and entailment. |
| other,8-3-C90-3063,bq | these <term> statistics </term> reflect <term> | semantic | constraints </term> and thus are used to | #16641 To a large extent, these statistics reflectsemantic constraints and thus are used to disambiguate anaphora references and syntactic ambiguities. |
| tech,16-1-I05-5003,bq | related to the task of <term> sentence-level | semantic | equivalence classification </term> . This | #8333 The task of machine translation (MT) evaluation is closely related to the task of sentence-level semantic equivalence classification. |
| other,39-3-H92-1060,bq | gluing them together to obtain a single <term> | semantic | frame </term> encoding the full <term> meaning | #19425 Robust parsing is applied only after a full analysis has failed, and it involves the two stages of 1) parsing a set of phrases and clauses, and 2) gluing them together to obtain a singlesemantic frame encoding the full meaning of the sentence. |
| other,26-7-A94-1026,bq | its neighbors is not a member of the <term> | semantic | set </term> defined by the <term> homophone | #20510 The method accurately determines that a homophone is misused in a compound noun if one or both of its neighbors is not a member of thesemantic set defined by the homophone. |
| other,17-6-A94-1026,bq | component places some restrictions on the <term> | semantic | categories </term> of the <term> adjoining | #20477 The basic idea of this method is that a compound noun component places some restrictions on thesemantic categories of the adjoining words. |
