| other,11-4-H01-1001,ak | <term> keywords </term> as the <term> document | representation | </term> but <term> oral communication </term> | #67 Traditional information retrieval techniques use a histogram of keywords as the document representation but oral communication may offer additional indices such as the time and place of the rejoinder and the attendance. | |
| tech,19-2-H01-1041,ak | mediated by a <term> language neutral meaning | representation | </term> called a <term> semantic frame </term> | #433 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 a semantic frame. | |
| model,26-1-N03-1033,ak | contexts </term> via a <term> dependency network | representation | </term> , ( ii ) broad use of <term> lexical | #2938 We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of lexical features, including jointly conditioning on multiple consecutive words, (iii) effective use of priors in conditional loglinear models, and (iv) fine-grained modeling of unknown word features. | |
| </term> . We describe a new method for the | representation | of NLP structures within <term> reranking | #5437 We describe a new method for the representation of NLP structures within reranking approaches. | ||
| other,4-2-P05-1018,ak | </term> . We present a novel <term> entity-based | representation | of discourse </term> which is inspired by | #8609 We present a novel entity-based representation of discourse which is inspired by Centering Theory and can be computed automatically from raw text. | |
| other,14-3-P05-1018,ak | and show that the proposed <term> discourse | representation | </term> supports the effective learning of | #8642 We view coherence assessment as a ranking learning problem and show that the proposed discourse representation supports the effective learning of a ranking function. | |
| model,13-1-P06-1052,ak | </term> : Given an <term> underspecified semantic | representation | ( USR ) </term> of a <term> scope ambiguity | #12070 We present an efficient algorithm for the redundancy elimination problem: Given an underspecified semantic representation (USR) of a scope ambiguity, compute an USR with fewer mutually equivalent readings. | |
| model,4-2-P06-1052,ak | </term> operates on <term> underspecified chart | representations | </term> which are derived from <term> dominance | #12094 The algorithm operates on underspecified chart representations which are derived from dominance graphs; it can be applied to the USRs computed by large-scale grammars. | |
| <term> path-based inference rules </term> to the | representation | of the <term> extensional equivalence </term> | #13129 Applications of path-based inference rules to the representation of the extensional equivalence of intensional concepts, and to the explication of inheritance in hierarchies are sketched. | ||
| other,27-5-P81-1033,ak | construction </term> , and specialized <term> ambiguity | representations | </term> for each type of <term> ambiguity </term> | #14016 Focused interaction of this kind is facilitated by a construction-specific approach to flexible parsing, with specialized parsing techniques for each type of construction, and specialized ambiguity representations for each type of ambiguity that a particular construction can give rise to. | |
| other,10-2-P84-1047,ak | the <term> structure </term> and <term> surface | representation | </term> of <term> domain entities </term> are | #15058 In this approach, the definitions of the structure and surface representation of domain entities are grouped together. | |
| other,26-3-P85-1024,ak | goals </term> , rather than upon precise <term> | representations | </term> of the preceding <term> utterance </term> | #16002 We claim that the advantage of this approach is its reliance upon pragmatic information, including discourse content and conversational goals, rather than upon preciserepresentations of the preceding utterance alone. | |
| other,21-4-C88-1007,ak | relation </term> , not as levels of <term> textual | representation | </term> . After introducing this approach | #17966 Semantic and other information may still be incorporated, but as constraints on the translation relation, not as levels of textual representation. | |
| model,3-3-C88-2162,ak | linguistic domain . For another , <term> linguistic | representation | </term> used by <term> language processing | #18621 For another, linguistic representation used by language processing systems is not geared to learning. | |
| model,4-4-C88-2162,ak | </term> . We introduced a new <term> linguistic | representation | </term> , the <term> Dynamic Hierarchical Phrasal | #18638 We introduced a new linguistic representation, the Dynamic Hierarchical Phrasal Lexicon (DHPL) [Zernik88], to facilitate language acquisition. | |
| other,11-4-E91-1012,ak | simple way to construct a very compact <term> | representation | </term> of the <term> parse forest </term> . | #21526 Memo-functions also facilitate a simple way to construct a very compactrepresentation of the parse forest. | |
| expressing <term> relations </term> between | representations | in the form of <term> feature structures </term> | #21668 Unification is often the appropriate method for expressing relations between representations in the form of feature structures; however, there are circumstances in which a different approach is desirable. | ||
| tech,9-4-P91-1025,ak | <term> information lattice </term> , a <term> | representation | scheme </term> for <term> utterances </term> | #22334 The basic ingredients are an information lattice, arepresentation scheme for utterances embedded in contexts, and a mismatch resolution scheme defined in terms of information flow. | |
| other,8-4-A94-1011,ak | a more <term> linguistically sophisticated | representation | </term> of <term> documents </term> over a <term> | #25897 One of the distinguishing features of a more linguistically sophisticated representation of documents over a word set based representation of them is that linguistically sophisticated units are more frequently individually good predictors of document descriptors (keywords) than single words are. | |
| other,15-4-A94-1011,ak | documents </term> over a <term> word set based | representation | </term> of them is that linguistically sophisticated | #25905 One of the distinguishing features of a more linguistically sophisticated representation of documents over a word set based representation of them is that linguistically sophisticated units are more frequently individually good predictors of document descriptors (keywords) than single words are. |
