Báo cáo khoa học: "LEXICAL ACCESS IN CONNECTED SPEECH RECOGNITION" pptx

... distinguish word.initial/I/ in/ 17/fzom word-inlernal /I/ in /hid/? In this paper, I shall argue for a model which splits the lexical access process into a pre-lexical phonological parsing ... warranted because the resulting system will be considerably more robust in the face of inacct~rate or indeterminate input concerning the nature of the weak syllables in the input utterance. CONCLUSION ... type which all begin at the same point in the signal will be refened to as an access path. The differ, tee between the access strategies is mostly in the number of distinct access paths they...

Tài liệu Báo cáo khoa học: "Lexical Morphology in Machine Translation: a Feasibility Study" potx

... done in NLP research (section 3). We then explain why implementing morphology in the context of ma-chine translation (MT) is a real challenge and what kind of aspects need to be taken into ... particularly useful in a bilingual context for rules that have more than one prefix in both languages: more than one affix can be declared in one single rule, the selection being made according to different ... different constraints or restrictions. For example, the rule for “indeter-minate plurality” explained in section 4.1 can be formalised as follows: Italian French input input (G) Xit...

Tài liệu Báo cáo khoa học: "LEXICAL ACQUISITION IN THE CORE LANGUAGE ENGINE" doc

... linguistic features would allow gen- uinely novel entries to be created, which, given that the user is a non-linguist, Would almost certainly lead to inconsistencies. In addition, endowing ... variable and indeterminate, they are much less so than judgments of semantic acceptabil- ity, which do not play any part in VEX's main decision-making process. In or- der to remind the user ... example sen- tences containing "nonsense nouns" such as "thingummy" and "whatsit". 5 ELICITING SYNTACTIC INFORMATION The algorithm for defining a new word or phrase...

Báo cáo khoa học: "Lexical Selection in the Process of Language Generation" ppt

... proposition-oriented items. Finally, we discuss how lexical selection is influenced by thematic ([oc~) information in the input. I. Introduction There is a consensus among computational linguists that ... and indexicats (here, now, I, there); • prepositions (on, during, against); . paxentheticals and attitudinal~ (az a matter off act, o~ the contrary); • conjunctions, including discontinuous ... lexical output. In other words, the input to generate in English the concept 'son's wife's mother' will find no single lexical item covering the entire expression. In Russian,...

Báo cáo khoa học: "LEXICAL SEMANTICS IN HUMAN-COMPUTER COMMUNICATION" doc

... aspects of naming in computer systems. To the linguist or psycholinguist they are disappointing because there is no theory or analytic framework for describing what is happening. In my own work ... (1983) work on planning referring expressions, and Finin's (1982) work on parsing complex noun phrases, but individual lexical items have not been treated in much detail. In contrast, the ... usefulness of including them in the analyis is seen in the discussion of non-words as names. As Bolinger {1965l pointed out long ago, names and actions have a potentially infinite number of...

Tài liệu Báo cáo khoa học: "What''''s in a Semantic Network?" pptx

... primitives include a fixed set of predicate names and terms denoting three kinds of elements in the domain. We give meaning to these primitives by writing domain- independent axioms involving them. ... could find all properties of an object ol (including those by inheritance) by retrieving all bindings of x in the query 3x,r ROLE(x,r,ol). The ease of access provided by the links in a semantic ... ourselves to binary relations, we can generalize our representation by introducing the predicate ROLE and making rolenames into individuals in the domain. ROLE(o, r, v) asserts that individual...

Báo cáo khoa học: "Modeling Adjectives in Computational Relational Lexica" pptx

... cannot be organized in opposite clusters. As pointed out by Levi (1978), the intrinsic meaning of these ad-jectives is something along the following lines: ‘of, relating/pertaining to, associated ... offer interesting insights concerning adjective linguistic behavior and the identification of relevant common fea-tures, which may set the basis for an accurate modeling of this POS in computational ... should be encoded in computational relational lexica such as wordnets. 3 Adjectives in WordNet and in Eu-roWordNet Hyponymy is the main structuring relation both in WordNet and in EuroWordNet....

Báo cáo khoa học: "Tracking Initiative in Collaborative Dialogue Interactions" pptx

... role in coordinating initiative shifts in face-to-face interactions, a great deal of information regarding initiative shifts can be extracted from utterances based on linguistic and domain ... expertis assigned as follows: in the TRAINS domain, the system; in the airline domain, the travel agent; in the map- task domain, the instruction giver; and in the switchboard dia- logues, ... i.e., informing S of the invalidity of the proposal, while in (3c), A responds by taking over both the task and dialogue initiatives, i.e., informing S of the invalidity and suggesting a possible...

Báo cáo khoa học: "Decoding Algorithm in Statistical Machine Translation" pptx

... do not think I have got anything open m January I think I will not free in January ich glaube wit sollten em weiteres Meeting vereinbaren I think we have to have another meeting I think we ... habe ein Meeting yon halb zehn bis um zwSlf I have a meeting from nine thirty to twelve I have a meeting from nine thirty to twelve versuchen wir sollten es vielleicht mit einem anderen Termin ... following operations: 1. INSERT: to insert a new hypothesis into the set. 2. DELETE: to delete a state in hard pruning. 3. MAXIMUM: to find the state with the best score to extend. 4. MINIMUM:...

Báo cáo khoa học: "Automatic Detection of Poor Speech Recognition at the Dialogue Level" potx

... "good" or "bad" speech recognition (the training set). We then apply standard machine learning algorithms to this training set in the hope of discovering, in a principled manner, classifiers ... learning pro- gram are performed. Thus, each run uses the exam- pies not in the test set for training and the remain- ing examples for testing. An estimated error rate is obtained by averaging ... applied machine learning to detecting patterns suggesting that the user is having problems over the course of a dialogue, (Levow, 1998) has applied machine learning to identifying single misrecogni-...

Xem thêm