Báo cáo khoa học: "DESIGN DIMENSIONS FOR NON-NORMATIVE ONDERSTARDING SYSTEMS" ppt

... proposed for relaxing well-formedness constraints on input to permit components to derive well- structured output for both well-formed and ill- formed input: 1. extend the notion of well-formed ... criteria for different classes of errors, and procedures to invert the error process, an "explanation" for an ill-formed utterance could be generated in the form of an i...

Ngày tải lên: 24/03/2014, 01:21

... describe an approach for the use of syntactic information within phrase-based SMT systems. The approach constitutes a simple, direct method for the incorporation of syntactic informa- tion in a phrase–based ... transformation that moves an infinitival verb to the first position in a verb phrase. Xia et. al’s approach would require learning of a different rule transformation for every prod...

Ngày tải lên: 20/02/2014, 15:20

... bracketing for a given noun sequence, known to form a compound noun, without knowledge of the context. E.G.: (pottery (coffee mug)); ((coffee mug) holder) Corpus Statistics: The need for wide ... ordered pair of thesaurus categories (ti, t2) using the formula below. CA(t1, t2) is the mutual information between the categories, weighted for ambiguity. It measures the degree to wh...

Ngày tải lên: 08/03/2014, 07:20

... interface for Information Retrieval. Proceedings of the 6th Annual International ACM SIGIR Conference, ACM Special Interest Group on Information Retrieval and American Society for Infor- mation ... word gets transmitted and no pattern for it exists in a base IRule for the head word, higher IRules are searched for the pattern. If a pattern does exist for the modifier in a gi...

Ngày tải lên: 08/03/2014, 18:20

... Targeted Help for Spoken Dialogue Systems: intelligent feedback improves naive users' performance Beth Ann Hockey Research Institute for Advanced Computer Science (RIACS), NASA ... the information from the secondary recognizer is suf- ficient to produce useful help messages. Since this domain is relatively novel, there is not very much data for training the SLM and the performance...

Ngày tải lên: 08/03/2014, 21:20

... map- ping. Therefore, we obtained new results for these methods in our setup. For the Transfer baseline, for each target language we trained the model on all other languages in our dataset. For the Mixture baseline, ... im- pact the final performance. As a selection criterion for initialization, we consider the performance of the final model averaged over the supervised source lan- gu...

Ngày tải lên: 16/03/2014, 19:20

... dev2 and dev3) for development and testing. We used the dev1 set for parameter tuning, the dev2 set for choosing the setting of the proposed method, which is described below, and the dev3 set for test- ing. The ... translation experiments using IWSLT 2007 (Fordyce, 2007) dataset. This dataset con- tains EJ and EC parallel corpus for the travel domain and consists of 40k sentences f...

Ngày tải lên: 17/03/2014, 00:20

... Introduction In many information foraging tasks, there is a need to find all text snippets relevant to a target concept. Patent search services spend significant resources looking for prior art relevant ... problems can be formulated as a relation recognition task, where the information need is ex- pressed as tuples of arguments and relations. This structure provides additional information wh...

Ngày tải lên: 17/03/2014, 02:20

... preposi- tional phrases and vice-versa, a normalized form for noun phrases has been defined which reserves a position in the tree for prepositions. For stan- dard noun phrases a special value (NIL) ... Example of the normalized form for NPs and PPs. 4.4 CONSIDERATIONS FOR TRANSLATION The goal of the system, and perhaps of MT in general, has to be to carry over the information...

Ngày tải lên: 17/03/2014, 19:21

... Chapter of the Association for Computational Linguistics, pages 92–96, Avignon, France, April 23 - 27 2012. c 2012 Association for Computational Linguistics A platform for collaborative semantic ... is a web-based platform, it paves the way for a collab- orative annotation effort. Currently it is actively in use as a tool to create a large semantically an- notated corpus for Englis...

Ngày tải lên: 17/03/2014, 22:20