Báo cáo khoa học: "EXPLOITING CONVERSATIONAL IMPLICATURE FOR GENERATING CONCISE EXPLANATIONS" pdf

... approach for achieving conciseness in generating explanations, which is clone by exploiting formal reconstructions of aspects of the Gricean principle of relevance to simulate conversational implicature. ... EXPLOITING CONVERSATIONAL IMPLICATURE FOR GENERATING CONCISE EXPLANATIONS HELMUT HORACEK Universit~t Bielefeld Fakultlit f'dr ... kind of infor- mation is ty...

Ngày tải lên: 24/03/2014, 05:21

... problem is par- ticular severe for WSD, since sense-tagged data must be collected separately for each word in a language. One source to look for potential training data for WSD is parallel texts, ... surrounding channel then forms a training example for a supervised WSD program in the next step. The average time taken to perform manual se- lection of target translations for...

Ngày tải lên: 08/03/2014, 04:22

... disturbing elements. As for morphol- ogy, verbs are expanded with all their tense forms (i.e. present, present continuous, past tense and past participle). Synonyms and morphological forms are added ... before, AltaVista was used as search engine. A baseline for the answer validation experiment was defined by considering how often an answer oc- curs in the top 10 documents among those (100...

Ngày tải lên: 08/03/2014, 07:20

... Association for Computational Linguistics, pages 675–684, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Exploiting Multiple Treebanks for Parsing ... present a simple and effective framework for exploiting multiple monolingual treebanks with different annotation guidelines for pars- ing. Several types of transformation patterns (TP) are d...

Ngày tải lên: 16/03/2014, 19:20

... PS parses for each sentence in C DS , and convert PS to DS for each parse; — For each sentence in C DS Do  ˆ t=argmax t Score(x i,t ), and select the ˆ t-th parse as a converted tree for this ... POS tag information, dependency structures and depen- dency tags in test set for conversion. Similarly, we used POS tag information in the test set to restrict search space of the parser...

Ngày tải lên: 17/03/2014, 01:20

... develop a novel prior for named entity recognition that exploits the hierarchical fea- ture space often found in natural language domains (§1.2) and allows for the transfer of information from labeled ... 2001), which are now one of the most preferred sequential models for many natural language processing tasks. The parametric form of the CRF for a sentence of length n is given as fol...

Ngày tải lên: 23/03/2014, 17:20

... function, defined as R : S × A → , R(s, a) encodes the utility for the agent to perform the action a while in state s. It is therefore a model for the goals or preferences of the agent. A graphical illustration ... 2010. c 2010 Association for Computational Linguistics Towards Relational POMDPs for Adaptive Dialogue Management Pierre Lison Language Technology Lab German Research Cent...

Ngày tải lên: 20/02/2014, 04:20

... Boks 1080 Blindern; 0316 Oslo (Norway) ♠ Center for the Study of Language and Information, Stanford, CA 94305 (USA) { jtl@ifi.uio.no| oe@csli.stanford.edu} Abstract The LOGON MT demonstrator assembles independently ... Norwegian Research Council program for building national infrastructure for language technology (Fenstad et al., 2006). It is the goal for the program as well as for...

Ngày tải lên: 20/02/2014, 12:20

... the Association for Computational Linguistics, pages 16–19, Avignon, France, April 23 - 27 2012. c 2012 Association for Computational Linguistics TransAhead: A Writing Assistant for CAT and CALL ... parts-of-speech for syntactic generalization. Secondly, we build up inverted files of the words in C t for the next stage (i.e., pattern grammar generation). Apart from sentence an...

Ngày tải lên: 22/02/2014, 03:20

... In addition to performance, efficiency of the classifier (C) is important for self-training, which is computationally expensive. Our classifier is a compromise between performance and efficien- cy. ... the total training set. We use one unlabeled training set (U) for in- domain and another for out-of-domain experi- ments. The former is the remaining portion of CoNLL training data...

Ngày tải lên: 07/03/2014, 22:20