Báo cáo khoa học: "Question Answering Using Web News as Knowledge Base" docx

Báo cáo khoa học: "Question Answering Using Web News as Knowledge Base" docx

Báo cáo khoa học: "Question Answering Using Web News as Knowledge Base" docx

... AnswerBus News Engine to automatically answer news related questions. We chose CNN Web site as the knowledge base because it has a good archive of news stories since 1996 and the CNN Web site ... Engine' is a question answering system using the contents of CNN Web site 2 as its knowledge base. Comparing to other question answering systems including its previous...
Ngày tải lên : 31/03/2014, 20:20
  • 4
  • 258
  • 0
Báo cáo khoa học: "Question Answering using Constraint Satisfaction: QA-by-Dossier-with-Constraints" docx

Báo cáo khoa học: "Question Answering using Constraint Satisfaction: QA-by-Dossier-with-Constraints" docx

... is achieved by using con- straints, compared with our baseline system, using standard evaluation metrics. 2 Related Work Logic and inferencing have been a part of Ques- tion -Answering since ... first-round question, the sys- tem can ask more specific questions based on that knowledge. For example, on discovering a person’s profession, it can ask occupation-specific follow-on quest...
Ngày tải lên : 31/03/2014, 03:20
  • 8
  • 254
  • 0
Báo cáo khoa học: "Question Answering System in the Web using the Web" doc

Báo cáo khoa học: "Question Answering System in the Web using the Web" doc

... Esfinge – a Question Answering System in the Web using the Web Luís Fernando Costa Linguateca at SINTEF ICT Pb 124 Blindern, 0314 Oslo, ... question answering system. It tries to take advantage of the great amount of in- formation existent in the World Wide Web. Since Portuguese is one of the most used languages in the web and the web ... existent in the web to find it...
Ngày tải lên : 08/03/2014, 21:20
  • 4
  • 454
  • 0
Tài liệu Báo cáo khoa học: "Question Answering by Lexical Fabric and External Resources" ppt

Tài liệu Báo cáo khoa học: "Question Answering by Lexical Fabric and External Resources" ppt

... include the Web, WordNet, Knowledge bases, and query logs. In our system, we focus on the amalgama- tion of the Web and WordNet. 5.1 Using the Web The Web is the most rapidly growing and com- plete knowledge ... tests. Method P CWS Baseline 0.438 0.440 Baseline + WordNet Gloss 0.442 0.448 Baseline + WordNet Synset 0.438 0.446 Baseline + WordNet (Gloss,Synset) 0.442 0.446 Baseline...
Ngày tải lên : 22/02/2014, 02:20
  • 8
  • 503
  • 0
Báo cáo khoa học: "Question Answering with Lexical Chains Propagating Verb Arguments" pptx

Báo cáo khoa học: "Question Answering with Lexical Chains Propagating Verb Arguments" pptx

... Value ble 1). VerbNet has a static aspect and a dynamic aspect. The static aspect refers to the organiza- tion of verb entries. The dynamic aspect refers to the lexicalized trees associated with syntactic ... VerbNet classes. WordNet 2.0 has 24,632 verb sensekeys, but only 4,983 sensekeys are listed in VerbNet classes. For the rest, syntactic patterns were as- signed automatically. In order...
Ngày tải lên : 08/03/2014, 02:21
  • 8
  • 322
  • 0
Báo cáo khoa học: "Question Answering as Question-Biased Term Extraction: A New Approach toward Multilingual QA" doc

Báo cáo khoa học: "Question Answering as Question-Biased Term Extraction: A New Approach toward Multilingual QA" doc

... no class name extractor. To the best of our knowledge, no previous study has regarded Question Answering as Question-Biased Term Extraction. As a feasibility study, we built a QA system using ... extracts an- swers as terms biased by the question. To confirm the feasibility of our QBTE ap- proach, we conducted experiments on the CRL QA Data based on 10-fold cross val- idation, usin...
Ngày tải lên : 08/03/2014, 04:22
  • 8
  • 357
  • 0
Báo cáo khoa học: "Sense Disambiguation Using Semantic Relations and Adjacency Information" docx

Báo cáo khoa học: "Sense Disambiguation Using Semantic Relations and Adjacency Information" docx

... uses 39 heuristics based on 12 relationships. 1 Introduction Word-sense disambiguation has long been recognized as a difficult problem in computational linguistics. As early as 1960, Bar-Hillel ... linguistics, considerable effort has been devoted to word-sense disambiguation [8]. These approaches can be broadly classified based on the refer- ence from which senses are assigned, a...
Ngày tải lên : 08/03/2014, 07:20
  • 3
  • 297
  • 0
Báo cáo khoa học: "Hybrid Parsing: Using Probabilistic Models as Predictors for a Symbolic Parser" docx

Báo cáo khoa học: "Hybrid Parsing: Using Probabilistic Models as Predictors for a Symbolic Parser" docx

... different knowledge sources into a system for syntactic parsing to our knowledge has never been attempted so far. The possible synergy be- tween different knowledge sources is often as- sumed ... hand CoNLL restricted itself to the eas- ier attachment task and therefore provided the gold standard POS tag as part of the input data, whereas in our case pure word form sequences are ana...
Ngày tải lên : 31/03/2014, 01:20
  • 8
  • 271
  • 0
Tài liệu Báo cáo khoa học: "DESIGN AND IMPLEMENTATION OF A LLXICAL DATA BASE " docx

Tài liệu Báo cáo khoa học: "DESIGN AND IMPLEMENTATION OF A LLXICAL DATA BASE " docx

... least tens of thousands of entries, perhaps even more than I00,000 lexical entries. Needless to say the task of creating as well as the one of updating such huge databases represents an astronomical ... lexical data base is what I would call "practical requirements" and has to do with the complexity of the task of creating a lexical entry. It can roughly be viewed as a...
Ngày tải lên : 22/02/2014, 09:20
  • 8
  • 535
  • 0
Báo cáo khoa học: "Methods for Using Textual Entailment in Open-Domain Question Answering" doc

Báo cáo khoa học: "Methods for Using Textual Entailment in Open-Domain Question Answering" doc

... by as much as 20% overall. 1 Introduction Open-Domain Question Answering (Q/A) sys- tems return a textual expression, identified from a vast document collection, as a response to a question asked ... increase the likelihood that 909 only true paraphrases were considered as phrase- level alternations for an example, extracted sen- tences were clustered using complete-link cluster- i...
Ngày tải lên : 08/03/2014, 02:21
  • 8
  • 535
  • 0