Báo cáo khoa học: "Resource Analysis for Question Answering" doc

... to relevant documents in the local corpus. 0 10 20 30 40 50 60 70 80 90 100 0 100 200 300 400 500 600 700 800 900 1000 Web Retrieval Performance For QA document rank # questions Correct Doc Density First ... Density First Correct Doc Figure 1: Web retrieval: relevant document density and rank of first relevant document. In order to evaluate the impact of web docu- ments on TREC questions...

Ngày tải lên: 31/03/2014, 03:20

... annotated a corpus of 2100 questions. 1500 of those questions come from the Li & Roth cor- pus (Li and Roth, 2002), 500 questions were taken from the TREC-10 questions and 100 questions were asked ... the question What operas did Puccini write? We use the term expected answer type or EAT when the type of the answer is implicit but can be deduced from the question using formal methods....

Ngày tải lên: 31/03/2014, 00:20

... Shell Online Question Answering Topic Predictive Dialogue Question Answer Decomposition Question Information Extraction Representation Off−line Question Answering Database (QUAB) Question Answer Figure ... evaluating our proposed 1 AQUAINT is an acronym for Advanced QUestion Answer- ing for INTelligence. 205 Dialogue Management Collection Document Question Similarity Answer F...

Ngày tải lên: 08/03/2014, 04:22

... containing NEs of the question Expected Answer Type (EAT). Table 2 presents the results ob- tained for English and Table 3 for Spanish. We indicate the id of the question (Q), the question type (T) ... the correct answers corresponding to the questions. 1.1 Questions No TYPE QUESTION 1 F F What international organization do people criticize for its policy on ca...

Ngày tải lên: 20/02/2014, 09:20

... initially to be uniform 2. for several iterations do: a. set up a count( , ) table with zero entries b. for = 1 to Q[ ,1] = b( boundary) c. for = 2 to for = 1 to Q[ , ] = 0 for = 1 to Q[ , ] += ... 1 to Q[ , ] += Q[ , ] b( ) s( ) d. for = 1 to R[ , ] = b(boundary ) e. for = to 1 for = 1 to R[ , ] = 0 for = 1 to R[ , ] += R[ , ] b( ) s( ) f. for = 1 to for = 1 to count( ,...

Ngày tải lên: 08/03/2014, 02:21

... 2007. c 2007 Association for Computational Linguistics Text Analysis for Automatic Image Annotation Koen Deschacht and Marie-Francine Moens Interdisciplinary Centre for Law & IT Department ... bulk of un- structured information such as text, images and video, a situation witnessed in many domains (news, biomedical information, intelligence information, business documents, etc.)....

Ngày tải lên: 23/03/2014, 18:20

... 1024–1031, Prague, Czech Republic, June 2007. c 2007 Association for Computational Linguistics Topic Analysis for Psychiatric Document Retrieval Liang-Chih Yu* ‡ , Chung-Hsien Wu*, Chin-Yew ... relevant documents. This work proposes the use of high-level topic information ex- tracted from consultation documents to im- prove the precision of retrieval results. The topic information...

Ngày tải lên: 23/03/2014, 18:20

... techniques for reducing the human effort, such as simplifying rules based on linguis- tic information and machine learning approaches. Our effort for the robustness is focused the question analysis. ... using a technique for deep understanding of the question, the ques- tion analysis component of K-QARD tries to ex- tract only essential information for answering us- ing the info...

Ngày tải lên: 31/03/2014, 01:20

... S 1 , which contains all of the information that is in the input sentence. The part of the information that is implicit in the sentence (tense, voice, and so forth) is made explicit in S 1 . ... certain German verb form into English, it is necessary to un- derstand the German verb form as part of a complex of features of German structure in- cluding possibly other verb forms within t...

Ngày tải lên: 19/02/2014, 19:20

... gestures, in which the form of motion is the principle communicative fea- ture (McNeill, 1992). Non-textual features for topic segmentation Re- search on non-textual features for topic segmenta- tion ... Hirshberg, 1992; Hirschberg and Nakatani, 1998). These studies informed the devel- opment of applications such as segmentation tools for meeting analysis, e.g. (Tur et al., 2001; Galle...

Ngày tải lên: 20/02/2014, 09:20