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

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

... querylogs. 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 resource in the world now. The terms in the ... uses the knowledge of both the Web and WordNet to expand the original query.This is done by first using the original query tosearch the web for top N,„ documents and extract-ing additional web ... documents retrieved from the Web are likely to be similar or even the sameas those in the QA corpus since they both containinformation about the facts of nature or the fac-tual events in the...

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

... towin the title?has the following wrong answer:WA: He saw Ingemar Johanson knock downFloyd Patterson seven times there in winning the heavyweight title.Although the above sentence contains the ... propagation. The arguments in the syntactic pattern instance of the destination synset take their values from the arguments with the same thematic roles from the syntactic pattern instance of the start ... began life in 1982 The verb establish in the question has sense 2 in WordNet 2.0 and the verb begin in the answer901has also sense 2. The following lexical chain canbe found between these two...

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

... the middle of the answer wordsequence;O: if the word is not in the answer word sequence;B: if the word is the start word of the answer wordsequence. The class labeling system in our experiment ... anyQA dataset. Beyond this main goal, as a reference, The Appendix shows our experimental results clas-siﬁed into question types without using them in the training phase. The results of automatic ... that contain the answers. Each ques-tion is categorized as one of 115 hierarchicallyclassiﬁed question types. The document set is used not only in the trainingphase but also in the execution...

Báo cáo khoa học: "Searching for Topics in a Large Collection of Texts" doc

... Our intention is to employ thesevirtual concepts in document indexing. In this paper we show some preliminaryexperimental results and discuss direc-tions of future work.1 Introduction In the ... to reduce the high dimension-ality of the vectors in order to improve the effec-tivity of retrieving. The most famous is probably the method called Latent Semantic Indexing (LSI),introduced ... byadding or taking away one documentinto/from it;2. since the quality of modiﬁed cuts cannot in- crease in nitely, a ﬁnite necessarilyexists so that is locally optimal and con-sequently the...

Tài liệu Báo cáo khoa học: "Semi-Supervised Learning of Partial Cognates using Bilingual Bootstrapping" doc

... contained the partial cognate. The same approach was used for the MB on the Eng-lish side only this time we were using the English side of the training seeds for training the classi-fier and the ... taken into account as features. Leaving them in would mean to indicate the classes, when applying the methods for the English sentences since all the sentences with the cognate sense contain the ... used the bag-of-words (BOW) ap-proach of modeling context, with binary values for the features. The features were words from the training corpus that appeared at least 3 times in the training...

Tài liệu Báo cáo khoa học: "Discovering asymmetric entailment relations between verbs using selectional preferences" doc

... excludes the Pnompattern (61%), the improvement in the AROC is of 5% and 3%.Moreover, the shape of the nom + hb + pe ROCcurve in Fig. 1.(a) is above all the other in all the points. In the second ... vh(x) of the noun playing thelogical sub-ject role. The action vhwill be the one entailed by the verb vtheading the sentence. As an example in the sentence the player wins”, the action ... of the different methods in detecting verb entailment. We experiment with the method by itself or in combination with othersets of patterns. We are then interested only in verb pairs where the...

Báo cáo khoa học: "Sentence Dependency Tagging in Online Question Answering Forums" pdf

... Structure of Linear-chain CRFs.Linear-chain CRF is a special case of the generalCRFs. In linear-chain CRF, cliques only involve twoadjacent variables in the sequence. Figure 3 shows the graphical ... disjoint sets, and run a three-foldcross validation. Within each fold, ﬁrst sentencetypes are labeled using linear-chain CRFs, then the 559resulting sentence type tagging is used in the sec-ond ... calculatedaccordingly.5.1 Sentence Type Tagging Results The results of sentence type tagging using linear-chain CRFs are shown in Table 5. For a comparison,we include results using a basic ﬁrst-order...

Tài liệu Báo cáo khoa học: "Mining metalinguistic activity in corpora to create lexical resources using Information Extraction techniques: the MOP system" doc

... Mining metalinguistic activity in corpora to create lexical resources using Information Extraction techniques: the MOP system Carlos Rodríguez Penagos Language Engineering Group, Engineering ... that they ingest oxygen from the air via fine hollow tubes, known as tracheae, in which the term trachea is linked to the description fine hollow tubes in the context of a globally non-metalinguistic ... objects in the mind or in the physical world. The two are isomorphic and this ac-counts for reflexivity, the property of referring to itself, as when linguistic items are mentioned instead of being...

Tài liệu Báo cáo khoa học: "MACHINE-READABLE COMPONENTS IN A VARIETY OF INFORMATION-SYSTEM APPLICATIONS" potx

...

Tài liệu Báo cáo khoa học: "Domain-transcending mappings in a system for metaphorical reasoning" docx

... cause-to-existpropositions in the target domain. The mapping in THEORY AS HOME combined with the Event-Shape VNMA can create the target-domain proposition that the people came to es-pouse the theories corresponding ... use The mental/emotional states VNMA allows the mapping of the excitement in Lakoff' s example(1, above) from the source to the target domain.Since the agents in the source domain (the ... physicallylocated in (the main part of) that space.Thus, if the idea is physically located in the far-reaches of the mind-space, whilst the con-scious self of Anne is located in the main part of the mind-space,...

Xem thêm