Báo cáo khoa học: "Unsupervised Learning of Narrative Schemas and their Participants" potx

Báo cáo khoa học: "Unsupervised Learning of Narrative Schemas and their Participants" potx

Báo cáo khoa học: "Unsupervised Learning of Narrative Schemas and their Participants" potx

... Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, pages 602–610, Suntec, Singapore, 2-7 August 2009. c 2009 ACL and AFNLP Unsupervised Learning of Narrative Schemas and ... scripts (Schank and Abelson, 1977) (structured represen- tations of events, their causal relationships, and their participants) and frames to drive interpre...

Ngày tải lên: 23/03/2014, 16:21

9 335 0
Báo cáo khoa học: "Unsupervised Learning of Narrative Event Chains" pptx

Báo cáo khoa học: "Unsupervised Learning of Narrative Event Chains" pptx

... coherence judgements of real narrative in- stances extracted from documents. Finally, the space of narrative events and temporal orders is clustered and pruned to create discrete sets of narrative chains. 2 ... consti- tute narrative chains. Formally, a narrative chain is a partially ordered set of narrative events that share a common actor. A narrative event is a tu...

Ngày tải lên: 31/03/2014, 00:20

9 450 0
Báo cáo khoa học: "Unsupervised Learning of Dependency Structure for Language Modeling" potx

Báo cáo khoa học: "Unsupervised Learning of Dependency Structure for Language Modeling" potx

... C(w i , w j , R) is the number of times w i and w j have a dependency relation in a sentence in training data, and C(w i , w j ) is the number of times w i and w j are seen in the same ... probability of Equation (11) backs off to the estimate of P(w j |R), which is computed as: N RwC RwP j j ),( )|( = , (14) where N is the total number of dependencies in training...

Ngày tải lên: 17/03/2014, 06:20

8 380 0
Báo cáo khoa học: "Unsupervised Learning of Acoustic Sub-word Units" pot

Báo cáo khoa học: "Unsupervised Learning of Acoustic Sub-word Units" pot

... France emmanuel.dupoux@gmail.com Abstract Accurate unsupervised learning of phonemes of a language directly from speech is demon- strated via an algorithm for joint unsupervised learning of the topology and parameters of a hidden Markov ... µ s 4 and µ s 2 = µ s +δ = µ s 3 , with δ = λ ∗ v ∗ , where λ ∗ and v ∗ are the principal eigenvalue and eigen- vector of Σ s and...

Ngày tải lên: 08/03/2014, 01:20

4 295 0
Báo cáo khoa học: "Unsupervised Learning of Arabic Stemming using a Parallel Corpus" pot

Báo cáo khoa học: "Unsupervised Learning of Arabic Stemming using a Parallel Corpus" pot

... reliable and are a very important part of the information extracted from the parallel corpus. Therefore, the score of a candidate stem should be based on the score of the corresponding prefix and the ... probability of the prefix and suffix, with a smoothing back-off (the product of the individual probabilities). Scor- ing models of this form proved to be poor perform- ers from...

Ngày tải lên: 08/03/2014, 04:22

8 424 0
Báo cáo khoa học: "Unsupervised Learning of Semantic Relation Composition" ppt

Báo cáo khoa học: "Unsupervised Learning of Semantic Relation Composition" ppt

... Huhns and Stephens (1989). Their relations are not linguistically motivated and ten of them map to some sort of PART-WHOLE (e.g. PIECE- OF, SUBREGION -OF) . Unlike (Cohen and Losielle, 1988; Huhns and ... deep characteristics of relations. They are independently determinable for each relation and specify a property between an el- ement of the domain and an element of...

Ngày tải lên: 23/03/2014, 16:20

10 293 0
Báo cáo khoa học: "Unsupervised Learning of Field Segmentation Models for Information Extraction" pot

Báo cáo khoa học: "Unsupervised Learning of Field Segmentation Models for Information Extraction" pot

... title, and date. Classified advertise- ments, such as the one in Figure 1(b), also exhibit field structure, if less rigidly: an ad consists of de- scriptions of attributes of an item or offer, and ... range of linguistic phe- nomena in text, including morphology, parts -of- speech (POS), named entity mentions, and even topic changes in discourse. An HMM consists of a set of s...

Ngày tải lên: 23/03/2014, 19:20

8 343 0
Tài liệu Báo cáo khoa học: "Automatic learning of textual entailments with cross-pair similarities" ppt

Tài liệu Báo cáo khoa học: "Automatic learning of textual entailments with cross-pair similarities" ppt

... ex- amples of the previous section. From the point of view of bag -of- word methods, the pairs (T 1 , H 1 ) and (T 1 , H 2 ) have both the same intra-pair simi- larity since the sentences of T 1 and H 1 as ... by their bold subtrees. These are more similar to the subtrees of T 1 and H 1 than those of T 1 and H 2 , respectively. Indeed, H 1 and H 3 share the pro- ductio...

Ngày tải lên: 20/02/2014, 12:20

8 413 0
Tài liệu Báo cáo khoa học: "Unsupervised Segmentation of Chinese Text by Use of Branching Entropy" pdf

Tài liệu Báo cáo khoa học: "Unsupervised Segmentation of Chinese Text by Use of Branching Entropy" pdf

... Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions, pages 428–435, Sydney, July 2006. c 2006 ... Computational Linguistics 428 0.5 1 1.5 2 2.5 3 3.5 4 4.5 5 1 2 3 4 5 6 7 8 entropy offset 429 430 431 432 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 0.55 0.6 0.65 0.7 0.75

Ngày tải lên: 20/02/2014, 12:20

8 395 0
Tài liệu Báo cáo khoa học: "Online Learning of Approximate Dependency Parsing Algorithms" potx

Tài liệu Báo cáo khoa học: "Online Learning of Approximate Dependency Parsing Algorithms" potx

... Online Learning of Approximate Dependency Parsing Algorithms Ryan McDonald Fernando Pereira Department of Computer and Information Science University of Pennsylvania Philadelphia, ... incorporate all of their features as well as the new second-order features we now describe. The old first-order features are built from the parent and child words, their POS tags, and the POS...

Ngày tải lên: 22/02/2014, 02:20

8 415 0
w