Báo cáo khoa học: "Spectral Learning of Latent-Variable PCFGs" doc

... good choice of values for ψ and φ for parsing. 9 Proofs This section gives proofs of theorems 1 and 2. Due to space limitations we cannot give full proofs; in- stead we provide proofs of some key ... the conven- tional form of the inside-outside algorithm. The proof is by induction, and is similar to the proof of lemma 2; for reasons of space it is omitted. 9.2 Proof of the Iden...

Ngày tải lên: 23/03/2014, 14:20

... 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 ... rules that describe a non trivial set of entailment cases. The experiments with the data sets of the RTE 2005 challenge show an improvement of 4.4% over the state -of- the-art me...

Ngày tải lên: 20/02/2014, 12:20

... Online Learning of Approximate Dependency Parsing Algorithms Ryan McDonald Fernando Pereira Department of Computer and Information Science University of Pennsylvania Philadelphia, ... parsing algorithm. of dependents have been gathered. T his allows for the collection of pairs of adjacent dependents in a single stage, which allows for the incorporation of second-order scores,...

Ngày tải lên: 22/02/2014, 02:20

... 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 ... im- provement in the efficacy of the SSS algorithm as described in Section 2. It is based on observing that the improvement in the goodness...

Ngày tải lên: 08/03/2014, 01:20

... a set of Arabic documents and an Arabic query, find a list of documents relevant to the query, and rank them by probability of relevance. We used the TREC 2002 documents (several years of AFP ... two examples use the joint 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 pe...

Ngày tải lên: 08/03/2014, 04:22

... McDonald and Fernando Pereira. 2006. Online learning of approximate dependency parsing algo- rithms. In Proceedings of the 11th Conference of the European Chapter of the Association for Com- putational ... dependency parsing. In Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natu- ral Language Processing...

Ngày tải lên: 08/03/2014, 21:20

... Department University of Rochester Rochester, NY 14627 zhanghao@cs.rochester.edu Chris Quirk Microsoft Research One Microsoft Way Redmond, WA 98052 USA chrisq@microsoft.com Robert C. Moore Microsoft Research One ... regimen of 5 it- erations of Model 1, 5 iterations of HMM, and 5 iterations of Model 4. We computed Chinese-to- English and English-to-Chinese word translation ta- bles...

Ngày tải lên: 17/03/2014, 02:20

... the performance of that grammar to that of a heuristically pruned “minimal subset” of it. The latter’s performance was quite good, achiev- ing 90.8% F 1 score 1 on section 23 of the WSJ. This ... Grammar Matt Post and Daniel Gildea Department of Computer Science University of Rochester Rochester, NY 14627 Abstract Tree substitution grammars (TSGs) of- fer many advantages over co...

Ngày tải lên: 17/03/2014, 02:20

... Unsupervised Learning of Dependency Structure for Language Modeling Jianfeng Gao Microsoft Research, Asia 49 Zhichun Road, Haidian District Beijing 100080 China jfgao@microsoft.com Hisami ... the number of pa- rameters of the combined model manageable. To overcome the second obstacle, we used an unsu- pervised learning method that discovers the de- pendency structure of a g...

Ngày tải lên: 17/03/2014, 06:20

... the score of self-BLEU, this is done by both of the process of joint learning and introducing the metric of iBLEU to avoid trivial self-paraphrase. It is not capable with no joint learning or ... not involve joint learning to control the quality of para- phrase results. For joint learning, results of α from 0.7 to 1 are listed. From the results we can see that, when the val...

Ngày tải lên: 23/03/2014, 14:20