Báo cáo khoa học: "Joint Annotation of Search Queries" docx

Báo cáo khoa học: "Joint Annotation of Search Queries" docx

Báo cáo khoa học: "Joint Annotation of Search Queries" docx

... Linguistics Joint Annotation of Search Queries Michael Bendersky Dept. of Computer Science University of Massachusetts Amherst, MA bemike@cs.umass.edu W. Bruce Croft Dept. of Computer Science University of ... information retrieval. In Proc. of SIGIR, pages 810–811. Michael Bendersky, W. Bruce Croft, and David A. Smith. 2010. Structural annotation of search queries using...

Ngày tải lên: 30/03/2014, 21:20

10 342 0
Báo cáo khoa học: "Joint Inference of Named Entity Recognition and Normalization for Tweets" doc

Báo cáo khoa học: "Joint Inference of Named Entity Recognition and Normalization for Tweets" doc

... China † Microsoft Research Asia Beijing, 100190, China † {xiaoliu, fuwei, mingzhou}@microsoft.com § zhongyang.fu@gmail.com ♯ v-xzho@microsoft.com Abstract Tweets represent a critical source of fresh ... Here is an example of a tweet: “my- craftingworld: #Win Microsoft Of ce 2010 Home and Student #Contest from @of ce http://bit.ly/ ··· ”, where “mycraftingworld” is the name of the user...

Ngày tải lên: 07/03/2014, 18:20

10 444 0
Báo cáo khoa học: "Joint Satisfaction of Syntactic and Pragmatic Constraints Improves Incremental Spoken Language Understanding" doc

Báo cáo khoa học: "Joint Satisfaction of Syntactic and Pragmatic Constraints Improves Incremental Spoken Language Understanding" doc

... structure building has been previously explored by a number of authors. Stoness et al. (2004, 2005) describe a proof -of- concept imple- 514 mentation of a “continuous understanding” mod- ule that uses ... S!] TagIU $TopOfTags TextualWordIU nimm TextualWordIU den TextualWordIU winkel TextualWordIU in TextualWordIU $TopOfWords Figure 1: An example network of incremental units, including...

Ngày tải lên: 17/03/2014, 22:20

10 361 0
Báo cáo khoa học: "Joint Evaluation of Morphological Segmentation and Syntactic Parsing" pptx

Báo cáo khoa học: "Joint Evaluation of Morphological Segmentation and Syntactic Parsing" pptx

... , w n of space- delimited words from a set W. We assume a lexicon LEX, distinct from W, containing pairs of segments drawn from a set T of terminals and PoS categories drawn from a set N of nonterminals. LEX ... Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, pages 6–10, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association ... ass...

Ngày tải lên: 23/03/2014, 14:20

5 297 0
Báo cáo khoa học: "Joint Learning of a Dual SMT System for Paraphrase Generation" pptx

Báo cáo khoa học: "Joint Learning of a Dual SMT System for Paraphrase Generation" pptx

... Learning of a Dual SMT System for Paraphrase Generation Hong Sun ∗ School of Computer Science and Technology Tianjin University kaspersky@tju.edu.cn Ming Zhou Microsoft Research Asia mingzhou@microsoft.com Abstract SMT ... control the self-paraphrase rate and lower down the score of self-BLEU, this is done by both of the process of joint learning and introducing the metric of iBLE...

Ngày tải lên: 23/03/2014, 14:20

5 347 0
Báo cáo khoa học: "Joint Training of Dependency Parsing Filters through Latent Support Vector Machines" pptx

Báo cáo khoa học: "Joint Training of Dependency Parsing Filters through Latent Support Vector Machines" pptx

... state of the art We directly compare our filters to those of Bergsma and Cherry (2010) in terms of both intrinsic fil- ter quality and impact on the MST parser. The B&C system consists of three ... effect. The performance of Joint-P2+MST-2 is compa- rable to the system of Huang and Sagae (2010), who report a parsing speed of 25 sentences per second and an accuracy of 92.1 on...

Ngày tải lên: 23/03/2014, 16:20

6 325 0
Báo cáo khoa học: "Towards resolution of bridging descriptions" docx

Báo cáo khoa học: "Towards resolution of bridging descriptions" docx

... Background As part of our research on definite description (DD) interpretation, we asked 3 subjects to classify the uses of DDs in a corpus using a taxonomy related to the proposals of (Hawkins, ... idiosyncratic encoding, it is often 522 necessary to look for a semantic relation between sisters, i.e. hyponyms of the same hypernym, such as home the house. An automatic search...

Ngày tải lên: 08/03/2014, 21:20

3 260 0
Báo cáo khoa học: "Semantic Transliteration of Personal Names" docx

Báo cáo khoa học: "Semantic Transliteration of Personal Names" docx

... decision of gender had led to deterioration in MRR performance of the male names compared to the case where no prior information was assumed. Soft decision of gender yielded further gains of 17.1% ... the C-C corpus, out of the total of 4,507 characters, only 776 of them are for surnames. It is interesting to find that female given names are represented by a smaller set...

Ngày tải lên: 17/03/2014, 04:20

8 205 0
Báo cáo khoa học: "Unsupervised Discovery of Persian Morphemes" docx

Báo cáo khoa học: "Unsupervised Discovery of Persian Morphemes" docx

... is the left part of word, RP is the right part of it, Len (p) is the length of part P (number of characters), freq(p) is the frequency of part P in corpus, WN is the number of words (corpus ... length of the optimal com- pression of the corpus, when we use the prob- abilistic model to compress the data. The length of the optimal compression of the corpus is the base 2...

Ngày tải lên: 17/03/2014, 22:20

4 357 0
Báo cáo khoa học: Structural properties of semenogelin I docx

Báo cáo khoa học: Structural properties of semenogelin I docx

... the presence of 7.4 m urea indicates that the fluorescence of the Trp residue was quenched (e.g. by a charged Fig. 2. Far-UV CD spectra of SgI in buffer containing urea at concentrations of 0.2 M (j), ... and a temperature of 37 °C. Only results corresponding to a voltage below 600 mV are shown. Table 1. Prediction of the secondary structure of SgI by computer- based analysis of...

Ngày tải lên: 23/03/2014, 07:20

8 263 0
Từ khóa:
w