Báo cáo khoa học: "Correcting Automatic Translations through Collaborations between MT and Monolingual Target-Language Users" pptx

... Computational Linguistics Correcting Automatic Translations through Collaborations between MT and Monolingual Target-Language Users Joshua S. Albrecht and Rebecca Hwa and G. Elisabeta Marai Department ... collabora- tive approach for mediating between an MT system and users who do not under- stand the source language and thus cannot easily detect translation mist...

Ngày tải lên: 31/03/2014, 20:20

... and corpora in the agricultural domain and AFIRST for supporting this research through the SKETCHI project. a part-of-speech tagger for French described in (Tzoukermann and Radev, 1997) and ... indexes i and j and their syntactic heads H(i) and H(j): Definition 3.1 (Index priority) Let i and j be two indexes in the same sentence. The rela- tive priority ranking of...

Ngày tải lên: 31/03/2014, 04:20

... al., 1993), employs word-alignment algorithm (such as GIZA++ (Och and Ney, 2003)) that pro- vides local associations between source and target words. The source-to-target word alignments are sometimes ... al., 1998; Yamada and Knight, 2001; Chiang, 2005) and the string transduction models (Kanthak et al., 2005). In this paper, we present an alternate approach to lexical selection a...

Ngày tải lên: 17/03/2014, 04:20

...   S 1 (i) and S 2 (i) are indices of the i th matched word in sentences S 1 and S 2 respectively and n is the number of matched words between the sentences S 1 and S 2 . Let = ... and semantic features to pursue this goal, and the details are discussed below. 3.2.1 Ngram Matching (NM) One straightforward measure is to exploit the n- gram similarity betw...

Ngày tải lên: 23/03/2014, 14:20

... sentences) and produce the final answer accordingly, e.g.: — System: Roald Dahl wrote many books for kids and adults, including: “The Witches”, “Charlie and the Chocolate Fac- tory”, and “James and the ... al., 2001) and SiteIF (Magnini and Strapparava, 2001) news recommender systems where age and browsing history, respectively, are part of the UM. In this paper we focus on how...

Ngày tải lên: 17/03/2014, 22:20

... amino acid differences between mesophilic and thermophilic phosphoribosyl diphosphate synthase Bjarne Hove-Jensen 1 and James N. McGuire 2 1 Department of Biological Chemistry and 2 Center for Enzyme ... Mg 2+ . ADP and GDP inhibit the B. caldo- lyticus enzyme in a cooperative fashion with Hill coefficients of 2.9 for ADP and 2.6 for GDP. K i values are determined as 113 and 490 l...

Ngày tải lên: 23/03/2014, 13:20

... methods: the perceptron algorithm, and a method based on conditional random fields (CRFs). The models are encoded as determin- istic weighted finite state automata, and are applied by intersecting ... parame- ter has on the error rate, and then modifies the parameters to reduce the error rate based on this prediction. 2 Linear Models, the Perceptron Algorithm, and Conditional Random Fiel...

Ngày tải lên: 23/03/2014, 19:20

... the best candidate for ASR adaptation or training (Riccardi and Hakkani-Tur, 2005; Huo and Li, 2007). 1 Even with all of these, however, there remains a significant gap between this WER and the ... Meeting of the ACL and the 4th IJCNLP of the AFNLP, pages 764–772, Suntec, Singapore, 2-7 August 2009. c 2009 ACL and AFNLP Improving Automatic Speech Recognition for Lectures throug...

Ngày tải lên: 20/02/2014, 07:20

... “employer”, creates and uploads new HITs and rewards the workers. Requesters can upload simple HITs through the MTurk Re- quester web site, and more complicated ones through the MTurk Web Service ... insight, resources and motivation for further research and projects using similar collection methods. We collected our corpus through Amazon Mechanical Turk service 4 (MTurk). The...

Ngày tải lên: 20/02/2014, 09:20

... least in part (e.g., means). There is no difference between capital let- ters and small letters in Chinese, and no difference between singular and plural forms of the same term. This also led ... text2, this part would be segmented between two anchor points (i, j) and (u, v). We know point i is matched to point j, and point u to point v, the texts between these two poi...

Ngày tải lên: 20/02/2014, 22:20