Báo cáo khoa học: "Improving Machine Translation of Null Sub

Báo cáo khoa học: "Improving Machine Translation of Null Subjects in Italian and Spanish" pot

... pairs, and includes a 3- gram language model. Tables 3 and 4 show percentages of correct, in- correct and missing translations of personal and impersonal null subjects calculated on the basis of the ... 2: Null- subjects in our corpus compared to Live Memories and AnCora-Co corpora. Percentages are calculated with respect to the total number of words. 3 Baseline...

Ngày tải lên : 24/03/2014, 03:20

9
508
0

Báo cáo khoa học: "Statistical Machine Translation for Query Expansion in Answer Retrieval" pptx

... SMT training pipeline. This training procedure includes various standard procedures such as preprocessing, sentence and chunk alignment, word alignment, and phrase extraction. The goal of question-answer ... 2006) in a 10-fold cross validation setup. Training was done using 20 feature functions on occurrences question marks and key words in different ﬁelds of web pages, and re...

Ngày tải lên : 08/03/2014, 02:21

8
392
0

Tài liệu Báo cáo khoa học: "Exploring the Use of Linguistic Features in Domain and Genre Classification" potx

... class of the majority of the items which reached it during training. The trees were grown using recursive partitioning; the splitting criterion was reduction in deviance. Using the Gini index ... work. Seman- tic classes were not examined, because defining, building, fine-tuning, and maintaining such word lists can be an arduous task (cf. e.g. (Klavans and Kan, 1998)), which...

Ngày tải lên : 22/02/2014, 03:20

8
689
1

Báo cáo khoa học: "A Computational Model of Text Reuse in Ancient Literary Texts" potx

... preceding pericope or to the beginning of the following one. 5.3 Test Results The two models trained in §5.2, B and J, are intended to capture the characteristics of text reuse in L train according to two different ... §5.2 describes the training process, which uses text-reuse hypotheses of two different re- searchers (L train.B and L train.J ) on the same training text. The t...

Ngày tải lên : 08/03/2014, 02:21

8
536
0

Báo cáo khoa học: "A Uniform Treatment of Pragmatic Inferences in Simple and Complex Utterances and Sequences of Utterances" pot

... type of indefeasible information and two types of defeasible information, namely, infelicitously defeasible and felicitously defeasible. The notion of infelicitously defeasible information ... 1. Most linguistic approaches account for the de- feasibility of pragmatic inferences by analyzing them in a context that consists of all or some of the pre- vious utterance...

Ngày tải lên : 08/03/2014, 07:20

7
418
1

Báo cáo khoa học: Hydrogen independent expression of hupSL genes in Thiocapsa roseopersicina BBS pot

... ⁄ HoxJ kinase in vitro [4]. The role of the N-terminal part of the kinase, containing a PAS domain, was established in signal transduction between the RH and the kinase [6,7]. Addition of H 2 to ... single point mutation in the helix–turn–helix DNA binding motif of PpsR, rendering it inactive [26]. Comparison of HupSL regulations and the functional roles of HupTUV in o...

Ngày tải lên : 16/03/2014, 23:20

10
551
0

Báo cáo khoa học: "Improving Pronoun Translation for Statistical Machine Translation" docx

... Philipp Koehn, Christof Monz and Omar Zaidan. 2011. Findings of the 2011 Workshop on Statistical Machine Translation. In Proceedings of the Sixth Workshop on Statistical Machine Translation, pages ... Sung-Kwon Choi and Randall Sharp. 1995. Anaphora Resolution in Machine Transla- tion. In Proceedings of the Sixth International Con- ference on Theoretical and Methodol...

Ngày tải lên : 17/03/2014, 22:20

10
347
0

Báo cáo khoa học: "DEALING WITH INCOMPLETENESS OF LINGUISTIC KNOWLEDGE IN LANGUAGE TRANSLATION TRANSFER AND GENERATION STAGE OF MU MACHINE TRANSLATION PROJECT" potx

... DEALING WITH INCOMPLETENESS OF LINGUISTIC KNOWLEDGE IN LANGUAGE TRANSLATION TRANSFER AND GENERATION STAGE OF MU MACHINE TRANSLATION PROJECT Makoto Nagao, Toyoaki Nishida and Jun-ichi ... uncertainty of knowledge we have for machine translation. Especially at the transfer stage of machine translation, the selection of target language expression is rather subjec...

Ngày tải lên : 31/03/2014, 17:20

8
326
0

Tài liệu Báo cáo khoa học: "Modeling the Translation of Predicate-Argument Structure for SMT" ppt

... (see details in Section 6.1) in our word-aligned bilingual training data. Then we extract all training events for verbal predicates which occur at least 10 times in the training data. A training event ... right. ing, we run the training toolkit in a parallel manner. 4 Argument Reordering Model In this section we introduce the discriminative argument reordering model, features and...

Ngày tải lên : 19/02/2014, 19:20

10
561
0

Tài liệu Báo cáo khoa học: "Robust Machine Translation Evaluation with Entailment Features∗" pptx

... Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, pages 297–305, Suntec, Singapore, 2-7 August 2009. c 2009 ACL and AFNLP Robust Machine Translation Evaluation ... on development and test sets. We are currently investi- gating caching and optimizations that will enable the use of our metric for MT parameter tuning in a Minimum Error Rate...

Ngày tải lên : 20/02/2014, 07:20

9
467
0