Báo cáo khoa học: "Semi-Supervised Training for Statistical Word Alignment" docx

... self training wsj self training brown self training 0 500 1000 1500 2000 20 40 60 80 100 number of manually annotated sentences recall no self training wsj self training brown self training 0 ... self training wsj self training brown self training 0 500 1000 1500 2000 20 30 40 50 60 70 80 number of manually annotated sentences recall no self training wsj self training brown...

Ngày tải lên: 23/03/2014, 18:20

... discriminative training with EM and are therefore performing semi-supervised training. We show that semi-supervised training leads to better word alignments than running unsu- pervised training followed ... parameters used in generating Foreign words which are unaligned 11 backoff fertility for words with count <= 5 4 d 1 (j) movement probs of leftmost Foreign word translated...

Ngày tải lên: 31/03/2014, 01:20

... the Association for Computational Linguistics:shortpapers, pages 294–298, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics Corpus Expansion for Statistical Machine ... B. words in any other semantic role constituent of the same frame. • The phrase on side B must not contain words that link to words not in the phrase on side A. • Both of the two bou...

Ngày tải lên: 20/02/2014, 04:20

... June 2008. c 2008 Association for Computational Linguistics Self -Training for Biomedical Parsing David McClosky and Eugene Charniak Brown Laboratory for Linguistic Information Processing (BLLIP) Brown ... detail how self- training improved the parser. We conclude in section five. 2 Previous Work While self -training has worked in several do- mains, the early results on self -traini...

Ngày tải lên: 20/02/2014, 09:20

... (2004). Statistical machine translation with scarce resources using morpho-syntactic information. Computational Linguistics, 30(2):181–204. Och, F. J. (2003). Minimum error rate training in statistical machine ... smorgasbord of features for statistical machine translation. In Proceedings of HLT- NAACL 2004. Och, F. J., Tillmann, C., and Ney, H. (1999). Improved align- ment models...

Ngày tải lên: 20/02/2014, 15:20

... performance end end average_performance and keep average_performance end B = best average_performance bestFeatures  B ∪ bestFeatures end Figure 2. Implemented algorithm for forward ... and 140 for the test set (used to measure the performance). The training set is randomly divided into two sets in each iteration of the algorithm: One for training and the other...

Ngày tải lên: 20/02/2014, 16:20

... method for measuring word order similarity (or differences) be- tween any given language pair. This method is based on word- alignments and the BLEU metric. We assume that we have word- alignments for ... are for Arabic-English machine translation of news stories. We also present a novel method for measuring word order similarity (or differences) between any given pair of langua...

Ngày tải lên: 08/03/2014, 02:21

... alternative to the full re -training 26 Algorithm 1 Transductive learning algorithm for statistical machine translation 1: Input: training set L of parallel sentence pairs. // Bilingual training data. 2: ... bilingual training data. 5: i := 0. // Iteration counter. 6: repeat 7: Training step: π (i) := Estimate(L, T i−1 ). 8: X i := {}. // The set of generated translations for t...

Ngày tải lên: 08/03/2014, 02:21

... clump. A headword language model uses two unigram models, a headword model and a non-headword model. Each clump is required to have a headword. All other words are non-headwords. The identity ... number of words in q is denoted by g(ci), cl begins at the first word in the sentence, and ct(c) ends at the last word in the sentence. The clumps form a proper partition of E. All the...

Ngày tải lên: 08/03/2014, 21:20

... ap- proximating Viterbi training for PCFGs is NP-hard. We motivate the use of uniform- at-random initialization for Viterbi EM as an optimal initializer in absence of further information about the ... Meeting of the Association for Computational Linguistics, pages 1502–1511, Uppsala, Sweden, 11-16 July 2010. c 2010 Association for Computational Linguistics Viterbi Training for...

Ngày tải lên: 17/03/2014, 00:20