Báo cáo khoa học: Colored Pr¨ufer codes for k-edge colored trees pptx

... Association for Computational Linguistics, pages 620–631, Portland, Oregon, June 19-24, 2011. c 2011 Association for Computational Linguistics Incremental Syntactic Language Models for Phrase-based ... sen- tences in a similar left-to-right fashion, and are therefore a good mechanism for incorporat- ing syntax into phrase-based translation. We give a formal definition of one such line...

Ngày tải lên: 20/02/2014, 04:20

... bet- ter than CRF (the structured model) not only for time cost but also for the performance on our ex- periment 4 . This result shows that local informa- tion provides the fundamental decision clues. ... exploit non-local information in the next section. 3 Incorporating Non-local Information 3.1 Using Trigger Features To exploit non-local information to sequential la- beling for a stat...

Ngày tải lên: 20/02/2014, 12:20

... NIST LRE database, we choose it as the platform of comparison. In Table 4, we report the perform- ance across different approaches in terms of error rate for a quick comparison. MMC presents a ... t4(t3,#) to account for left and right contexts. The # sign is a place holder for free context. In the interest of manageability, we propose to use up to token trigram. In this way, fo...

Ngày tải lên: 20/02/2014, 15:20

... posterior probability) for each word in the lattice. A simple dynamic programming algorithm which is a variation on the standard forward-backward al- gorithm can be employed for performing this com- putation. ... index size for various pruning thresholds applied to the lat PSPL. MAP performance increases with PSPL depth, as expected. A good compromise between accuracy and index size is...

Ngày tải lên: 20/02/2014, 15:20

... average precision for all the pruned topic types is 74.64%, varying from 95.63% for ROOM to 37.63% for MIx. If MIx is left out, the average precision is 79.27%. The poor precision for MIX is due ... vector. For each topic type ti, add up the amounts of mutual information rni(wj;ti) by which it is supported by the words wj, and rank the topic types in the descending order of...

Ngày tải lên: 20/02/2014, 18:20

... number. • For verbs, generated forms had to match the original form for tense and negation. • For adjectives, generated forms had to match the original form for degree of comparison and negation. • For ... The forms pro- duced by the tool from the lemma of an observed in- flected word form were subjected to several restric- tions: • For nouns, generated forms had to match the origi...

Ngày tải lên: 07/03/2014, 22:20

... POS tag information with the existing ANLT lexical re- sources. Our view is that POS tag information for content words (nouns, verbs, adjectives, adverbs) is usually reliable and informative, ... tag infor- mation with lexical entries preserves all informa- tion in the lexical entries, including inflectional and subcategorisation information. The preserva- tion of subcategorisation informati...

Ngày tải lên: 08/03/2014, 05:20

... perform much worse on dev and test1 that are close to training data, but better on NIST standard test2. We ob- serve half BLEU point improvement for optimiza- tion method but marginal gain for ... DARPA TransTac program for funding and the anonymous reviewers for their constructive suggestions. References N. F. Ayan. 2005. Combining Linguistic and Machine Learn- ing Techniques for W...

Ngày tải lên: 17/03/2014, 02:20

... proposed, for example, the relations permutation and sequence union to constrain word sequences in his HPSG fragment for German. A different motivation for extending the constraint language for ... is the rule for vertical infixation for fractions, used in a grammar of mathematical nota- tion. Let us consider now what the feature structure for an active chart-parsing edg...

Ngày tải lên: 17/03/2014, 09:20

... 2012. c 2012 Association for Computational Linguistics Hierarchical Bayesian Language Modelling for the Linguistically Informed Jan A. Botha Department of Computer Science University of Oxford, UK jan.botha@cs.ox.ac.uk Abstract In ... items from M combine to form the observed surface words: G u . . . (as before, except G 0 =Uniform(|M|)) H u ∼ P Y (d |u| , θ |u| , G u × F ) ˜w ∼ H u So t...

Ngày tải lên: 24/03/2014, 03:20