Báo cáo khoa học: "Bilingual Co-Training for Monolingual Hyponymy-Relation Acquisition" pdf

... fact that the information encoded for these does not cover very specific syntactic contexts as those found in technical texts— make high informative grammars not suitable for real applications. ... be more informative for real parsing than a general corpus. 1 Introduction The coverage of the computational lexicon used in deep Natural Language Processing (NLP) is crucial for p...

Ngày tải lên: 23/03/2014, 19:20

... for training without performing any bootstrapping. Further, it consis- tently performs better than monolingual bootstrap- ping. A simple and intuitive explanation for this is as follows. In monolingual ... for both the lan- guages in both the domains. Further, bilingual boot- strapping also does better than monolingual boot- strapping for small seed sizes. As explained earlier,...

Ngày tải lên: 30/03/2014, 21:20

... of the Association for Computational Linguistics, pages 316–324, Uppsala, Sweden, 11-16 July 2010. c 2010 Association for Computational Linguistics Discriminative Pruning for Discriminative ... ITG. For instance, there are two parses for three consecutive word pairs, viz. [/ [/ / ] ] and [[/ /] /] . The problem of re- dundancy is fixed by adopting ITG normal for...

Ngày tải lên: 20/02/2014, 04:20

... applications. Grishman (1995) and Hobbs et al. (1995) use phrasal information in information extraction. Alshawi (1996) uses dependency information in a machine translation system. The need to impose ... supertagging may be employed in informa- tion retrieval. Furthermore, given a sentence aligned parallel corpus of two languages and al- most parse information for the sentences of on...

Ngày tải lên: 08/03/2014, 21:20

... only limited and local context information for learning and prediction, they often fail to en- force simple yet important global linguistic con- straints that exist for most languages, e. g. that there ... grandmother’s head node • the case features for noun phrases • the category for PP objects • the lemma for PP objects (if terminal node) These features are also computed for the...

Ngày tải lên: 17/03/2014, 00:20

... infor- mation tuned to genres and sublanguages. Such resources are critical for natural language process- ing (NLP), both for enhancing the performance of state-of-art statistical systems and for ... which easy[8] occurs as a complement. The first (PP)-complement is for us, as indicated by ncmod (for[ 9] easy[8] we+[10]), with for as PFORM and we+ (us) as NP. The sec- ond complement...

Ngày tải lên: 17/03/2014, 04:20

... succinct and gener- alizable evidence than measuring the distributions for each of the inflected forms. If part-of-speech informa- tion is available in a lexicon, it is useful to compute the 4The ... tagger for Spanish would be quite costly (and require special tagged corpora). The current approach uses just the information avail- able in dictionaries, exploiting only that which is...

Ngày tải lên: 17/03/2014, 09:20

... bilingual co-training improved the per- formance of monolingual hyponymy-relation ac- quisition about 3.6–10.3% in the F-measure. Bilingual co-training also enables us to build clas- sifiers for two ... framework called bilingual co-training for a large- scale, accurate acquisition method for monolingual semantic knowledge. In this framework, we combine the indepen- dent proc...

Ngày tải lên: 08/03/2014, 00:20

... co-occurrence counts of the two units. Therefore, questions emerge: how good is the sense similarity computed via VSM for two units from parallel corpora? Is it useful for multi- lingual applications, ... (WSD) techniques in SMT for translation selection. However, WSD techniques for SMT do so indirectly, using source-side context to help select a particular translation for a so...

Ngày tải lên: 20/02/2014, 04:20

... are two parameters for the dis- tortion probability: one for head words and the other for non-head words. Distortion Probability for Head Words The distortion probability for head words represents ... only be used for very similar language pairs. In this paper, besides the limited resources for the given language pair, we make use of large amounts of resources available...

Ngày tải lên: 20/02/2014, 12:20