Báo cáo khoa học: "Combining Multiple, Large-Scale Resources in a Reusable Lexicon for Natural Language Generation" pptx

... accuracy; corpus analysis based information is also linked with information from static resources. By these measures, we are able to acquire an accurate, reusable, rich, and large-scale lexicon ... manually formatted the alternate pat- terns in each alternation in COMLEX format. 608 The reason to choose manual formatting rather than automating the process is to guarantee the...

Ngày tải lên: 31/03/2014, 04:20

... training data are comparatively smaller than WAQ and WAQA, they however yield comparable results. The linear combination of datasets (WAQ+WAQA+LSR Lin ) yields statistically significant performance ... the availability of suitable training data for the translation probabilities. Berger and Laf- ferty (1999) initially built synthetic training data consisting of queries automatically generated...

Ngày tải lên: 20/02/2014, 07:20

... cialize a given source grammar to a specific domain. In that case, EBL is used as a method for adapting a general grammar and/or parser to the sub -language defined by a suitable training ... of paraphrases. In this paper, we present a novel method for the automatic extraction of subgrammars for the control and speeding-up of natural language generation. Its...

Ngày tải lên: 08/03/2014, 21:20

... all possible target sentences: argmax { Pr (ej e i fi' )  (1) The objective of natural language understanding (NLU) is to extract all the information from a nat- ural language based input which are ... the same training proce- dure as for the automatic translation of natural lan- guages. When rewriting the translation probabil- ity Pr(fi J 4) by introducing a 'hid...

Ngày tải lên: 31/03/2014, 20:20

... Introduction Paraphrases are alternative ways of conveying the same meaning. Paraphrases are important in many natural language processing (NLP) applications, such as machine translation (MT), question an- swering ... sparseness. Kauchak and Barzilay (2006) used paraphrases of the reference translations to improve automatic MT evaluation. In QA, Lin and Pantel (2001) and Ravichandran...

Ngày tải lên: 17/03/2014, 02:20

... story and paragraph breaks) in conversational speech, dialogue segmentation is useful in many spoken language understanding tasks, including anaphora resolution (Grosz and Sid- ner, 1986), information ... obtained using standard technol- ogy including HMM based acoustic modeling and N-gram based language models (Hain et al., 2005). The average word error rates (WER) are 39.1%. We also...

Ngày tải lên: 23/03/2014, 18:20

... coenzyme analog lacking the ade- nine ring in the upper axial ligand; a model of damaged cofactors) for free adeninylpentylcobalamin (AdePeCbl) (an inactive coenzyme analog containing the adenine ring ... glycerol dehydratase-reactivating factor reactivates the inacti- vated hologlycerol dehydratase in a similar manner. Both dehydratase-reactivating factors exist as a 2 b 2 hetero...

Ngày tải lên: 15/02/2014, 01:20

... evaluate various methods for combining translation tables. 2 Baselines The natural baseline for model adaption is to con- catenate the IN and OUT data into a single paral- lel corpus and train ... Translation Majid Razmara 1 George Foster 2 Baskaran Sankaran 1 Anoop Sarkar 1 1 Simon Fraser University, 8888 University Dr., Burnaby, BC, Canada {razmara,baskaran,anoop}@sfu.ca 2 Nationa...

Ngày tải lên: 19/02/2014, 19:20

... technique of Pan et al. (2010). Both the LSA and FALSA techniques are based on latent semantic analysis (Pan et al., 2010). For the Within-Domain baseline, we train a binary classifier using the la- beled ... mutual information between a feature (uni- gram or bigram) and a domain label. After selecting salient features, the SCL algorithm is used to train a binary classifier. SFA is th...

Ngày tải lên: 20/02/2014, 04:20

... permuted), and trained a SVM preference ranking model with discourse role S 1 Japan normally depends heavily on the High- land Valley and Cananea mines as well as the Bougainville mine in Papua New Guinea. S 2 Recently, ... the update task. The results are much better on Spearman and Kendall. This is because LIN is trained with a ranking model, and both Spearman and Kendall are ranking-...

Ngày tải lên: 07/03/2014, 18:20