Báo cáo khoa học: "Automatic Sanskrit Segmentizer Using Finite State Transducers" pdf

... Sweden, 13 July 2010. c 2010 Association for Computational Linguistics Automatic Sanskrit Segmentizer Using Finite State Transducers Vipul Mittal Language Technologies Research Center, IIIT-H, Gachibowli, ... analyze the bound morphemes in compounds. A segmentizer for Sanskrit developed by Huet (Huet, 2009), decorates the final states of its fi- nite state transducer handling...

Ngày tải lên: 07/03/2014, 22:20

... Probabilistic Finite- State Transducers ∗ Jason Eisner Department of Computer Science Johns Hopkins University Baltimore, MD, USA 21218-2691 jason@cs.jhu.edu Abstract Weighted finite -state transducers ... de- velopment cycle in natural language engineering. 2 Transducers and Parameters Finite- state machines, including finite -state au- tomata (FSAs) and transducers (FSTs), are a kind...

Ngày tải lên: 20/02/2014, 21:20

... “ and he wrote it ” is compared with the word “ﺐﺘﻛ” “ he wrote ” using the EWM method the resulting score will be 0, but when using the CCC method it will be 0.667. The CCC method comes from ... have shown the effectiveness of using charac- ter cross-correlation in choosing the best headline out of nominated sentences from Arabic document. The advantage of using character cross-...

Ngày tải lên: 20/02/2014, 05:20

... task. Classification performance using Charniak parses is about 3% absolute worse than when using Tree- Bank parses. On the other hand, argument identifi- cation performance using Charniak parses is about 12.7% ... on all tasks using hand-corrected parses and automatic parses on PropBank data. Table 2 shows the performance of the system us- ing the hand corrected, TreeBank parses (HAND)...

Ngày tải lên: 08/03/2014, 04:22

... for each sense using the conditional probabilities of the words. As in Bengio and Kermorvant (2003), this generative procedure may be captured by factor- ing the joint distribution using the conditional ... Qu´ebec, Canada bengioy@IRO.UMontreal.CA Abstract We describe two probabilistic models for unsuper- vised word-sense disambiguation using parallel cor- pora. The first model, which we...

Ngày tải lên: 08/03/2014, 04:22

... Automatic Evaluation of Machine Translation Quality Using Longest Com- mon Subsequence and Skip-Bigram Statistics Chin-Yew Lin and Franz Josef Och ... methods correlate with human judgments very well in both ade- quacy and fluency. 1 Introduction Using objective functions to automatically evalu- ate machine translation quality is not new. Su ... called position-independent word error...

Ngày tải lên: 20/02/2014, 16:20

... 5. CONCLUSION Using word pairs of Japanese and English to distinguish among senses of the same verb, we have shown that using word pairs to classify nouns is better than not using word pairs, ... shown. One (solid line) is the result of using the word pair to distinguish among senses of the same verb. The other (dotted line} is the result of using the verb form itself. The X-...

Ngày tải lên: 20/02/2014, 21:20

... of noisy candidate instances using hand-coded pat- terns, and ranks the instances by using a sim- ple ranking model. The Expander expands and ranks the instances using evidence from semi- structured ... their instances by using “concept signatures” (statistics on co-occuring instances). Pasca (Pasca, 2004) presented a method for acquiring named entities in arbitrary categories using...

Ngày tải lên: 08/03/2014, 00:20

... and method. • TRG: The models were trained using only the real-error corpus (baseline). • SRC: Trained using only the pseudo-error corpus. • ALL: Trained using the real-error and pseudo- error corpora ... task is hindered by the difficulty of collecting large error cor- pora. We tackle this problem by using pseudo- error sentences generated automatically. Fur- thermore, we apply domain...

Ngày tải lên: 19/02/2014, 19:20

... polarity classes. The method is exper- imentally tested using a manually labeled set of positive and negative words. It out- performs the state of the art methods in the semi-supervised setting. ... h(i|k) is de- fined as the average number of steps a random walker, starting in state i = k, will take to en- ter state k for the first time (Norris, 1997). Let G = (V, E) be a graph with a...

Ngày tải lên: 20/02/2014, 04:20