Báo cáo khoa học: "Realistic Grammar Error Simulation using Markov Logic" potx

Báo cáo khoa học: "Realistic Grammar Error Simulation using Markov Logic" potx

Báo cáo khoa học: "Realistic Grammar Error Simulation using Markov Logic" potx

... background in Markov logic. We then describe our Markov Logic Net- work (MLN) for grammar error simulation. Fi- nally, we present our experiments and results. 2 Overall process of grammar error si- mulation ... statistical grammar error simulation that can incorporate this type of knowledge about language learners’ error characteristics and shows that it does in- deed...

Ngày tải lên: 23/03/2014, 17:20

4 185 0
Tài liệu Báo cáo khoa học: "Japanese OCR Error Correction using Character Shape Similarity and Statistical Language Model " pptx

Tài liệu Báo cáo khoa học: "Japanese OCR Error Correction using Character Shape Similarity and Statistical Language Model " pptx

... were 1422 (2.1%) re- placement errors, 244 (0.4%) insertion errors and 41 (0.06%) deletion errors. 1 0.99 0.98 0.97 0.96 0.95 0.94 0.93 0.92 0.91 Error Correction Accuracy oo o ... characters, and try to solve the problem by using only linguistic devices. We found that, by using character shape similarity, the resulting OCR error corrector is robust and ac- curate e...

Ngày tải lên: 20/02/2014, 18:20

7 472 0
Báo cáo khoa học: "Jointly Identifying Temporal Relations with Markov Logic" ppt

Báo cáo khoa học: "Jointly Identifying Temporal Relations with Markov Logic" ppt

... Jurafsky. Instead of combining the output of a set of local classifiers using ILP, we approach the problem of joint temporal relation identification using Markov Logic (Richardson and Domingos, 2006). In this 405 framework ... of these methods are often already provided in existing Markov Logic inter- preters such as Alchemy 7 and Markov thebeast. 8 4 Proposed Markov Logic Network A...

Ngày tải lên: 08/03/2014, 00:20

9 307 0
Báo cáo khoa học: "Determining Word Sense Dominance Using a Thesaurus" potx

Báo cáo khoa học: "Determining Word Sense Dominance Using a Thesaurus" potx

... Determining Word Sense Dominance Using a Thesaurus Saif Mohammad and Graeme Hirst Department of Computer Science University of Toronto Toronto, ... of that sense in text. We propose four new methods to accurately determine word sense dominance using raw text and a pub- lished thesaurus. Unlike the McCarthy et al. (2004) system, these methods ... the need for a similarly-sense- distributed...

Ngày tải lên: 08/03/2014, 21:20

8 252 0
Tài liệu Báo cáo khoa học: "Dependency Grammar Induction via Bitext Projection Constraints" doc

Tài liệu Báo cáo khoa học: "Dependency Grammar Induction via Bitext Projection Constraints" doc

... Rules child POS parent POS acc(%) errors errors V 65.2 2237 T/V 2175 N 73.8 1938 V/V 1305 P 58.5 1705 N/V 1112 R 70.3 961 root/V 555 child POS parent POS acc(%) errors errors N 78.7 1572 N/V 938 P ... 376 child POS parent POS acc(%) errors errors N 79.3 1532 N/V 1116 P 75.7 998 V/V 560 R 69.3 993 V/N 507 V 86.2 889 N/N 450 Table 3: Top 4 discriminative parser errors by child POS tag and true/...

Ngày tải lên: 20/02/2014, 07:20

9 253 0
Tài liệu Báo cáo khoa học: "Interactive ASR Error Correction for Touchscreen Devices" docx

Tài liệu Báo cáo khoa học: "Interactive ASR Error Correction for Touchscreen Devices" docx

... the effective speed of text input using speech is significantly reduced by the fact that even the best speech recognition systems make errors. After accounting for error correction, the effective number ... slower than using a 12-digit keypad for typing SMS mes- sages (Karpov et al., 2006). 2 Description It has been shown that multimodal error correction methods are much more effective...

Ngày tải lên: 20/02/2014, 09:20

3 282 0
Tài liệu Báo cáo khoa học: "Universal Grammar and Lexis for Quick Ramp-Up of MT Systems" doc

Tài liệu Báo cáo khoa học: "Universal Grammar and Lexis for Quick Ramp-Up of MT Systems" doc

... of universal grammar parame- ters or even those for particular languages o] language families. For Project Boas, it means tha~. both the nature of the parameters it would be using and their ... languages, resulting in the creation of a variety of machine-tractable resources text corpora, grammars, lexi. cons, analyzers, etc. Thus, Spanish will most probably count a ; "high-den...

Ngày tải lên: 20/02/2014, 18:20

5 428 0
Tài liệu Báo cáo khoa học: "Supervised Grammar Induction using Training Data with Limited Constituent Information *" docx

Tài liệu Báo cáo khoa học: "Supervised Grammar Induction using Training Data with Limited Constituent Information *" docx

... ducing grammars from sparsely labeled training data (e.g., only higher-level constituent labels), we propose an adaptation strategy, which pro- duces grammars that parse almost as well as grammars ... a directly in- duced grammar parses test sentences with 66% accuracy, whereas an adapted grammar parses with 91% accuracy, which is only 2% lower than the score of a grammar ind...

Ngày tải lên: 20/02/2014, 19:20

7 423 0
Báo cáo khoa học: "Cross-Domain Dependency Parsing Using a Deep Linguistic Grammar" docx

Báo cáo khoa học: "Cross-Domain Dependency Parsing Using a Deep Linguistic Grammar" docx

... in Section 2, one pitfall of using a precision-oriented grammar in parsing is its lack of robustness. Even with a large scale broad cover- age grammar like ERG, using our settings we only achieved ... number reported here should not be taken as an absolute measure of grammar performance. 3.3 Using Feature-Based Models Besides directly using the dependency backbone of the HPSG ou...

Ngày tải lên: 08/03/2014, 00:20

9 349 0
w