Báo cáo khoa học: "A LANGUAGE-INDEPENDENT AN APHORARE SOLUTION SYSTEM FOR UNDERSTANDING MULTILINGUAL TEXTS" pptx

... A LANGUAGE-INDEPENDENT ANAPHORA RES()LUTION SYSTEM FOR UNDERSTANDING MULTILINGUAL TEXTS Chinatsu Aone and Douglas McKee Systems Research and Applications (SRA) 2000 ... a new discourse module within our multilingual natural language processing system which has been used for understanding texts in En- glish, Spanish and Japanese (el. [1, 2])) The follow- ing ... the on...

Ngày tải lên: 08/03/2014, 07:20

... FRIENDLY AND FLEXIBLE FRONT-END FOR DATA MANAGEMENT SYSTEMS Marjorie Templeton System Development Corporation, Santa Monica, CA. EUFID is a natural language frontend for data management systems. ... dictionary is not rich enough for him. For example, for efficiency a user might prefer to use "wh" for "warehouse" and "co" for "company&qu...

Ngày tải lên: 08/03/2014, 18:20

... (rather than as a postmodifier in a higher level clause). When semantic infor- mation is available, it can be used to select appropriate values for K, too, such as using 100 for an anomalous ... sentences and to provide for top-down computation. Also, we have done an analysis of 80 sentences with multiple parses from our data base to evaluate the per- formance of this metric,...

Ngày tải lên: 08/03/2014, 18:20

... a system for understanding and summarizing descriptive texts (SUSY, a SUmmarizing SYstem) , which is in progress a~-~Te University" of SUSY proposes an approach to descriptive text understanding ... 1981), and it seems to require different understanding processes, different summarization skills, and different cognitive models (Lehnert, 1984). Work on the problem of und...

Ngày tải lên: 09/03/2014, 01:20

... for Saccharomyces carlsbergensis, no data available for E. coli; b value for Lupinus luteus and bovine, no data available for E. coli; c value for Paracoccus denitrificans, no data available for ... hCypA labelling were 50 l M for [ 15 N]Trp and [ 15 N]Tyr, 150 l M for [ 15 N]Ile, [ 15 N]Thr and [ 15 N]His, 0.35 m M for remaining Group II [ 15 N]amino acids, and 1m M for th...

Ngày tải lên: 16/03/2014, 18:20

... using TE for filtering or ranking answers can enhance the accuracy of current QA systems, where the an- swer of a question must be entailed by the text that supports the correctness of this answer. We ... our system. We present the performance of the models using Mean Recipro- cal Rank (MRR), top 1 (Top1) and top 5 predic- tion accuracies (Top5) as they are the most com- monly used perfor...

Ngày tải lên: 20/02/2014, 07:20

... resource for most languages other than English, a wide range of methods have been proposed to reduce the need for manual annotation. Many of these have relied on existing resources for English and ... present a FrameNet-based semantic role labeling system for Swedish text. As training data for the system, we used an annotated corpus that we produced by transferring FrameNet ann...

Ngày tải lên: 20/02/2014, 12:20

... Syntactic Word Order Model for Machine Translation Pi-Chuan Chang ∗ Computer Science Department Stanford University Stanford, CA 94305 pichuan@stanford.edu Kristina Toutanova Microsoft Research Redmond, ... or- acle performance on reference sentences is shown in Table 2. As we can see, the 30-best oracle perfor- mance of the combined model (98.0) is much higher than the 1-best performance (...

Ngày tải lên: 20/02/2014, 12:20

... A semantically-derived subset of English for hardware verification Alexander Holt and Ewan Klein HCRC Language Technology Group Division of Informatics University of Edinburgh alexander, ... target formalism (Fuchs and Schwitter, 1996; Schwitter and Fuchs, 1996; Pulman, 1996; Nelken and Francez, 1996). English input sentences are initially mapped into a general purpose semantic for...

Ngày tải lên: 20/02/2014, 19:20

... stands for 'Net Environment for Embodied Emo- tional Conversational Agents' and is an EU-IST project. • Information about the characters: 1. Personality traits such as extroversion and ... full semantic content can be provided —in the form of a Discourse Representation Structure— whereas for other acts, no semantic content is available at all. Typically, the dialogue planner...

Ngày tải lên: 22/02/2014, 02:20