Báo cáo khoa học: "Supervised Domain Adaption for WSD" pdf

... would expect the performance of a generic WSD system to drop when moving to the domain corpus for domain- related words (cf. Table 1), while the performance would be similar for generic words. In ... specific target domains separately (SPORTS and FINANCES). We do not perform any kind of adaptation, and therefore the results are those expected for a generic WSD system when applied to...

Ngày tải lên: 31/03/2014, 20:20

... the semantics of these domains, they are fairly simple, and several different types of semantic components are used depending on the nature of the domain. For some domains a procedural semantics ... linguistic requirements which have had to be violated in order for the parse to succeed. Such descriptions might well form the basis for a useful interaction between system and lea...

Ngày tải lên: 24/03/2014, 01:21

... Response times for distantly related pairs was faster than for homo- nyms (distantly related mean: 1253ms, homonym mean: 1406ms; t 32 =2.38; p<.0001). Accuracy was en- hanced as well for this ... implications for automatic word sense disam- biguation. 1 Introduction * The problem of creating a successful word sense disambiguation system begins, or should begin, well before...

Ngày tải lên: 23/03/2014, 17:20

... from each other by different namespace prefixes, for ex- ample gold:Noun and hpsg:noun. 3 An OWL Ontology for HPSG HPSG OWL is an OWL ontology for HPSG that is currently under development. As ... ontology for HPSG. The HPSG ontology is integrated with an existing OWL ontology, GOLD, as a community of practice extension. The basic ideas are illustrated by visualizations of type hierarch...

Ngày tải lên: 23/03/2014, 18:20

... expressing information in a format close to the linguistic theory they are familiar with. GIT has been developed for teaching purposes and cannot be considered as a system for large scale ... of linguists for experimental devel~t of an MT system for a special purpose language (Buchmann et al., 1984), and to train students in cc~putational linguistics. 2. THE UNIFORMITY AND S...

Ngày tải lên: 24/03/2014, 01:21

... earlier, we use different informa- tion sources to determine user/group similarity, in- cluding textual information and social connections. A module is designed for each information source to rank ... users. For these qualified users, their 1, 383 friends information is retrieved, again using Twitter API. For the friends that are retrieved, their 180, 296 tweets and 584, 339 friend-of-fr...

Ngày tải lên: 30/03/2014, 21:20

... labelled information for training. Our sys- tem extracts transliteration pairs in an unsupervised fashion. It is also able to utilize labelled information if available, obtaining improved performance. We ... of the Association for Computational Linguistics, pages 469–477, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics A Statistical Model for...

Ngày tải lên: 19/02/2014, 19:20

... = 0.001, which we tuned for best performance on the test set, giving an unfair advantage to our competitor. Finally, there are some methods that use auxil- iary tasks for training sequence models, ... their associated majority label. Features for each label were chosen by the method de- scribed in HK06 – top frequency for that label and not higher frequency for any other label. + SV...

Ngày tải lên: 20/02/2014, 09:20

... Association for Computational Linguistics, pages 55–60, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics DOMCAT: A Bilingual Concordancer for Domain- Specific ... always correlated in lexical level. Unfortunately, the above effects will be intensified in a domain- specific concordancer because the queries are usually domain- specific term...

Ngày tải lên: 07/03/2014, 18:20

... con- crete recommendations for modifying a question-answering system for improving robustness to spoken input. 1 Introduction This paper demonstrates a multimodal interface for asking questions and ... implemented systems for the Pocket PC that interpret queries spoken in English or Chinese. This last group appears to be at the forefront of current research in spoken interfaces for...

Ngày tải lên: 08/03/2014, 04:22