Báo cáo khoa học: "An Integrated Architecture for Shallow and Deep Processing" doc

... term, information, and answer extraction) has been to argue that for many purposes, shallow natural language processing (SNLP) of texts can provide sufficient information for highly accurate and useful ... component-based applica- tions, but also for the integration of deep and shallow processing components itself. 2.1 Components 2.1.1 Shallow NL component Shallow analysi...

Ngày tải lên: 08/03/2014, 07:20

... parenthetical constructions and incorpo- rate its findings into a natural language generation system. 2 System Architecture We propose an integrated generation architecture for this purpose which uses ... with each 1 See for example, Rule 14 of (Strunk and White, 1979) other will be localized in the trees themselves. By incorporating information about rhetorical structure and d...

Ngày tải lên: 23/03/2014, 17:20

... System Demonstrations, pages 74–79, Portland, Oregon, USA, 21 June 2011. c 2011 Association for Computational Linguistics Wikulu: An Extensible Architecture for Integrating Natural Language Processing ... author- ing systems (Leuf and Cunningham, 2001). As they offer fast and simple means for adding and editing content, they are used for various purposes such as creating ency...

Ngày tải lên: 07/03/2014, 22:20

... concerns. Finally, when other platforms usually enforce the use of a dedicated document format, LinguaStream is able to process any XML document. On the other hand, LinguaStream is more targeted ... unified representation of markups and annotations. The latter are uniformly represented by feature sets, which are commonly used in linguistics and NLP, and allow rich and structured inform...

Ngày tải lên: 22/02/2014, 02:20

... in corpora and are therefore more appropriate for statistical clustering. The contribution of this paper is to propose an integrated platform for computer-aided term extraction and structuring ... (Bouriganlt et al., 1996), and FASTR 1, a Term Normalization tool (Jacquemin et al., 1997). 2 Components of the Platform for Computer-Aided Terminology The platform for co...

Ngày tải lên: 24/03/2014, 03:20

... ((Candito, 1999), (Gaiffe et al., 2002)), 2 As we shall later see, a content can in fact be multi- dimensional and integrate for instance both semantic and syn- tax/semantics interface information. 3 We ... frame- work for the processing of linguistic meta- descriptions. 1 Introduction It is well known that grammar engineering is a complex task and that factorizing grammar in- forma...

Ngày tải lên: 22/02/2014, 02:20

... predeces- sor and successor word classes. With the notation I for the number of iterations needed for conver- gence, B for the number of word bigrams, M for the number of classes and V for the vocabulary ... mono-lingually classes for the target language (English) and afterwards optimizing classes for the source language (Eq. (11) and Eq. (12)). For EUTRANS-I we...

Ngày tải lên: 31/03/2014, 21:20

... candidates can be evaluated and compared. We use features of both the candidate parse and the ignored parts of the original input sentence. The fea- tures are designed to be general and, for ... on de- veloping an integrated heuristic scheme for selecting the parse that is deemed "best" from such a collection. We describe the heuristic measures used and their comb...

Ngày tải lên: 20/02/2014, 21:20

... 5-gram model. For GIZA ++, we use the standard training reg- imen up to Model 4, and combine alignments with grow-diag-final -and. For the proposed models, we train for 100 iterations, and use the ... removed for TM training. For both tasks, we perform weight tuning and testing on specified development and test sets. We compare the accuracy of our proposed method of joint phr...

Ngày tải lên: 20/02/2014, 04:20

... graphs show, SEPA outperforms CB and random for all val- 412 ues of the filter f-score parameter k, and outper- forms the MR baseline where the value of k is 95 or more. Although for small k values MR gets ... lines) and Charniak (bottom two lines) model, in the two scenarios (in-domain and adaptation), vs. the min- imum length (ML lines 1 and 3) and confidence (CB, lines 2 and...

Ngày tải lên: 20/02/2014, 12:20