Báo cáo khoa học: "Automatic Image Annotation Using Auxiliary Text Information" potx

... Ohio, USA, June 2008. c 2008 Association for Computational Linguistics Automatic Image Annotation Using Auxiliary Text Information Yansong Feng and Mirella Lapata School of Informatics, University ... human annotations in any way. We also show that the auxiliary docu- ment contains important information for generating more accurate image descriptions. 2 Related Work Automatic...

Ngày tải lên: 31/03/2014, 00:20

... in Arabic text, graph- 117 ical signs known as diacritics were invented in the seventh century. Currently in the Modern Standard Arabic (MSA), diacritics are omitted from written text almost ... “ 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 f...

Ngày tải lên: 20/02/2014, 05:20

... followed two different approaches to segment a Sanskrit text using sandhi 1 rules extracted from a parallel corpus of manually sandhi split text. While the first approach augments the finite state ... and vali- dates each constituent using a morph an- alyzer. 1 Introduction Sanskrit has a rich tradition of oral transmission of texts and this process causes the text to un- dergo euphoni...

Ngày tải lên: 07/03/2014, 22:20

... of cues, lexical cues are the most generic since they can work on text and multimedia sources. Previous approaches include TextTiling (Hearst 1997) that monitors changes in sentence similarity, ... count of chains continuing through it. We devise a Bayesian framework to capture such be- havior, using the lexical chain features of start, continuation and end. In the scoring criteri...

Ngày tải lên: 23/03/2014, 17:20

... related web-documents for each image using the Yahoo! search engine and the toponym associated with the image as a query. The text from these documents was extracted using an HTML parser and passed to ... generate captions based on the immediate textual context of the image with or without consideration of image related features such as colour, shape or texture (Deschacht and Mo...

Ngày tải lên: 30/03/2014, 21:20

... were also counted as active if the closest preceding auxiliary was have, while they were counted as passive if the closest preceding auxiliary was be. VBD: A part-of-speech tagged corpus ... years have witnessed a shift in grammar development methodology, from crafting large grammars, to annotation of corpora. Correspond- ingly, there has been a change from developing rule-ba...

Ngày tải lên: 31/03/2014, 21:20

... the posterior con- text model and the probability of our proposed model: score = P context (T ) α × P (T ), (8) where P context (T ) is the probability of the poste- rior context model. The α ... models to a feature set used in the posterior context model (f) one using only our proposed probabilities without the probability of the posterior con- text model The accuracies obtained with e...

Ngày tải lên: 20/02/2014, 12:20

... of corn. The contexts in which the word tezgiiino is used suggest that tezgiiino may be a kind of alcoholic beverage made from corn mash. Bootstrapping semantics from text is one of the ... Proceedings of COLING-94, pages 482-488. Kyoto, Japan. Dekang Lin. 1997. Using syntactic dependency as local context to resolve word sense ambiguity. In Proceed- ings of ACL/EACL-97, pages...

Ngày tải lên: 17/03/2014, 07:20

... the position of X in a text, i.e. #S(kth sentence) = k. ‘Last Sentence’ refers to the last sentence in a text. LocSen takes values between 0 and N−1 N . N is the number of sentences in the text. <LocPar> ... topics discussed in the text. A nice feature about their approach is that by creating a summary covering potential topics, which could be marginal to the main thread of the t...

Ngày tải lên: 17/03/2014, 08:20

... and n using standard dynamic program- ming technique in O(mn) time. LCS has been used to identify cognate candi- dates during construction of N-best translation lexicons from parallel text. ... 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...

Ngày tải lên: 20/02/2014, 16:20