Báo cáo khoa học: "Automatic Evaluation of Linguistic Quality in Multi-Document Summarization" pptx

... aspect of linguistic quality separately. 3 Indicators of linguistic quality Multiple factors in uence the linguistic quality of text in general, including: word choice, the ref- erence form of entities, ... 148–156. J.M. Conroy and H.T. Dang. 2008. Mind the gap: dan- gers of divorcing evaluations of summary content from linguistic quality. In Proceedings of C...

Ngày tải lên: 16/03/2014, 23:20

... devel- oping computational methods for deep as- sessment of quality in the domain of intel- ligence reports. We present an automated system for ranking intelligence reports with regard to coverage of ... team of analysts on a specific topic of interest. Each decision may involve several areas of interest, resulting in several collections of reports. Addi- tionally, the office...

Ngày tải lên: 23/03/2014, 16:20

... Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 344–351, Prague, Czech Republic, June 2007. c 2007 Association for Computational Linguistics GLEU: ... were interested in the level of agreement of intuitive un- derstanding of fluency. We instructed them also that they should evaluate the sentence without consider- ing its content, usi...

Ngày tải lên: 20/02/2014, 12:20

... Automatic Evaluation of Machine Translation Quality Using Longest Com- mon Subsequence and Skip-Bigram Statistics Chin-Yew Lin and Franz Josef Och Information Sciences Institute University of Southern ... shown in the higher correlations in Stem set than Case set in Table 1; while the reverse was true in the terms of fluency. The evaluation results of ROUGE-L, ROUG...

Ngày tải lên: 20/02/2014, 16:20

... deeper linguistic analysis, such as part -of- speech tagging, synonym matching, semantic role labeling, etc. Since part -of- speech tags are only defined for Chinese words and not for Chinese ... Joint Model for Chinese Word Segmentation. Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010), pages 1173-1181, Beijing, China. Kun Wang, Chengqin...

Ngày tải lên: 17/03/2014, 00:20

... dictionary for a certain domain. Re- cursive application of the method enables to collect a list of terms that are used in a certain domain: the list becomes a glossary of the domain. A technical-term dictionary ... development) 情報処理学会 (Information Processing Society of Japan; IPSJ) √√ 意味処理 (semantic processing) √√ 音声処理 (speech processing) √ 音声情報処理 (speech inform...

Ngày tải lên: 20/02/2014, 16:20

... machine learning. He represents instances of it as vectors of 35 features. These features encode, among other things, information about the parts of speech and lemmata of words in the context of ... anno- tation that we performed in order to collect train- ing and test data for our machine learning experi- ments. The annotation also offered interesting in- sights into how reli...

Ngày tải lên: 22/02/2014, 02:20

... the mean point-to-point accuracy of CP was 85.4% (a relative increase of about 100% in error). In their separate evaluation of CP, using 30 sam- ples of typically developing children, Long and Channell ... to train the classifier for labeling dependencies, the size of this training set is far smaller than what would be necessary to train a parser to find labeled dependen- 3 Klei...

Ngày tải lên: 08/03/2014, 04:22

... participate in a relation, such as the use of comma in coordi- nation. The label “Sentence” links the head of the sentence to the punctuation mark or a conjunct in case of coordination. So the head of ... consist of morphological infor- mation like existence of a “PRESPART” morpheme in (8), and part -of- speech of the word. However, there is still a problem in cases li...

Ngày tải lên: 17/03/2014, 06:20

... Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics, pages 6–10, Jeju, Republic of Korea, 8-14 July 2012. c 2012 Association for Computational Linguistics Joint ... lexicon LEX, distinct from W, containing pairs of segments drawn from a set T of terminals and PoS categories drawn from a set N of nonterminals. LEX = {s, p|s ∈ T , p ∈ N } Each...

Ngày tải lên: 23/03/2014, 14:20