Báo cáo khoa học: "Incorporating Extra-linguistic Information into Reference Resolution in Collaborative Task Dialogue" pot

... using Extra-linguistic Information Before explaining the treatment of extra-linguistic information, let us first describe the task defini- tion, taking the REX-J corpus as target data. In the task of reference ... extra-linguistic information as well as textual information examined by exist- ing approaches (Soon et al., 2001; Ng and Cardie, 2002, etc.). In this paper, we...

Ngày tải lên: 30/03/2014, 21:20

... information into such models may yield improvement over models which do not use topic information. 1 Introduction There are a number of challenging aspects in recognizing the favorability of opinion-based ... of which are used in abundance in many discourse domains, create challenges for these approaches. It is hoped that incorporating topic information along the lines suggested...

Ngày tải lên: 31/03/2014, 03:20

... Ananiadou, 1996), incorporating information gained from the textual context of the candidate term. 2 Context information for terms The idea of incorporating context information for term ... terms, domain-dependent linguistic information (i.e. mor- phology) is used (Ananiadou, 1994). Multi-word ATR usually uses linguistic information in the form of a grammar that mainly...

Ngày tải lên: 22/02/2014, 03:20

... Embedding New Information into Referring Expressions Hua Cheng Department of Artificial Intelligence, University of Edinburgh El7, 80 South Bridge, Edinburgh EH1 1HN, U.K. ... on generating referring expres- sions capable of serving multiple communicative goals. The components of a referring expression are divided into a referring part and a non-referring part. ... Expression The...

Ngày tải lên: 31/03/2014, 04:20

... syntax. In Advances in Neural Information Processing Sys- tems, volume 17, pages 537–544. Haghighi, A. and Klein, D. (2006). Prototype-driven learning for sequence models. In Proceedings of the main ... learning (Haghighi and Klein, 2006). We use Information Gain (Mitchell, 1997) to identify the required discriminating features. The Information Gain (IG) of a word (w) in a class...

Ngày tải lên: 31/03/2014, 20:20

... discourse markers for Patient Information Leaflets using a constraint-based method applied to RST trees during sentence planning. Finally, in the C IRC-SIM intelligent tutoring sys- tem (Yang et al., ... principally con- cerned with taking sets of small, single-proposition sentences and finding ways to combine them into more fluent, multiple-proposition sentences. Sen- tences can be combin...

Ngày tải lên: 31/03/2014, 03:20

... settings) on labeled training data sets of the same size used for the re- spective Co-Training experiment. We did this in or- der to verify the quality of the training data and for obtaining reference ... we implemented the standard Co-Training algorithm (as described in Section 3) in Java using the Weka machine learning library 3 . In contrast to other Co-Training approaches, we di...

Ngày tải lên: 20/02/2014, 21:20

... analysis. Each of the remaining terms has, on average, 4.45 distinct anno- tations. The information from multiple annotators was combined by taking the majority vote, result- ing in a lexicon with 8,813 ... certain colour categories (for example, danger with red, and softness with pink), complementing linguistic and non-linguistic information with appro- priate colours has a number of b...

Ngày tải lên: 07/03/2014, 22:20

... two training hy- potheses listed in Table 2, yielding two models, B and J. Table 3 shows the increasing accuracy of both models in describing the text reuse in L train as more features are incorporated. ... global linear models in (Collins, 2002), we cast this task as learning a mapping F from input verses x ∈ X to a text-reuse hypothesis y ∈ Y ∪ {}. X is the set of verses in the...

Ngày tải lên: 08/03/2014, 02:21

... functions for resolving different types of anaphora. Responsibilities of this layer include determining what anaphoric phenomena are to be resolved in the current experiment, determining what anaphora ... TRAINS93 dialogue transcripts. The input was POS-tagged words with no structural analysis. Other information, such as basic punc- tuation and whether each pronoun was in a main...

Ngày tải lên: 08/03/2014, 21:20