automatically evaluating text coherence using discourse relations

... June 19-24, 2011. c 2011 Association for Computational Linguistics Automatically Evaluating Text Coherence Using Discourse Relations Ziheng Lin, Hwee Tou Ng and Min-Yen Kan Department of Computer ... coherent and incoherent text in training to determine an unseen text s coherence. To evaluate the coherence of a text, we extract sub-sequences with various lengths from the discourse role matrix ... problem. 4.1 Discourse Role Matrix Figure 1 shows a text and its gold standard PDTB discourse relations. When a term appears in a dis- course relation, the discourse role of this term is defined as the discourse...

Ngày tải lên: 23/03/2014, 16:20

... when used by a text planner. We conclude by discussing our experiments in which this methodology is applied using a subset of the gnome corpus. 2 Evaluating the coherence of a corpus text according ... in (1). 7 2.3 Evaluating the coherence of a text and text structuring The statistics about transitions computed as just discussed can be used to determine the de- gree to which a text conforms ... al. (2004) to evaluate the coherence of a text according to Centering. 2.1 Computing CF lists, CPs and CBs According to Grosz et al. (1995), each “utter- ance” in a discourse is assigned a list...

Ngày tải lên: 17/03/2014, 06:20

... semantic links (R j) between discourse clauses (Ci): (a) back to the same discourse clause; (b) back to different discourse clauses; (c) back to different discourse clauses, with crossing ... der Sandt, 1992). This simpli- fies discourse structure, while still allowing the real- isation of a full range of discourse relations. This is achieved using the same semantic machinery used ... Coling/ACL Workshop on Discourse Relations and Discourse Markers, pages 86-92, Montreal, Canada. Bonnie Webber, Alistair Knott, and Aravind Joshi. 1999. Multiple discourse connectives in...

Ngày tải lên: 20/02/2014, 18:20

... Effects of using the empty categories 5 Experiments with Automatically Parsed data The next set of experiments use the BNC and Treebank, but strip POS and parse information, and parse them automatically ... summarise the findings : • Using the BNC, which is tagged with a com- plex tagging scheme but has no parse data, it is possible to get 76% F1 using lexical forms and POS data alone • Using the Treebank, ... raised to 68% using extra fea- tures • Parsing the BNC, top performance is 71%, raised to 72% using extra features • Combining the parsed data, top performance is 67%, raised to 71% using extra...

Ngày tải lên: 17/03/2014, 06:20

Ngày tải lên: 30/03/2014, 23:20

... video database. However, text extraction presents a number of problems because the properties of text may vary, as well as the text sizes and the text fonts. Furthermore, texts may appear in a ... horizontal edges to obtain candidate text regions. Real Text regions are then identified using the support vector machine. Text regions usually have special texture features because they consist ... or compressed images. Text extraction from uncompressed image can be classified as either component-based or texture-based. For component-based text extraction methods, text regions are detected...

Ngày tải lên: 05/11/2012, 14:51

... Understand that the parent–child relationship is not meant to be a human relationship. The term "parent–child" is simply a convenient reference to a common familial relationship. The "child" ... through 9) is written using the Chen-like model. Why did we choose this model? Chen (1976) introduced the idea of ER diagrams (Elmasri and Navathe, 2000), and most database texts use some variant ... Shoe Size. A partial proof using the reflexive rule would be: Name → City, Shoe Size (given) City, Shoe Size → City (by the reflexive rule) Name → City (using steps 1 and 2 and the...

Ngày tải lên: 22/10/2013, 10:15

... (2005; 2006) use a textual representation of words by collating all the glosses of the word as found in some dictionary. Then, a binary text clas- sifier is trained using the textual representation ... word by analyzing its relations to other words. Auto- matically classifying words as either positive or negative enables us to automatically identify the polarity of larger pieces of text. This could ... USA radev@umich.edu Abstract Automatically identifying the polarity of words is a very important task in Natural Language Processing. It has applications in text classification, text filtering, analysis of...

Ngày tải lên: 20/02/2014, 04:20

... interfaces (BCI). This paradigm is widely used to build letter-by- letter text input systems using BCI. Neverthe- less using a BCI-typewriter depending only on EEG responses will not be sufficiently ... 2011. c 2011 Association for Computational Linguistics An ERP-based Brain-Computer Interface for text entry using Rapid Serial Visual Presentation and Language Modeling K.E. Hild ◦ , U. Orhan † , D. ... next letters to be typed be- come highly predictable in certain contexts, partic- ularly word-internally. In applications where text generation/typing speed is very slow, the impact of language...

Ngày tải lên: 20/02/2014, 05:20

... 604-714 Korea yjko@dau.ac.kr Abstract This paper proposes how to automatically identify Korean comparative sentences from text documents. This paper first investigates many comparative sentences ... 153–156, Suntec, Singapore, 4 August 2009. c 2009 ACL and AFNLP Extracting Comparative Sentences from Korean Text Documents Us- ing Comparative Lexical Patterns and Machine Learning Techniques Seon Yang ... In this section, we define comparative keywords and extract comparative-sentence candidates by using those keywords. 3.1 Comparative keyword First of all, we classify comparative sentences...

Ngày tải lên: 20/02/2014, 09:20

... words tend to appear in similar contexts, we can compute the similarity by using contextual information. Words and contexts play complementary roles. Contexts are similar to the extent that ... Bayes classifier using machine-labeled data as purpose and remaining contexts are assigned to each context-cluster by that revised technique. 1) Measurement of word and context similarities ... the Naive Bayes Classifier Using Context-Clusters In above section, we obtained labeled training data: context-clusters. Since training data are labeled as the context unit, we employ a Naive...

Ngày tải lên: 20/02/2014, 16:20

... or NONE-OF-THE-ABOVE, even when the discourse relations are not explicitly signalled by discourse markers. 2.2 Discourse relation definitions The discourse relations we focus on are defined at ... NO-RELATION examples are also noisy because long distance relations are com- mon in well-written texts. 3 Determining discourse relations using Naive Bayes classifiers We hypothesize that we can ... two different documents. Table 2: Patterns used to automatically construct a corpus of text span pairs labeled with discourse re- lations. CONDITION relations and the number of examples extracted...

Ngày tải lên: 20/02/2014, 21:20

... sentential semantics by using defensible reasoning. Suppose that the reader also believes that the clauses in text (1) are related by some discourse relation, as they must be for the text to be coher- ... (3). The clauses in (3) must be related by a discourse relation for the text to be coherent, and therefore given the meanings of the discourse relations, the events described must be connected ... Problem The temporal interpretation of text involves an account of how the events described are related to each other. These relations follow from the discourse relations that are central to temporal...

Ngày tải lên: 08/03/2014, 07:20

... "Noun Homograph Disambigu- ation Using Local Context in Large Text Corpora," Proceedings of the 7th Annual Conference of the UW Centre for the New OED and Text Research, Oxford, England. ... Ellen. M. 1993. " ;Using WordNet to Dis- ambiguate Word Senses for Text Retrieval," in Pro- ceedings of SIGIR'93. 295 Sense Disambiguation Using Semantic Relations and Adjacency ... the context in which the word occurs. The reference can be a standard dictionary or thesaurus, or a lexicon con- structed specially for some application. The context is provided by the text...

Ngày tải lên: 08/03/2014, 07:20

... to those that are necessary for the anaphora resolution application (the ob- ject relations, the complement relations and the ncmod relation), and those that are a sim- ple by-product of extracting ... we com- pare F1 using the t-test. The 500 sentence corpus is split into 10 segments and an F- measure is computed for each algorithm on all segments. These are then compared using the t-test. ... Missing (aux printed be) relation). • Extra ncmod relations, due to wrong iden- tification of the head by the algorithms or in the gold standard. • Extra iobj relations, due to a misclassifi- cation...

Ngày tải lên: 08/03/2014, 21:20

... R. Dale. Using linguistic phenomena to motivate a set of coherence relations. Discourse processes, 18(1):35–62, 1994. J. van Kuppevelt and R. Smith, editors. Current Di- rections in Discourse ... approximation of discourse re- lations between different utterances in texts. Following the idea that every pair of events comes with preferences regarding the range and frequency of discourse relations ... another utterance, ibid., p.257), or relations between entities mentioned in the connected discourse segments (anaphoric rela- tions, Webber et al. 2003). Discourse relations can be indicated explicitly...

Ngày tải lên: 16/03/2014, 20:20

Ngày tải lên: 23/03/2014, 20:20

Ngày tải lên: 30/03/2014, 21:20

Ngày tải lên: 31/03/2014, 04:20

Ngày tải lên: 31/03/2014, 04:20