Get Anaphora Processing and Applications: 8th Discourse Anaphora PDF

By Iris Hendrickx, Orphée De Clercq, Veronique Hoste (auth.), Iris Hendrickx, Sobha Lalitha Devi, António Branco, Ruslan Mitkov (eds.)

ISBN-10: 3642259162

ISBN-13: 9783642259166

This publication constitutes the refereed court cases of the eighth Discourse Anaphora and Anaphor answer Colloquium, DAARC 2011, held in Faro, Portugal, in October 2011. The sixteen revised complete papers offered have been rigorously reviewed and chosen from forty five preliminary submissions. The papers are equipped in topical sections on computational answer method and structures; language research and illustration; and human processing and performance.

Show description

Read Online or Download Anaphora Processing and Applications: 8th Discourse Anaphora and Anaphor Resolution Colloquium, DAARC 2011, Faro, Portugal, October 6-7, 2011. Revised Selected Papers PDF

Best nonfiction_5 books

Get Evidence-based palliative care across the life span PDF

This ebook describes the present cutting-edge within the box of palliative care in childrens and adults. exact emphasis is put on addressing the efficacy and effectiveness of palliative care types, discomfort and symptom administration, and on measuring caliber of lifestyles. additionally the e-book evaluates present examine tools in palliative care and indicates compatible choices.

Additional resources for Anaphora Processing and Applications: 8th Discourse Anaphora and Anaphor Resolution Colloquium, DAARC 2011, Faro, Portugal, October 6-7, 2011. Revised Selected Papers

Sample text

1. Example of a tectogrammatical representation of two sentences interlinked with various types of anaphora Although PDT is already divided into training, development and evaluation set, it is not completely covered with NP coreference annotation. Therefore, we had to make our own partitioning of available data. The number of instances and the proportion of coreferential links in the data is sketched in Table 1. 3 Related Work Exploring the possibilities of the coreference resolution for Czech was until recently limited by the availability of annotated data.

Different settings can be applied to combine the patterns, whether we want a better coverage or a better precision: we set a threshold that corresponds to a minimum of nonzero matches among all the patterns required to accept a meronym candidate. In our experiments, meronym candidates are (potential antecedent, anaphora)pairs for the MERO class of DEDE. 9% of all meronyms were positively identified (275/296 different meronyms in DEDE, or 292/322 annotated bridges). We will give more detailed results in section 5.

A crucial finding comes from the analysis of the learning curves. The combination of presented feature sets and learning methods are not able to sufficiently exploit a growing amount of knowledge in a growing quantity of the annotated data. We took advantage of the tree nature of the annotated data to design several novel features. Most of them affect the quality of resolution positively, though there is still a place for smarter involvement of dependent nodes of phrases. Our future work should focus on feature engineering, mainly to investigate deeper lexical and semantic relations between phrases.

Download PDF sample

Anaphora Processing and Applications: 8th Discourse Anaphora and Anaphor Resolution Colloquium, DAARC 2011, Faro, Portugal, October 6-7, 2011. Revised Selected Papers by Iris Hendrickx, Orphée De Clercq, Veronique Hoste (auth.), Iris Hendrickx, Sobha Lalitha Devi, António Branco, Ruslan Mitkov (eds.)


by Ronald
4.0

Rated 4.05 of 5 – based on 47 votes