Báo cáo khoa học: "Learning Noun Phrase Anaphoricity to Improve Coreference Resolution: Issues in Representation and Optimization" ppt

... Learning Noun Phrase Anaphoricity to Improve Coreference Resolution: Issues in Representation and OptimizationVincent NgDepartment of Computer ScienceCornell ... paper is to improve learning-based coreference systems using automaticallycomputed anaphoricity information. In particular,we examine two important, yet largely unexplored, issues in anaphoricity ... deter-mined to be non-anaphoric. But for learning-based coreference systems, anaphoricity information canbe simply and naturally accommodated into the ma-chine learning framework by including...

Báo cáo khoa học: "Adding Noun Phrase Structure to the Penn Treebank" ppt

... addinggold-standard bracketing within each noun phrase in the Penn Treebank. Wethen examine the consistency and reliabil-ity of our annotations. Finally, we usethis resource to determine ... gold-standard labelledbracketing for every ambiguous noun phrase in thePenn Treebank. We describe the annotation guide-lines and process, including the use of named en-tity data to improve ... tagging and chunking, to full parsing.Unfortunately, the Penn Treebank does not anno-tate the internal structure of base noun phrases, in- stead leaving them flat. This significantly simplifiedand...

Báo cáo khoa học: "Supervised Noun Phrase Coreference Research: The First Fifteen Years" pptx

... determine that “Mr. Clinton” and “Clinton” are coreferent using string-matchingfeatures, and that “Clinton” and “she” are coref-erent based on proximity and lack of evidence forgender and number ... Learning noun phrase anaphoricity to improve conference resolution: Issues in repre-sentation and optimization. In Proceedings of the42nd Annual Meeting of the Association for Compu-tational Linguistics, ... ac-cessible to an anaphoric pronoun in his heuristicpronoun resolvers. It would be interesting to in- corporate this idea into a learning-based resolver.There are also features that do not fall into...

Báo cáo khoa học: "Parsing Noun Phrase Structure with CCG" potx

... method of as-signing supertags. Instead, conjuncts are identifiedduring the head-finding stage, and then assigned thesupertag dominating the entire coordination. Inter-vening non-conjunct nodes ... combined using combinatory rulessuch as forward and backward application:X /Y Y ⇒ X (>) (1)Y X \Y ⇒ X (<) (2)Other rules such as composition and type-raising areused to analyse some linguistic ... obtain is to have Victor Borge modify the preceding NP.The final step in the conversion process was to validate the corpus against the CCG grammar,first by those productions used in the existingCCGbank,...

Báo cáo khoa học: "Coordinate Noun Phrase Disambiguation in a Generative Parsing Model" doc

... head words and begins by looking at how thedifferent handling of coordination in noun phrases and base noun phrases (NPB) affects coordinationdisambiguation.1We look at how we might improve the ... in the phrase are nominal.However, we found that out of 1,417 examplesof NP coordination in sections 02 to 21, involvingphrases containing only nouns (common nouns or amixture of common and ... source of inconsistency in co-ordinate noun phrase bracketing occurs when a non-nominal modiﬁer appears in the coordinate noun phrase. As previously discussed, according to theguidelines the...

Báo cáo khoa học: "Learning Effective Multimodal Dialogue Strategies from Wizard-of-Oz data: Bootstrapping and Evaluation" pot

... taking the average of 4 ques-tions)3 to the number of items presented (DB) foreach modality, using curve fitting. In contrast to linear regression, curve fitting does not assume alinear inductive ... presentation. We partitionthe database feature into 3 bins, taking the first in- tersection point between verbal and multimodal re-ward and the turning point of the multimodal func-tion as discretisation ... moment of online-operation, and tedious hand-crafting of dialogue strategies is omitted. This inde-pendence from large amounts of in- domain dialoguedata allows researchers to apply RL to new appli-cation...

Tài liệu Báo cáo khoa học: "Wikipedia as Sense Inventory to Improve Diversity in Web Search Results" doc

... found in the page for the sense being trained.• TiMBL-inlinks uses the examples found in Wikipedia pages pointing to the sense beingtrained.• TiMBL-all uses both sources of examples. In order to ... H. Roitman, and N. Zwerdling. 2009. En-hancing Cluster Labeling using Wikipedia. In Pro-ceedings of the 32nd international ACM SIGIR con-ference on Research and development in informationretrieval, ... effective to pro-mote diversity in search results? In order to provide an initial answer to thesequestions, we have built a corpus consisting of 40nouns and 100 Google search results per noun, manually...

Tài liệu Báo cáo khoa học: "Using Cross-Entity Inference to Improve Event Extraction" docx

... cross-entity inference for event extraction (including training and testing processes) In the training process, for every entity type in the ACE training corpus, a clustering technique (CLUTO toolkit)3 ... extraction. In Proc. COLING/ACL 2006 Workshop on Annotating and Reasoning about Time and Events.Sydney, Aus-tralia. Jenny Rose Finkel, Trond Grenager and Christopher Manning. 2005. Incorporating ... By using simulated annealing in place of Viterbi de-coding in sequence models such as HMMs, CMMs, and CRFs, it is possible to incorporate non-local structure while preserving tractable inference....

Tài liệu Báo cáo khoa học: "Using Word Support Model to Improve Chinese Input System" ppt

... Chinese in- put system is phonetic and pinyin based ap-proach, because Chinese people are taught to write phonetic and pinyin syllables of each Chi-nese character in primary school. In Chinese, ... systems. In our previous work (Tsai, 2005), a word-pair (WP) identifier was proposed and shown a simple and effective way to improve Chinese input systems by providing tonal and toneless STW ... corresponding pinyin sylla-ble-words. The pinyin syllable-words were translated by phoneme -to- pinyin mappings, such as “ㄩˊ” -to- “ju2.” 2.1 Auto-Generation of WP Database Following (Tsai, 2005),...

Tài liệu Báo cáo khoa học: "A Feature Based Approach to Leveraging Context for Classifying Newsgroup Style Discussion Segments" pptx

... experimented with both ways of defining the history and have not observed any benefit of sequential learning techniques by defining the history for sequential learning in terms of previous messages. ... style interactions. The goal of assess-ing the quality of interactions in that context is to enable the quality and nature of discussions that occur within an on-line discussion board to be ... structure. In particular, the discussion environment used to collect the Weinberger and Fischer corpus inserts prompts into the message buffers before messages are composed in order to structure...

Xem thêm