Báo cáo khoa học: "Bootstrapping Coreference Resolution Using Word Associations" potx

... Manning. 2008.Enforcing transitivity in coreference resolution. InHLT ’08, pages 45–48.Aria Haghighi and Dan Klein. 2007. Unsupervised coreference resolution in a nonparametric bayesianmodel. ... Roukos. 2004. AMention-Synchronous Coreference Resolution Algo-rithm Based on the Bell Tree. In ACL ’04, pages 135–142.Xiaoqiang Luo. 2005. On coreference resolution perfor-mance metrics. ... June 19-24, 2011.c2011 Association for Computational LinguisticsBootstrapping Coreference Resolution Using Word AssociationsHamidreza Kobdani, Hinrich Sch¨utze, Michael Schiehlen and Hans...

Tài liệu Báo cáo khoa học: "Improving Pronoun Resolution Using Statistics-Based Semantic Compatibility Information" doc

... presented an unsupervisedapproach to coreference resolution, which minedthe co-referring NP pairs with similar predicate-arguments from a large corpus using a bootstrappingmethod.However, ... apparent improvement forthe overall pronoun resolution. Indeed, existinglearning-based approaches to anaphor resolution have performed reasonably well using limitedand shallow knowledge (e.g., ... (he & she) resolution. The experiments were done on the newswire do-main, using MUC corpus (Wall Street Journal ar-ticles). The training was done on 150 documentsfrom MUC-6 coreference data...

Báo cáo khoa học: "Unsupervised Coreference Resolution in a Nonparametric Bayesian Model" potx

... commonly used to evalu-ate coreference systems on a within-document basis.Since our system relies on sampling, all results areaveraged over ﬁve random runs.3 Coreference Resolution ModelsIn this ... approach to coreference reso-lution which models both global entity iden-tity across a corpus as well as the sequen-tial anaphoric structure within each docu-ment. While most existing coreference ... generativemodel of a document corpus which naturally con-nects these two processes.Most recent coreference resolution work has fo-cused on the task of deciding which mentions (nounphrases) in a document...

Báo cáo khoa học: "Spoken Dialogue Management Using Probabilistic Reasoning" potx

... Spoken Dialogue Management Using Probabilistic ReasoningNicholas Roy and Joelle Pineau and Sebastian ThrunRobotics InstituteCarnegie ... InstituteCarnegie Mellon UniversityPittsburgh, PA 15213AbstractSpoken dialogue managers have beneﬁtedfrom using stochastic planners such asMarkov Decision Processes (MDPs). How-ever, so far, MDPs do not ... rewards with rewards conditioned onobservations as well:The observations consist of a set of keywordswhich are extracted from the speech utterances.The POMDP plans in belief space; each beliefconsists...

Báo cáo khoa học: "Japanese Morphological Analyzer using Word " doc

... Algorithm JTAG selects the correct sequence of words using connective-cost, the number of co- occurrences, the priority of words, and the length of words. The precise description of the algolithm ... added unregistered words to the dictionaries, changed the costs of registered words, and supplied the information of the co-occurrence of words. The changes in the costs of words caused a small ... Without new registered words, the ratio is 95.6%, so unrecognized words caused an error in 4.2% of the onversions :urrence ~nal words Sentences Errors Unrecognized Words 4.2% 52% Co-occurrence...

Báo cáo khoa học: "Conﬁdence Measure for Word Alignment" potx

... alsointroduce many word alignment errors.The example in Figure 1 shows the word align-ment of the given Chinese and English sentencepair, where the English words following each Chi-nese word is its ... learned based on word alignment.In this paper we introduce a conﬁdence mea-sure for word alignment, which is robust to extraor missing words in the bilingual sentence pairs,as well as word alignment ... lexical translation probability of thealigned word pair with the translation probabilitiesof all the target words given the source word. If a word t occurs N times in the target sentence, forany...

Báo cáo khoa học: "Adaptive Language Modeling for Word Prediction" potx

... number of words in the prediction window. Wefocus on 5 -word prediction windows. Many com-mercial devices provide optimized input for the mostcommon words (called core vocabulary) and offer word ... word contributes to therelevance of the word. If a word was used somewhatrecently, we would expect to see the word again. Wefollow Bellegarda (2000) in using an exponentiallydecayed cache with ... ofeach topic using a similarity function. We determinethe weight of each word in the current document us-ing frequency, recency, and topical salience.The recency of use of a word contributes...

Tài liệu Báo cáo khoa học: "Bootstrapping Path-Based Pronoun Resolution" doc

... learneddecisions of the resolution classiﬁer. Withoutpath coreference knowledge, a resolution processwould resolve the pronouns in (1) and (2) thesame way. Indeed, coreference resolution researchhas ... Related Work Coreference resolution is generally conducted asa pairwise classiﬁcation task, using various con-straints and preferences to determine whether two33expressions corefer. Coreference ... pronoun resolution classiﬁer. Signiﬁcant gains in performanceare observed on several datasets.1 IntroductionPronoun resolution is a difﬁcult but vital part of theoverall coreference resolution...

Tài liệu Báo cáo khoa học: "Grammar Error Correction Using Pseudo-Error Sentences and Domain Adaptation" pdf

... CRF models aretrained using the alignment results as superviseddata.2.2 Insertion / DeletionSince an insertion can be regarded as replacing anempty word with an actual word, and deletion is ... output words (similar to the trans-lation models of PBSMT). The latter measure theﬂuency of the output word sequence (similar to lan-guage models).The mapping features are all binary. The focusingphrase ... andmethod.• TRG: The models were trained using only thereal-error corpus (baseline).• SRC: Trained using only the pseudo-error corpus.• ALL: Trained using the real-error and pseudo-error corpora...

Tài liệu Báo cáo khoa học: "Identifying Text Polarity Using Random Walks" pptx

... W is aset of word / part-of-speech pairs for all the wordsin WordNet. E is the set of edges connectingeach pair of synonymous words. Nodes represent word/ pos pairs rather than words because ... WordNet with a 5-long sequence “good, sound, heavy, big, bad”. Agiven word w may be more connected to one setof words (e.g., positive words), yet have a shorterpath connecting it to one word ... theirmethod only using adjectives.Hu and Liu (2004) use WordNet synonyms andantonyms to predict the polarity of words. Forany word, whose polarity is unknown, they searchWordNet and a list...

Xem thêm