Tài liệu Báo cáo khoa học: "Learning Event Durations from Event Descriptions" docx

... more fine-grained event duration in-formation, viz., the most likely temporal units of event durations (cf. (Rieger 1974)’s ORDER-HOURS, ORDERDAYS). For each original event annotation, ... learning event durations. 3.1 Local Context For a given event, the local context features in-clude a window of n tokens to its left and n to-kens to its right, as well as the event itself, ... information in the event s syntactic envi-ronment is very important in deciding the dura-tions of events. For example, there is a difference in the durations of the “watch” events in the phrases...

Tài liệu Báo cáo khoa học: "Learning to Translate with Multiple Objectives" doc

... M(h)): remove h from L6: else if (M(h)  M(h∗)): remove h from L; seth∗= h7: end for8: Add h∗to Frontier Set F9: for each h in L do10: if (M(h∗)  M(h)): remove h from L11: end ... here; testset trends are similar but notincluded due to space constraints.75 from www.kecl.ntt.co.jp/icl/lirg/ribes6 from www.umd.edu/˜snover/tercom7An aside: For comparing optimization methods, ... hy-pothesis space using lattices (Macherey et al., 2008).How to compute Pareto points directly from latticesis an interesting open research question. (2) Thebinary distinction between pareto...

Tài liệu Báo cáo khoa học: "Learning Syntactic Verb Frames Using Graphical Models" doc

... illustratehow our feature sets are extracted from CONLL-formatted data (Nivre et al., 2007). The CONLLformat is a common language for comparing output from dependency parsers: each lexical item ... from the VALEX lexicon’s data set,which was used in previous studies (Sun and Korho-nen, 2009; Preiss et al., 2007) and facilitates com-parison with that resource. This data set is drawn from ... diathesis alternations(i.e. semantically-motivated alternations betweenpairs of SCFs) and a mapping from surface framesto the underlying predicate-argument structure. In-formation about verb subcategorization...

Tài liệu Báo cáo khoa học: "Learning to Find Translations and Transliterations on the Web" doc

... through language links for training and testing. We obtained a total of 155,310 article pairs, from which we then randomly selected 13,150 and 2,181 titles as seeds to obtain the training and ... data. Since we are using Wikipedia bilingual titles as the gold standard, we exclude any snippets from the wikipedia.org domain, so that we are not using Wikipedia article content in both training ... The approach involves using a small set of terms and translations to obtain mixed-code snippets from a search engine, and automatically annotating the snippets with tags and features for training...

Tài liệu Báo cáo khoa học: "Learning the Latent Semantics of a Concept from its Deﬁnition" pptx

... 2012.c2012 Association for Computational LinguisticsLearning the Latent Semantics of a Concept from its DefinitionWeiwei GuoDepartment of Computer Science,Columbia University,New York, NY, ... discover more overlapping words. How-ever, exact word matching is lossy. Below are twodefinitions from WN:bank#n#1: a financial institution that accepts depositsand channels the money into lending ... leading to a very low similarity score.Accordingly we are interested in extracting latentsemantics from sense definitions to improve elesk.However, the challenge lies in that sense defini-tions are...

Tài liệu Báo cáo khoa học: "Learning to Follow Navigational Directions" pdf

... follows closely from their work. Their approach can incorpo-rate expert supervision into the reward functionin a similar manner to this paper, but is also ableto learn effectively from environment ... direc-tions. Where traditional models learn from linguistic annotation or word distri-butions, our approach is grounded in theworld, learning by apprenticeship from routes through a map paired with ... Reinforcement learning formapping instructions to actions. In ACL-IJCNLP’09.James Richard Curran. 2003. From Distributional toSemantic Similarity. Ph.D. thesis, University of Ed-inburgh.Charles Fillmore....

Tài liệu Báo cáo khoa học: "Learning Word-Class Lattices for Deﬁnition and Hypernym Extraction" doc

... taxo-nomic relation (term pairs are taken from Word-Net (Miller et al., 1990)); then they parse the sen-tences, and automatically extract patterns from theparse trees. Finally, they train ... ofword lattices that we use to model tex-tual definitions. Lattices are learned from a dataset of definitions from Wikipedia.Our method is applied to the task of def-inition and hypernym extraction ... hypernym extractionmethods in the literature do not extract hypernyms from definitional sentences, like we do, but rather from specific patterns like “X such as Y”. There-fore a direct comparison...

Tài liệu Báo cáo khoa học: "Learning Word Vectors for Sentiment Analysis" ppt

... datasetof Pang and Lee (2004), which contains subjectivesentences from movie review summaries and objec-tive sentences from movie plot summaries. This task2Dataset and further details are ... imbalance in ratings presentin review collections. This weighting prevents theoverall distribution of document ratings from affect-ing the estimate of document ratings in which a par-ticular ... us-ing 25,000 movie reviews from IMDB. Becausesome movies receive substantially more reviewsthan others, we limited ourselves to including atmost 30 reviews from any movie in the collection.We...

Tài liệu Báo cáo khoa học: "Learning Hierarchical Translation Structure with Linguistic Annotations" ppt

... phrase.3.2 Grammar Extraction From every word-aligned sentence-pair and its la-bel chart, we extract SCFG rules as those of Figure2. Binary rules are extracted from adjoining syn-chronous spans ... and Chinese as tar-get. The data for the ﬁrst three language pairs arederived from parliament proceedings sourced from the Europarl corpus (Koehn, 2005), with WMT-07 development and test data ... include investigating the impact of hierar-chical phrases for our models as well as any gains from additional features in the log-linear decodingmodel.Smoothing the HR-SCFG grammar estimatescould...

Tài liệu Báo cáo khoa học: "Learning Sub-Word Units for Open Vocabulary Speech Recognition" doc

... the OOV detectortraining set is different from the LVCSR training set.We also use a hybrid LVCSR system, combin-ing word and sub-word units obtained from ei-ther our approach or a state-of-the-art ... lexicon includesresulting sub-words – ranging from unigrams to 5-gram phones, and the 83K word lexicon.5.3 EvaluationWe obtain confusion networks from both the wordand hybrid LVCSR systems. ... 3.2).9Our baseline results differ from Parada et al. (2010). Whenimplementing the lexicon baseline, we discovered that their hy-brid units were mistakenly derived from text containing testOOVs....

Xem thêm