Báo cáo khoa học: "Combining a Chinese Thesaurus with a Chinese Dictionary" potx

Tài liệu Báo cáo khoa học: "Combining Lexical Semantic Resources with Question & Answer Archives for Translation-Based Answer Finding" doc

... training dataare comparatively smaller than WAQ and WAQA,they however yield comparable results. The linearcombination of datasets (WAQ+WAQA+LSRLin)yields statistically signiﬁcant performance ... statistical word as-sociations which are trained on parallel monolin-gual corpora. The major drawback of this ap-proach lies in the limited availability of truly par-allel monolingual corpora. ... synonym pairs extracted fromWordNet, and an additional parallel corpus of En-glish words translating to the same Arabic term in a parallel English-Arabic corpus.Similar work has also been...

Báo cáo khoa học: "Combining Speech Retrieval Results with Generalized Additive Models" pptx

... channelwas down-sampled to 8kHz and segmented using anavailable broadcast news segmenter. Because we didnot have a pronunciation dictionary which coveredthe transcribed audio, we automatically ... does assume that they belong to an in-terval scale. Similarly, the arithmetic mean of MAPassumes AP has interval scale. As Robertson (2006)has pointed out, it is in no sense clear that AP(prior ... large and yet not statistically signiﬁcant (it isin fact a larger mean improvement than several otherbaseline combination approaches which are signiﬁ-cant improvements. This may suggest that...

Báo cáo khoa học: "Ordering Prenominal Modiﬁers with a Reranking Approach" potx

... Modiﬁers with a Reranking ApproachJenny LiuMIT CSAILjyliu@csail.mit.eduAria HaghighiMIT CSAILme@aria42.comAbstractIn this work, we present a novel approachto the generation task of ordering ... We canexpress this as a real-valued feature:φ(B,H, x)=count in training data of alln-grams present in xSee Table 2 for a summary of our features. Manyof the features we use are similar ... Switchboard, WSJ, and NANC.The test data was held out and each approach was trained on the rest of the data. Winning scores are in bold. Thenumber of features used during training for the MAXENT approach...

Báo cáo khoa học: "Building Deep Dependency Structures with a Wide-Coverage CCG Parser" ppt

... the data. If a word ap-pears at least K times in the data, the supertaggeronly considers categories that appear in the word’scategory set, rather than all lexical categories.The second parsing ... Adjoining Grammaras an alternative to context-free grammar, andhere we use another “mildly context-sensitive” for-malism, Combinatory Categorial Grammar (CCG,Steedman (2000)), which arguably ... standard, and computed precisionand recall ﬁgures over the dependencies. Recall that a dependency is deﬁned as a 4-tuple: a head of a functor, a functor category, an argument slot, and a head...

Báo cáo khoa học: "Approximating Context-Free Grammars with a Finite-State Calculus" docx

... grammar. An exam- ples is: S ~ al S S~al A1 S-+anS S-+anAn A~ -+ a~ X A2 + al A2 An -~ al An X-+e A1 -+ a2 Az A1 ~ an A1 A2 -+ a2 X A2 ~ an A2 An -+ a2 A, ~ An ~ an X Here the grammar ... context-free grammars because context-free languages are the smallest class of formal language that can realistically be applied to the analysis of natural language. Techniques such as restriction ... ac. uk Abstract Although adequate models of human language for syntactic analysis and semantic interpretation are of at least context- free complexity, for applications such as speech...

Báo cáo khoa học: "Unsupervised Event Coreference Resolution with Rich Linguistic Features" potx

... param-eters associated with an event z, φ a notation forall model parameters, and X a notation for all ran-dom variables that represent observable features.2Given a document collection annotated ... dia of Philosophy (Fall 2009Edition), Edward N. Zalta (ed.), http://plato.stanford.edu/archives/fall2009/entries/davidson/.Srini Narayanan and Sanda Harabagiu. 2004. Ques-tion Answering Based ... vari-ous applications such as topic detection and track-ing (Allan et al., 1998), information extraction(Humphreys et al., 1997), question answering(Narayanan and Harabagiu, 2004), textual...

Báo cáo khoa học: "Joint Bilingual Sentiment Classification with Unlabeled Parallel Corpora" potx

... unlabeled data and its automatic Chinese translation, and vice versa. Although not as significant as those with parallel data, we can still obtain improvements using the pseudo-parallel data, ... Banea, Rada Mihalcea, and Janyce Wiebe. 2010. Multilingual subjectivity: Are more languages better? In Proceedings of COLING’10. Carmen Banea, Rada Mihalcea, Janyce Wiebe, and Samer Hassan. ... labeled data, with and without the unlabeled parallel data. From Figure 5 for setting 1, we can see that the translated data can be helpful given the labeled data and even the unlabeled data,...

Báo cáo khoa học: "Training Conditional Random Fields with Multivariate Evaluation Measures" potx

... forward and backwardViterbi algorithm, which is almost the same ascalculating Eq. 3 with a variant of the forward-backward algorithm (Sha and Pereira, 2003). Thesame numerical optimization ... non-linear measures such as F-score, while all of the above criteria achieve op-timization based on the linear combination of av-erage accuracies, or error rates, rather than a giventask-speciﬁc ... Chunking and NERobtained with this parameter initialization setting.When we compare Tables 1 and 2, we ﬁnd thatthe initialization with the MAP parameter valuesfurther improves performance.6 Related...

Báo cáo khoa học: "Reducing SMT Rule Table with Monolingual Key Phrase" potx

... reason isthat f3may appears in various phrases, such as“, accept France ’s invitation”.While f2almost always appears in f1, indicatingthat the variable X may not be replaced with otherwords ... C-value, a measurementof automatic term recognition, to score sourcephrases. A source phrase is regarded as a keyphrase if its score greater than a threshold. Notethat a source phrase is either a ... Technology, Chinese Academy of Sciences, Beijing, China{lvyajuan, liuqun}@ict.ac.cnAbstractThis paper presents an effective approachto discard most entries of the rule table forstatistical machine...

Báo cáo khoa học: "Combining a Chinese Thesaurus with a Chinese Dictionary" potx

... evaluation, on the one hand, can be .carried out automatically in a large scale, on the other hand, can suggest what the direct evaluation entails in some way because that none appropriate ... their accuracy rates and loss rates manually. Tab. 5 lists the results. Ta~ num. 0 2 Aver. accuracy(%) Aver. loss(%) 94.6 7.3 90.1 5.2 87.6 2.1 Tab. 5. Average accuracy and loss rates ... Chinese thesaurus with the Chinese dictionary into such a resource, by tagging the entries in the thesaurus with appropriate senses in the dictionary, meanwhile assigning appropriate semantic...

Xem thêm