Báo cáo khoa học: "Latent variable models of selectional preference" potx
... data. Latent variable models that use E M for infer- ence can be very sensitive to the number of latent variables chosen. For example, the performance of ROOTH-EM worsens quickly if the number of clusters ... top- ical structure of documents can be adapted to learn probabilistic models of selectional prefer ence. These models are especially effective for estimat- ing plaus...
Ngày tải lên: 07/03/2014, 22:20
... Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, pages 620–628, Suntec, Singapore, 2-7 August 2009. c 2009 ACL and AFNLP Latent Variable Models of Concept-Attribute ... between the top 10 concepts of C(w) and any of the gold-standard concepts, or if C(w) is empty. The overalll precision of a given model is the average of the DRR scores o...
Ngày tải lên: 30/03/2014, 23:20
... type of phrase contains most of interesting properties of phrases, such as emergence or inversion of se- mantic orientations. In order to capture the properties of semantic orientations of phrases, ... into the models to capture the properties of phrases. Through experiments, we showed that the proposed latent variable models work well in the classification of semantic or...
Ngày tải lên: 17/03/2014, 22:20
Báo cáo khoa học: "HIDDEN UNDERSTANDING MODELS OF NATURAL LANGUAGE" ppt
... states of each of the two models are unseen and must be inferred from the words. The problem of language understanding, then, is to recover the most likely meaning structure given a sequence of ... 92]. Hidden understanding models are capable of learning a variety of meaning representations, ranging from simple domain-specific representations, to ones at a level of deta...
Ngày tải lên: 08/03/2014, 07:20
Báo cáo khoa học: "Evaluating Distributional Models of Semantics for Syntactically Invariant Inference" doc
... the selectional preferences of words. The vector representation of a word in context depends on the inverse selectional prefer- ences of its dependents, and the selectional pref- erences of its ... Penn Department of Computer Science University of Toronto Toronto, ON, M5S 3G4, Canada {jcheung,gpenn}@cs.toronto.edu Abstract A major focus of current work in distri- butional...
Ngày tải lên: 17/03/2014, 22:20
Báo cáo khoa học: "Vector-based Models of Semantic Composition" ppt
... achieves. As a result of the assumption of symmetry, both these models are ‘bag of words’ models and word order insensitive. Relaxing the assumption of sym- metry in the case of the simple additive ... function of the tensor product of u and v, then we obtain multi- plicative models: p = Cuv (4) where C is a tensor of rank 3, which projects the tensor product of u and...
Ngày tải lên: 23/03/2014, 17:20
Báo cáo khoa học: "Cognitively Plausible Models of Human Language Processing" ppt
... developing cognitively plausible models of human language processing. Developing computational models is of scientific importance in so far as models are im- plemented theories: models of language process- ing ... psycholinguis- tics is often oblivious of work in computational linguistics (CL). To test their theories, psycholin- guists construct computational models of hu-...
Ngày tải lên: 30/03/2014, 21:20
Báo cáo khoa học: "Real-Time Correction of Closed-Captions" potx
... were made up of 1.37M words and 0.17M words, respectively. 2. A phoneme based confusion matrix was used for scoring the alignment of each word of the vocabulary with every other word of the same vocabulary. ... into consideration and the fact that 48% of the words were common to both lists. On this basis, we have constructed an alternate list of 10 words comprised of the most li...
Ngày tải lên: 08/03/2014, 03:20
Báo cáo khoa học: "Automating the Acquisition of Bilingual Terminology" potx
... group consists of 334 NPs which it would not be able to extract because of one or a combination of errors in one of the preprocessing steps. Section 5.3 contains a detailed analysis of these errors. ... classes of fundamental counter-examples. These are the four classes of errors due to preprocessing. 1. Incorrect alignment of text segments accounts for 6% of the erro...
Ngày tải lên: 09/03/2014, 01:20
Báo cáo khoa học: "Interactive Discourse: Influence of Problem Context " potx
... critical to the study of language in gener- al, and to the construction of computer systems that can co~nunicate with people in particular. Of course, the issue of the influence of "problem ... construction of computer-based natural language processing systems will address some of the issues of "how" and that all of the panelists will consider the prior...
Ngày tải lên: 17/03/2014, 19:20