Inference and Categorization
نویسندگان
چکیده
In the general framework of natural language sentence understanding, categorization appears as useful for two main purposes: (1) categories are needed in order to account for the ability to cope with a virtually infinite set of sentences, (2) understanding implies the ability to infer; now, drawing the appropriate conclusions cannot be derived on a case-by-case basis but on the basis of
منابع مشابه
Categorization vs. Inference: Shift in Attention or in Representation?
Recently it has been found that people that learn through inference create qualitatively different cognitive representations than those who learn through categorization. The present study addresses the question of whether the findings supporting this claim generalize to a design where both learning tasks have a probabilistic relation between each stimulus cue and the category label. It was show...
متن کاملSituational information contributes to object categorization and inference.
Three experiments demonstrated that situational information contributes to the categorization of functional object categories, as well as to inferences about these categories. When an object was presented in the context of setting and event information, categorization was more accurate than when the object was presented in isolation. Inferences about the object similarly became more accurate as...
متن کاملA probabilistic model of cross-categorization.
Most natural domains can be represented in multiple ways: we can categorize foods in terms of their nutritional content or social role, animals in terms of their taxonomic groupings or their ecological niches, and musical instruments in terms of their taxonomic categories or social uses. Previous approaches to modeling human categorization have largely ignored the problem of cross-categorizatio...
متن کاملAn analysis of textual inference in German customer emails
Human language allows us to express the same meaning in various ways. Recognizing that the meaning of one text can be inferred from the meaning of another can be of help in many natural language processing applications. One such application is the categorization of emails. In this paper, we describe the analysis of a real-world dataset of manually categorized customer emails written in the Germ...
متن کاملA Practical Guide to Inference in Simulation Models
This paper introduces a categorization of simulation models. It provides an explicit overview of the steps that lead to a simulation model. We highlight the advantages and disadvantages of various simulation approaches by examining how they advocate different ways of constructing simulation models. To this end, it discusses a number of relevant methodological issues, such as how realistic simul...
متن کاملExact Inference for Multi-label Classification using Sparse Graphical Models
This paper describes a parameter estimation method for multi-label classification that does not rely on approximate inference. It is known that multi-label classification involving label correlation features is intractable, because the graphical model for this problem is a complete graph. Our solution is to exploit the sparsity of features, and express a model structure for each object by using...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2002