Many teaching practices implicitly assume that conceptual knowledge can be abstracted from the situations in which it is learned and used. This article argues that this assumption inevitably limits the effectiveness of such practices. Drawing on recent research into cognition as it is manifest in everyday activity, the authors argue that knowledge is situated, being in part a product of the activity, context, and culture in which it is developed and used. They discuss how this view of knowledge affects our understanding of learning, and they note that conventional schooling too often ignores the influence of school culture on what is learned in school. As an alternative to conventional practices, they propose cognitive apprenticeship (Collins, Brown, & Newman, in press), which honors the situated nature of knowledge. They examine two examples of mathematics instruction that exhibit certain key features of this approach to teaching.

/pdf/situated-cognition-and-the-culture-of-learning-3pg6ch1r4f.pdf

Situated Cognition and the Culture of Learning

Statistical approaches to processing natural language text have become dominant in recent years This foundational text is the first comprehensive introduction to statistical natural language processing (NLP) to appear The book contains all the theory and algorithms needed for building NLP tools It provides broad but rigorous coverage of mathematical and linguistic foundations, as well as detailed discussion of statistical methods, allowing students and researchers to construct their own implementations The book covers collocation finding, word sense disambiguation, probabilistic parsing, information retrieval, and other applications

/pdf/foundations-of-statistical-natural-language-processing-1ou5e6c2q6.pdf

Foundations of Statistical Natural Language Processing

The automated categorization (or classification) of texts into predefined categories has witnessed a booming interest in the last 10 years, due to the increased availability of documents in digital form and the ensuing need to organize them. In the research community the dominant approach to this problem is based on machine learning techniques: a general inductive process automatically builds a classifier by learning, from a set of preclassified documents, the characteristics of the categories. The advantages of this approach over the knowledge engineering approach (consisting in the manual definition of a classifier by domain experts) are a very good effectiveness, considerable savings in terms of expert labor power, and straightforward portability to different domains. This survey discusses the main approaches to text categorization that fall within the machine learning paradigm. We will discuss in detail issues pertaining to three different problems, namely, document representation, classifier construction, and classifier evaluation.

/pdf/machine-learning-in-automated-text-categorization-e4pkjhyj3r.pdf

Machine learning in automated text categorization

An important part of our information-gathering behavior has always been to find out what other people think. With the growing availability and popularity of opinion-rich resources such as online review sites and personal blogs, new opportunities and challenges arise as people now can, and do, actively use information technologies to seek out and understand the opinions of others. The sudden eruption of activity in the area of opinion mining and sentiment analysis, which deals with the computational treatment of opinion, sentiment, and subjectivity in text, has thus occurred at least in part as a direct response to the surge of interest in new systems that deal directly with opinions as a first-class object.

This survey covers techniques and approaches that promise to directly enable opinion-oriented information-seeking systems. Our focus is on methods that seek to address the new challenges raised by sentiment-aware applications, as compared to those that are already present in more traditional fact-based analysis. We include material on summarization of evaluative text and on broader issues regarding privacy, manipulation, and economic impact that the development of opinion-oriented information-access services gives rise to. To facilitate future work, a discussion of available resources, benchmark datasets, and evaluation campaigns is also provided.

/pdf/opinion-mining-and-sentiment-analysis-3v5ya3qqiw.pdf

Opinion Mining and Sentiment Analysis

Merchants selling products on the Web often ask their customers to review the products that they have purchased and the associated services. As e-commerce is becoming more and more popular, the number of customer reviews that a product receives grows rapidly. For a popular product, the number of reviews can be in hundreds or even thousands. This makes it difficult for a potential customer to read them to make an informed decision on whether to purchase the product. It also makes it difficult for the manufacturer of the product to keep track and to manage customer opinions. For the manufacturer, there are additional difficulties because many merchant sites may sell the same product and the manufacturer normally produces many kinds of products. In this research, we aim to mine and to summarize all the customer reviews of a product. This summarization task is different from traditional text summarization because we only mine the features of the product on which the customers have expressed their opinions and whether the opinions are positive or negative. We do not summarize the reviews by selecting a subset or rewrite some of the original sentences from the reviews to capture the main points as in the classic text summarization. Our task is performed in three steps: (1) mining product features that have been commented on by customers; (2) identifying opinion sentences in each review and deciding whether each opinion sentence is positive or negative; (3) summarizing the results. This paper proposes several novel techniques to perform these tasks. Our experimental results using reviews of a number of products sold online demonstrate the effectiveness of the techniques.

/pdf/mining-and-summarizing-customer-reviews-3kfih6aknk.pdf

Mining and summarizing customer reviews

The non-uniqueness of semantic solutions: Polysemy

As the text databases available to users become larger and more heterogeneous, genre becomes increasingly important for computational linguistics as a complement to topical and structural principles of classification. We propose a theory of genres as bundles of facets, which correlate with various surface cues, and argue that genre detection based on surface cues is as successful as detection based on deeper structural properties.

Automatic Detection of Text Genre

L'A. examine les transferts de significations en anglais, operation dans laquelle des noms de propriete sont transferes dans de nouveaux noms qui denotent des proprietes auxquelles ils correspondent fonctionnellement. C'est cette operation qui est responsable du nouveau sens du predicat parked out back dans l'enonce I am parked out back, ainsi que des alternances lexicales representees en polysemie systematique

Transfers of Meaning

It is generally assumed that the "lexical component" of a grammar may be treated on the analogue of the syntac­ tic and phonological components, as a device that pairs words with specifications of the things and classes of things that they can normally be used to refer to; if an item can be used to refer to more than one extension, then, it must be accorded more than one lexical entry. We begin by showing how these assumptions come to grief over the prob­ lems posed by the phenomenon of polysemy, when one word, like chicken, is used to refer at one time to a kind of bird and at another to a kind of meat. It is argued, first that the inclusion of multiple lexical entries leads to undesirable complications in the syntax, and second that pragmatic schemata that generate multiple uses must be inde­ pendently available, since the same phenomena appear in ostensive reference. An account of "deferred ostension" is presented, in which it is shown why you can point at some things to identify others; this account is then extended to the multiple uses of "descriptive terms." We proceed to argue that with descriptions, there is no way to tell which of the uses of a word is specified by the rules of language, either in practice or in principle; the semantics/pragmatics distinction cannot be drawn. In that case, we argue, the idealization to the knowledge of the ideal speaker-listener in a perfectly homogeneous speech-community is considerably more pernicious for semantics than for syntax or phonology, as we must pre­ sume as well a community in which extralinguistic beliefs and practices are uniform. We conclude that it is more reasonable to describe the speaker's knowledge of wordmeanings as part of his knowledge of the (heterogeneous) collective beliefs of the community, which we can idealize as his "system of normal beliefs," borrowing our model from game theory. Against this idealization, we show, it is possible to explain a number of disparate linguistic phenom­ ena, such as speaker judgments that some word uses are "acceptable," the phenomena associated with "partial moti­ vation," metaphorical word-uses, and change in meaning. Adviser: Professor D. Terence Langendoen Reproduced with permission of the copyright owner. Further reproduction prohibited without permission.

The pragmatics of reference

https://link.springer.com/content/pdf/10.1007/BF00984721.pdf

Geoffrey Nunberg

Papers

The non-uniqueness of semantic solutions: Polysemy

Automatic Detection of Text Genre

Transfers of Meaning

The pragmatics of reference

Indexicality and deixis