The primary goal of this study is to assess two approaches for detecting comprehension processes in R-SAT (Reading Strategy Assessment Tool). One approach is based on Latent Semantic Analysis (LSA) while the other is a combination of literal word matching and soundex. A secondary goal is to assess the potential for detecting specific reading comprehension strategies, either in isolation or combination. Participants typed “think-aloud” protocols while reading texts presented on computers. Human judges rated these protocols for the presence of the various reading comprehension strategies. LSA, word, and combined algorithms were compared and the results showed that a combination of both approaches yielded the best results. However, performance of the combined algorithm varied in terms of the type of processes and the grain size of the human coding system. Lastly, the use of reading strategies (either in isolation or combination) is positivity related to students’ Gates–MacGinitie reading comprehension scores, which illustrates the merit of this approach for assessing comprehension skill.

We propose and evaluate five related algorithms that automatically derive limited-size noun vocabularies from text documents of 2,000-30,000 words.The proposed algorithms combine Personalized Page Rank and principles of information maximization, and are applied to the WordNet graph for nouns. For the best-performing algorithm the difference between automatically generated reduced noun lexicons and those created by human writers is approximately 1-2 WordNet edges per lexical item. Our results also indicate the importance of performing word-sense disambiguation with sentence-level context information at the earliest stage of analysis.

This paper presents a semantically grounded method for extracting commonsense knowledge. First, commonsense rules are identified, e.g., one cannot see imaginary objects. Second, those rules are combined with a basic semantic representation in order to infer commonsense knowledge facts, e.g. one cannot see a flying carpet. Further combinations of semantic relations with inferred commonsense facts are proposed and analyzed. Results show that this novel method is able to extract thousands of commonsense facts with little human interaction and high accuracy.

When people interact with language-producing agents (other people or computers), they assume that the shared experience leads to shared representations — of the world, the interaction, and the language used in the interaction. This phenomenon occurs even during interaction with systems that give no evidence of building shared representations. The absence of shared representations leads to errors and delays; alternatively, even simple shared representations can lead to reduced error rates and more efficient interaction. In this talk, we present three case studies: a mobile local business search application that builds no interaction representations; a telephone-based recommendation and review system that builds limited representations of the shared language in the interaction; and computer models of coreference that use shared representations to permit both coreference resolution and referring expression generation. We lay out a range of possibilities for shared representations, show that they can be built incrementally as an interaction progresses, and point to possibilities for future work in probabilistic shared representations for interactive systems.

Negation is present in all human languages and it is used to reverse the polarity of parts of a statement. It is a complex phenomenon that interacts with many other aspects of language. Besides the direct meaning, negated statements often carry a latent positive meaning. Negation can be interpreted in terms of its scope and focus. This paper explores the importance of both scope and focus to capture the meaning of negated statements. Some issues on detecting negation from text are outlined, the forms in which negation occurs are depicted and heuristics to detect its scope and focus are proposed.

The track on applied natural language processing is a forum for researchers working in natural language processing (NLP), computational linguistics (CL), and related areas. The rapid pace of development of online materials, most of them in textual form or text combined with other media, has led to a revived interest for tools capable of understanding, organizing and mining those materials. Novel human-computer interfaces (such as talking heads), can benefit from language understanding and generation techniques. Dialoguebased intelligent tutoring systems require advanced dialogue processing, language understanding and generation components in order to assess students' natural language inputs and provide appropriate feedback. Moreover, language can facilitate human-computer interaction for the handicapped (no typing needed) and elderly leading to an ever increasing user base for computer systems.

In informational terms, a module dedicated to process information always has specific inputs and outputs. It describes a particular process constrained by specific rules. A processing chain can be a serial combination or a parallel combination of such modules. Thus, an architecture of language engineering, each processing chain becomes a particular instantiation of all possible paths. A processing chain is built from a choice of tasks underlying modules that an engineer wants to apply to the text. Therefore, in this perspective, a fundamental question arises: given a set of modules, what are the eligible chains of all combinations of the given modules? This is what we will discuss about in our paper.

The paper argues, briefly, that much work in formal Computational Semantics (alias CompSem ) is not computational at all, and does not attempt to be; there is some mis-description going on here on a large and long-term scale. Moreover, the examples used to support its value for the representation of the meaning of language strings have no place in normal English usage, or their corpora, and this should be better understood. The recent large-scale developments in Natural Language Processing (NLP), such as machine translation or question answering, which are quite successful and undeniably semantic and computational, have made no use of such techniques. Most importantly, the Semantic Web (and Information Extraction techniques generally) now offer the possibility of large scale use of language data so as to achieve concrete results achieved by methods deemed impossible in formal semantics, namely annotation methods that are fundamentally forms of Lewis’ (1970) “markerese.”

Could we enrich speech-act theory to deal with discourse? Wittgenstein and Searle are sceptical. In my view, the primary aim of discourse pragmatics is to analyze the structure and dynamics of language-games with an internal conversational goal. Logic can analyze felicity-conditions of such collective illocutions. For interlocutors obey systems of constitutive rules in conducting descriptive, deliberative, declaratory or expressive dialogues. I will show how to construct speaker-meaning from sentence-meaning, conversational background and maxims. I will also explain how to use the resources of formalisms and mathematical logic and to further develop intensional and illocutionary logics, the logic of attitudes and of action in order to characterize our ability to converse. I will also deal with the nature of intelligent dialogues between man and machines in A.I.

In this paper, we discuss the question of closure conditions for dialogues in three different frameworks: W. C. Mann's DMT framework, Vanderveken's illocutionary theory of discourse and Asher and Lascarides SDRT approach. We are interested in formal frameworks that aim to describe the logical structure of conversations between diversely bounded agents who are — to some extent — rational, intelligent, linguistically competent and who possess some awareness of their environment and some knowledge of the circumstances of their interactions. We use the notion of closure conditions as a benchmark for theory comparison.