Introduction

This chapter introduces and motivates the book. It introduces monads as a way to model enriched meanings and motivates enriched meanings as a way to avoid generalizing to the worst case in natural language interpretation. It reviews the three goals of the book: 1. to provide background on the theory of enriched meanings and how to model meaning enrichment formally using category theory, in particular monads; 2. to show the usefulness of the theory by providing new compositional analyses of the three phenomena; and 3. to explore the compositional possibilities for combining the three monads used in these analyses. The chapter also discusses the place of this kind of research in cognitive science. It lists some related literature on monads for natural language interpretation. It also introduces the computational tools and exercises.

The Bound Variable Hierarchy and Donkey Anaphora in Mandarin Chinese

Cheng and Huang (1996) argue that both unselective binding and E-type pronoun strategies are necessary for the interpretation of natural language sentences and claim that there exists a correspondence between two sentence types in Chinese and the two strategies, namely that the interpretation of the “wh … wh” construction (which they call “bare conditional”) employs the unselective binding strategy, while the ruguo ‘if’ and dou ‘all’ conditionals use the E-type pronoun strategy. They also suggest that there is a complementary distribution between bare conditionals and ruguo/dou conditionals in the sense that the latter allows all the NP forms, e.g. (empty) pronouns and definite NPs, except for wh-phrases in their consequent clauses, and can even have a consequent clause with no anaphoric NP in it, while the former permits only the same wh-phrase appearing in both the antecedent clause and the consequent clause. Although we agree with Cheng and Huang on the necessity of the two strategies in natural language interpretation, we see apparent exceptions to the correspondence between sentence types and interpretation strategies and the complementary distribution between wh-phrases and other NPs in bare conditionals and ruguo/dou conditionals. We think that the claimed correspondence and complementary distribution are the default or preferred patterns, or a special case of a more general picture, namely that (i) bare conditionals prefer the unselective binding strategy and the ruguo ‘if’ and dou ‘all’ conditionals, the E-type pronoun strategy; and (ii) wh-phrases are more suitable for being a bound variable, and pronouns are more suitable for being the E-type pronoun. This paper proposes a Bound Variable Hierarchy to help account for the distribution of wh-phrases and pronouns in Chinese conditionals and claims that any deviation from the preferred patterns will require additional contexts or accommodation.

An Emotional Engine for Behavior Simulators

Interpreting, modeling and representing emotions is a key feature of new generation games. This paper describes the first version of the Emotional Engine we have developed as a component of more complex behavior simulators. The purpose of this module is to manage the state and behavior of the characters present in a scene while they interact with a human user. We use preexistent language recognition libraries like Windows™ Speech API, and Kinect™ devices to communicate real humans with artificial characters participating in a virtual scene. The Emotional Engine works upon numeric variables extracted from such devices and calculated after some natural language interpretation process. It then produces numerical results that lead the behavior, modify both the verbal and body language of the characters, and influence the general evolution of the scene that takes place inside the simulator. This paper presents the system architecture and discusses some key components, such as the Language Interpretation and the Body Language Interpreter modules.

ECG Prediction Based on Classification via Neural Networks and Linguistic Fuzzy Logic Forecaster

The paper deals with ECG prediction based on neural networks classification of different types of time courses of ECG signals. The main objective is to recognise normal cycles and arrhythmias and perform further diagnosis. We proposed two detection systems that have been created with usage of neural networks. The experimental part makes it possible to load ECG signals, preprocess them, and classify them into given classes. Outputs from the classifiers carry a predictive character. All experimental results from both of the proposed classifiers are mutually compared in the conclusion. We also experimented with the new method of time series transparent prediction based on fuzzy transform with linguistic IF-THEN rules. Preliminary results show interesting results based on the unique capability of this approach bringing natural language interpretation of particular prediction, that is, the properties of time series.

SPATIAL ANALYSIS IN PUBLIC HEALTH DOMAIN: AN NLP APPROACH

Remote sensing products are effectively used as a tool for decision making in various fields, especially in medical research and health care analyses. GIS is particularly well suited in this context because of its spatial analysis and display capabilities. The integration of RS techniques in public health has been categorised as continuous and discrete strategies where latter is preferred. We have investigated the integration of these approaches through linguistic interpretation of images. In this paper, we propose a framework for direct natural language interpretation of satellite images using probabilistic grammar rules in conjunction with evolutionary computing techniques. Spectral and spatial information has been dynamically combined using adaptive kernel strategy for effective representation of the contextual knowledge. The developed methodology has been evaluated in different querying contexts and investigations revealed that considerable success has been achieved with the procedure. The methodology has also demonstrated to be effective in intelligent interpolation, automatic interpretation as well as attribute, topology, proximity, and semantic analyses.

Formal Pragmatics

In this article, three theoretic frameworks are discussed: optimality-theoretic, game-theoretic, and decision-theoretic pragmatics, the last being based on Ducrot’s argumentation theory. The close similarities between optimality-theoretic and game-theoretic pragmatics are pointed out. Concerning decision-theoretic pragmatics, some arguments are provided demonstrating that an independent, argumentation-theoretic grounding is neither needed nor useful. Rather, it seems more appropriate to incorporate the argumentation-theoretic insights into a general Gricean-oriented theory of natural language interpretation, let it be optimality-theoretic pragmatics or a game-theoretic variant.