John A. Barnden

Metaphor and metonymy: Making their connections more slippery

Abstract This paper continues the debate about how to distinguish metaphor from metonymy, and whether this can be done. It examines some of the differences that have been alleged to exist, and augments the already existing doubt about them. The main differences addressed are the similarity/contiguity distinction and the issue of whether source-target links are part of the message in metonymy or metaphor. In particular, the paper argues that metaphorical links can always be used metonymically and regarded as contiguities, and conversely that two particular, central types of metonymic contiguity essentially involve similarity. The paper also touches briefly on how metaphor and metonymy interact with domains, frames, etc. and on the role of imaginary identification/categorization of target as/under source items. With the possible exception of this last issue, the paper suggests that no combination of the alleged differences addressed can serve cleanly to categorize source/target associations into metaphorical ones and metonymic ones. It also suggests that it can be more profitable to analyse utterances at the level of the dimensions involved in the differences than at the higher level of metaphor and metonymy as such.

Encoding Techniques for Complex Information Structures in Connectionist Systems

Two general information-encoding techniques called ‘relative-position encoding’ and ‘pattern-similarity association’ are presented. They are claimed to be a convenient basis for the connectionist implementation of complex, short-term information processing of the sort needed in commonsense reasoning, semantic/pragmatic interpretation of natural language utterances, and other types of high-level cognitive processing. The relationships of the techniques to other connectionist information-structuring methods, and also to methods used in computers, are discussed in detail. The rich interrelationships of these other connectionist and computer methods are also clarified. We detail the particular, simple forms that the relative-position encoding and pattern-similarity association techniques take in our own connectionist system, called Conposit, in order to clarify some issues and to provide evidence that the techniques are indeed useful in practice.

SemEval-2015 Task 11: Sentiment Analysis of Figurative Language in Twitter

This report summarizes the objectives and evaluation of the SemEval 2015 task on the sentiment analysis of figurative language on Twitter (Task 11). This is the first sentiment analysis task wholly dedicated to analyzing figurative language on Twitter. Specifically, three broad classes of figurative language are considered: irony, sarcasm and metaphor. Gold standard sets of 8000 training tweets and 4000 test tweets were annotated using workers on the crowdsourcing platform CrowdFlower. Participating systems were required to provide a fine-grained sentiment score on an 11-point scale (-5 to +5, including 0 for neutral intent) for each tweet, and systems were evaluated against the gold standard using both a Cosinesimilarity and a Mean-Squared-Error measure.

Belief Ascription, Metaphor, and Intensional Identification

This article discusses the extension of ViewGen, an algorithm derived for belief ascription, to the areas of intensional object identification and metaphor. ViewGen represents the beliefs of agents as explicit, partitioned proposition sets known as environments. Environments are convenient, even essential, for addressing important pragmatic issues of reasoning. The article concentrates on showing that the transfer of informotion in metophors, intensional object identification, and ordinary, nonmetaphorical belief ascription can all be seen OS different manifestations of a single environment-amalgomatian process. The article also briefly discusses the extension of ViewGen to speech-act processing and the addition of a heuristic-based, relevance-determination procedure. and justifies the partitioning approach to belief ascription.

Emotions in autonomous agents: comparative analysis of mechanisms and functions

Emotion mechanisms are often used in artificial agents as a method of improving action selection. Comparisons between agents are difficult due to a lack of unity between the theories of emotion, tasks of agents and types of action selection utilised. A set of architectural qualities is proposed as a basis for making comparisons between agents. An analysis of existing agent architectures that include an emotion mechanism can help to triangulate design possibilities within the space outlined by these qualities. With this in mind, twelve autonomous agents incorporating an emotion mechanism into action selection are selected for analysis. Each agent is dissected using these architectural qualities (the agent architecture, the action selection mechanism, the emotion mechanism and emotion state representation, along with the emotion model it is based on). This helps to place the agents within an architectural space, highlights contrasting methods of implementing similar theoretical components, and suggests which architectural aspects are important to performance of tasks. An initial framework is introduced, consisting of a series of recommendations for designing emotion mechanisms within artificial agents, based on correlations between emotion roles performed and the aspects of emotion mechanisms used to perform those roles. The conclusion discusses how problems with this type of research can be resolved and to what extent development of a framework can aid future research.

An Implemented Context System that Combines Belief Reasoning, Metaphor-Based Reasoning and Uncertainty Handling

An implemented context-based reasoning system called ATT-Meta is sketched. The system can perform both reasoning about beliefs of agents and metaphor-based reasoning. In particular, it can perform metaphor-based reasoning about beliefs and reasoning acts. The metaphor-based reasoning and belief reasoning facilities are fully integrated into a general framework for uncertain reasoning. This framework allows for uncertain reasoning and conflict resolution within individual contexts, uncertainty in individual inter-context bridging rules, conflict resolution between the effects of different bridging rules, and conflict-resolution across context boundaries when argumentation inside a context conflicts with argumentation outside.

Overcoming rule-based rigidity and connectionist limitations through massively-parallel case-based reasoning

Abstract Symbol manipulation as used in traditional Artificial Intelligence has been criticized by neural net researchers for being excessively inflexible and sequential. On the other hand, the application of neural net techniques to the types of high-level cognitive processing studied in traditional artificial intelligence presents major problems as well. We claim that a promising way out of this impasse is to build neural net models that accomplish massively parallel case-based reasoning. Case-based reasoning, which has received much attention recently, is essentially the same as analogy-based reasoning, and avoids many of the problems leveled at traditional artificial intelligence. Further problems are avoided by doing many strands of case-based reasoning in parallel, and by implementing the whole system as a neural net. In addition, such a system provides an approach to some aspects of the problems of noise, uncertainty and novelty in reasoning systems. We are accordingly modifying our current neural net system (Conposit), which performs standard rule-based reasoning, into a massively parallel case-based reasoning version.

Domain-transcending mappings in a system for metaphorical reasoning

We illustrate how the use of metaphorical views for reasoning with metaphor requires the mapping of information such as event shape, event rate and mental/emotional states from the source domain to the target domain. Such mappings are domain-independent and can be implemented by means of rules we call View Neutral Mapping Adjuncts (VNMAs). We give a list of the main VNMAs that appear to be required, and show how they can be incorporated into a pre-existing system (ATT-Meta) for metaphorical reasoning.

Reasoning in metaphor understanding: the ATT-Meta approach and system

A detailed approach has been developed for core aspects of the task of understanding a broad class of metaphorical utterances. The utterances in question are those that depend on known metaphorical mappings but that nevertheless contain elements not mapped by those mappings. A reasoning system has been implemented that partially instantiates the theoretical approach. The system, called ATT Meta, will be demonstrated. The paper briefly indicates how the system works, and outlines some specific aspects of the system, approach and the overall project.

Exploitation in Affect Detection in Open-Ended Improvisational Text

We report progress on adding affect-detection to a program for virtual dramatic improvisation, monitored by a human director. We have developed an affect-detection module to control an automated virtual actor and to contribute to the automation of directorial functions. The work also involves basic research into how affect is conveyed through metaphor. The project contributes to the application of sentiment and subjectivity analysis to the creation of emotionally believable synthetic agents for interactive narrative environments.