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.
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.
The history of semantic networks is almost as long as that of their parent discipline, artificial intelligence. They have formed the basis of many fascinating, yet controversial, discussions in conferences and in the literature, ranging from metaphysics through to complexity theory in computer science. Many excellent surveys of the field have been written, and yet it is our belief that none of them has examined the important link between their use as a formal scheme for knowledge representation and their more heuristic use as an informal tool for thinking. In our consideration of semantic networks as computerized tools, we will discuss three levels of abstraction that we believe can help us understand how semantic networks are used. I.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.