While the study of psychology has offered little in the way of explaining the creative process, Koestler examines the idea that we are at our most creative when rational thought is suspended--for example, in dreams and trancelike states. All who read The Act of Creation will find it a compelling and illuminating book.

The Act of Creation

This paper describes the SemEval 2016 shared task on Aspect Based Sentiment Analysis (ABSA), a continuation of the respective tasks of 2014 and 2015. In its third year, the task provided 19 training and 20 testing datasets for 8 languages and 7 domains, as well as a common evaluation procedure. From these datasets, 25 were for sentence-level and 14 for text-level ABSA; the latter was introduced for the first time as a subtask in SemEval. The task attracted 245 submissions from 29 teams.

https://hal.archives-ouvertes.fr/hal-01838537/document

SemEval-2016 task 5 : aspect based sentiment analysis

This paper describes the fifth year of the Sentiment Analysis in Twitter task. SemEval-2017 Task 4 continues with a rerun of the subtasks of SemEval-2016 Task 4, which include identifying the overall sentiment of the tweet, sentiment towards a topic with classification on a two-point and on a five-point ordinal scale, and quantification of the distribution of sentiment towards a topic across a number of tweets: again on a two-point and on a five-point ordinal scale. Compared to 2016, we made two changes: (i) we introduced a new language, Arabic, for all subtasks, and (ii) we made available information from the profiles of the Twitter users who posted the target tweets. The task continues to be very popular, with a total of 48 teams participating this year.

/pdf/semeval-2017-task-4-sentiment-analysis-in-twitter-5294l6x1f7.pdf

SemEval-2017 Task 4: Sentiment Analysis in Twitter

This paper surveys the current state of the art in Natural Language Generation (NLG), defined as the task of generating text or speech from non-linguistic input. A survey of NLG is timely in view of the changes that the field has undergone over the past two decades, especially in relation to new (usually data-driven) methods, as well as new applications of NLG technology. This survey therefore aims to (a) give an up-to-date synthesis of research on the core tasks in NLG and the architectures adopted in which such tasks are organised; (b) highlight a number of recent research topics that have arisen partly as a result of growing synergies between NLG and other areas of artifical intelligence; (c) draw attention to the challenges in NLG evaluation, relating them to similar challenges faced in other areas of nlp, with an emphasis on different evaluation methods and the relationships between them.

/pdf/survey-of-the-state-of-the-art-in-natural-language-26vdvzdbx0.pdf

Survey of the state of the art in natural language generation: core tasks, applications and evaluation

Metaphor and Thought

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.

/pdf/semeval-2015-task-11-sentiment-analysis-of-figurative-3lv4em4fgn.pdf

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

Just as observing is more than just seeing, comparing is far more than mere matching. It takes understanding, and even inventiveness, to discern a useful basis for judging two ideas as similar in a particular context, especially when our perspective is shaped by an act of linguistic creativity such as metaphor, simile or analogy. Structured resources such as WordNet offer a convenient hierarchical means for converging on a common ground for comparison, but offer little support for the divergent thinking that is needed to creatively view one concept as another. We describe such a means here, by showing how the web can be used to harvest many divergent views for many familiar ideas. These lateral views complement the vertical views of WordNet, and support a system for idea exploration called Thesaurus Rex. We show also how Thesaurus Rex supports a novel, generative similarity measure for WordNet.

Creating Similarity: Lateral Thinking for Vertical Similarity Judgments

Language affords a great many opportunities for the intelligent reuse of linguistic content. Rather than always putting our own thoughts into our own words, we often convey feelings through the words of others, by citing, quoting, mimicking, borrowing, varying or ironically echoing what others have already said. Social networking platforms such as Twitter elevate linguistic reuse into an integral norm of digital interaction. On such platforms, who you follow and what you re-tweet can say as much about you as the clothes you wear or the art you hang on your walls. But not everyone that is worth following is human, and not everything that is worth re-tweeting was first coined by a real person. More and more of the witty and thought-provoking content on Twitter is generated by bots, artificial systems that write their own material and vie for our attention just as humans do. Real people knowingly follow artificial bots for reasons that are subtle and diverse, but a significant reason is surely Twitter itself. This paper explores Twitter as a smart environment for automated wit, and describes the mechanics of a wittily inventive new Twitterbot named @MetaphorMagnet.

https://link.springer.com/content/pdf/10.1007%2F978-3-319-20804-6_63.pdf

Twitter: The Best of Bot Worlds for Automated Wit

Wireless sensor networks (WSNs) have been pushed to the forefront in the past decade, owing to the advert of the Internet of Things. Our research suggests that the reliability and lifetime performance of a typical application in WSNs depends crucially on a set of parameters. In this paper, we implemented our experiments on the nearest closer protocol with the J-Sim simulation tool. We then analyze the closure relationships among the density, reliability and lifetime, and reveal the trade-off among them based on our analysis on the experiment results. Next, we propose five intelligent evaluation models that are applicable to such situations. Our research allows the WSN users to predict the significant evaluation parameters directly from the settings while costly simulations are no longer necessary.

Evaluation Models for the Nearest Closer Routing Protocol in Wireless Sensor Networks

Introspection is a question-led process in which one builds on what one already knows to explore what is possible and plausible. In creative introspection, whether in art or in science, framing the right question is as important as finding the right answer. Presupposition-laden questions are themselves a source of knowledge, and in this paper we show how widely-held beliefs about the world can be dynamically acquired by harvesting such questions from the Web. We show how metaphorical reasoning can be modeled as an introspective process, one that builds on questions harvested from the Web to pose further speculative questions and queries. Metaphor is much more than a knowledge-hungry rhetorical device: it is a conceptual lever that allows a system to extend its model of the world.

Guofu Li

Papers

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

Creating Similarity: Lateral Thinking for Vertical Similarity Judgments

Twitter: The Best of Bot Worlds for Automated Wit

Evaluation Models for the Nearest Closer Routing Protocol in Wireless Sensor Networks

Creative introspection and knowledge acquisition: learning about the world through introspective questions and exploratory metaphors