Dan Assaf

Metaphor Identification in Large Texts Corpora

Identifying metaphorical language-use (e.g., sweet child) is one of the challenges facing natural language processing. This paper describes three novel algorithms for automatic metaphor identification. The algorithms are variations of the same core algorithm. We evaluate the algorithms on two corpora of Reuters and the New York Times articles. The paper presents the most comprehensive study of metaphor identification in terms of scope of metaphorical phrases and annotated corpora size. Algorithms’ performance in identifying linguistic phrases as metaphorical or literal has been compared to human judgment. Overall, the algorithms outperform the state-of-the-art algorithm with 71% precision and 27% averaged improvement in prediction over the base-rate of metaphors in the corpus.

Why “dark thoughts” aren't really dark: A novel algorithm for metaphor identification

Distinguishing between literal and metaphorical language is a major challenge facing natural language processing. Heuristically, metaphors can be divided into three general types in which type III metaphors are those involving an adjective-noun relationship (e.g. “dark humor”). This paper describes our approach for automatic identification of type III metaphors. We propose a new algorithm, the Concrete-Category Overlap (CCO) algorithm, that distinguishes between literal and metaphorical use of adjective-noun relationships and evaluate it on two data sets of adjective-noun phrases. Our results point to the superiority of the CCO algorithm to past and contemporary approaches in determining the presence and conceptual significance of metaphors, and provide a better understanding of the conditions under which each algorithm should be applied.

Profiling School Shooters: Automatic Text-Based Analysis

School shooters present a challenge to both forensic psychiatry and law enforcement agencies. The relatively small number of school shooters, their various characteristics, and the lack of in-depth analysis of all of the shooters prior to the shooting add complexity to our understanding of this problem. In this short paper, we introduce a new methodology for automatically profiling school shooters. The methodology involves automatic analysis of texts and the production of several measures relevant for the identification of the shooters. Comparing texts written by 6 school shooters to 6056 texts written by a comparison group of male subjects, we found that the shooters’ texts scored significantly higher on the Narcissistic Personality dimension as well as on the Humilated and Revengeful dimensions. Using a ranking/prioritization procedure, similar to the one used for the automatic identification of sexual predators, we provide support for the validity and relevance of the proposed methodology.

Opposition theory and computational semiotics

Opposition theory suggests that binary oppositions (e.g., high vs. low) underlie basic cognitive and linguistic processes. However, opposition theory has never been implemented in a computational cognitive-semiotics model. In this paper, we present a simple model of metaphor identification that relies on opposition theory. An algorithm instantiating the model has been tested on a data set of 100 phrases comprising adjective-noun pairs in which approximately a half represent metaphorical language-use (e.g., dark thoughts) and the rest literal language-use (e.g., dark hair). The algorithm achieved 89% accuracy in metaphor identification and illustrates the relevance of opposition theory for modelling metaphor processing.

How do we understand the meaning of connotations? A cognitive computational model

Abstract Denotation is the literal sense of a word, while connotation is its extended sense. The current paper presents a cognitive computational model of the adjective’s connotation (e.g., sweet baby). We tested the model by developing a novel algorithm – ConnoSense – that identifies the sense of an attribute’s connotation. More specifically, ConnoSense identifies the sense of an attribute such as in the case of a “sweet smile” where the attribute/adjective “sweet” is used in the sense of “friendly.” Tested on a multiple-choice test of identifying the sense of a connotation (e.g., “dark thoughts”) the algorithm gained 90% accuracy and outperforms two other models that are based on vectorial semantics. These results support the validity of our model. The paper points at the importance of fusing ideas from the semiotics interpretative tradition with experimental psychological knowledge and novel methodologies of computational semantics.

Identifying the location of a concealed object through unintentional eye movements

In some investigative and interrogative contexts, the investigator is seeking to identify the location of an object (e.g., implanted bomb) which is known to a given subject (e.g., a terrorist). In this paper, we present a non-intrusive methodology for uncovering the loci of a concealed object by analyzing the subjects eye movements. Using a combination of eye tracking, psychological manipulation and a search algorithm, we have performed two experiments. In the first experiment, we have gained 58% hit rate in identifying the location of the concealed object and in the second experiment 56% hit rate. The pros and cons of the methodology for forensic investigation are discussed.

Identifying the Meta-Forms of Situations: A Case-Study in Computational Semiotics

Various tasksofcomputingmeaning involve the identification, representationandprocessingof interconnectedandrecurrentpatternsknownassituations,context,framesorforms.Inthispaper, the authors propose a novel computational - semiotics approach for addressing various tasks of situationsemantics.Theapproachreliesonthedual-spacemodelandtherepresentationofasituation basedondomainandfunctionsimilarityofitsconstitutingparts.Theauthorsillustratethisapproach throughaworked-outexampleandtestitbyautomaticallyby(1)Judgingthetruth-valueofsituational propositionsand(2)Generatingexplanationstometaphors. KeywoRdS Cognition and Language, Computational Semiotics, Interdisciplinary Research, Meta-Form, Situation

A cognitively motivated word sense induction algorithm

The way in which word senses are produced and identified is of great interest to cognitive sciences as well as to various applications in natural language processing. In this paper, we present a cognitively inspired algorithm of word sense induction. The algorithm fuses the distributional and perceptual information of words. By drawing on minimal resources - word collocations and their level of concreteness/abstractness - our algorithm automatically produces for each target noun a graph that is an endomap with a maximal number of 50 nodes. This graph represents the major senses associated with the noun. Tested on a word sense disambiguation task and on psychological data, our algorithm gains significant empirical support for its efficiency.