Virginia Francisco

Ontological reasoning to configure emotional voice synthesis

The adequate representation of emotions in affective computing is an important problem and the starting point of studies related to emotions. There are different approaches for representing emotions, selecting one of this existing methods depends on the purpose of the application. Another problem related to emotions is the amount of different emotional concepts which makes it very difficult to find the most specific emotion to be expressed in each situation. This paper presents a system that reasons with an ontology of emotions implemented with semantic web technologies. Each emotional concept is defined in terms of a range of values along the three-dimensional space of emotional dimensions. The capabilities for automated classification and establishing taxonomical relations between concepts are used to provide a bridge between an unrestricted input and a restricted set of concepts for which particular rules are provided. The rules applied at the end of the process provide configuration parameters for a system for emotional voice synthesis.

EmoTales: creating a corpus of folk tales with emotional annotations

Emotions are inherent to any human activity, including human–computer interactions, and that is the reason why recognizing emotions expressed in natural language is becoming a key feature for the design of more natural user interfaces. In order to obtain useful corpora for this purpose, the manual classification of texts according to their emotional content has been the technique most commonly used by the research community. The use of corpora is widespread in Natural Language Processing, and the existing corpora annotated with emotions support the development, training and evaluation of systems using this type of data. In this paper we present the development of an annotated corpus oriented to the narrative domain, called EmoTales, which uses two different approaches to represent emotional states: emotional categories and emotional dimensions. The corpus consists of a collection of 1,389 English sentences from 18 different folk tales, annotated by 36 different people. Our model of the corpus development process includes a post-processing stage performed after the annotation of the corpus, in which a reference value for each sentence was chosen by taking into account the tags assigned by annotators and some general knowledge about emotions, which is codified in an ontology. The whole process is presented in detail, and revels significant results regarding the corpus such as inter-annotator agreement, while discussing topics such as how human annotators deal with emotional content when performing their work, and presenting some ideas for the application of this corpus that may inspire the research community to develop new ways to annotate corpora using a large set of emotional tags.

Ontological reasoning for improving the treatment of emotions in text

With the advent of affective computing, the task of adequately identifying, representing and processing the emotional connotations of text has acquired importance. Two problems facing this task are addressed in this paper: the composition of sentence emotion from word emotion, and a representation of emotion that allows easy conversion between existing computational representations. The emotion of a sentence of text should be derived by composition of the emotions of the words in the sentence, but no method has been proposed so far to model this compositionality. Of the various existing approaches for representing emotions, some are better suited for some problems and some for others, but there is no easy way of converting from one to another. This paper presents a system that addresses these two problems by reasoning with two ontologies implemented with Semantic Web technologies: one designed to represent word dependency relations within a sentence, and one designed to represent emotions. The ontology of word dependency relies on roles to represent the way emotional contributions project over word dependencies. By applying automated classification of mark-up results in terms of the emotion ontology the system can interpret unrestricted input in terms of a restricted set of concepts for which particular rules are provided. The rules applied at the end of the process provide configuration parameters for a system for emotional voice synthesis.

Inferring the scope of negation in biomedical documents

In the last few years negation detection systems for biomedical texts have been developed successfully. In this paper we present a system that finds and annotates the scope of negation in English sentences. It infers which words are affected by negations by browsing dependency syntactic structures. Thus, firstly a greedy algorithm detects negation cues, like no or not. And secondly the scope of these negation cues is computed. We tested the system over the Bioscope corpus, annotated with negation, obtaining competitive results. The system presented in this paper can be accessed via web.

Assessing the Novelty of Computer-Generated Narratives Using Empirical Metrics

Novelty is a key concept to understand creativity. Evaluating a piece of artwork or other creation in terms of novelty requires comparisons to other works and considerations about the elements that have been reused in the creative process. Human beings perform this analysis intuitively, but in order to simulate it using computers, the objects to be compared and the similarity metrics to be used should be formalized and explicitly implemented. In this paper we present a study on relevant elements for the assessment of novelty in computer-generated narratives. We focus on the domain of folk-tales, working with simple plots and basic narrative elements: events, characters, props and scenarios. Based on the empirical results of this study we propose a set of computational metrics for the automatic assessment of novelty. Although oriented to the implementation of our own story generation system, the measurement methodology we propose can be easily generalized to other creative systems.

Two Different Approaches to Automated Mark Up of Emotions in Text

This paper presents two different approaches to automated marking up of texts with emotional labels. For the first approach a corpus of example texts previously annotated by human evaluators is mined for an initial assignment of emotional features to words. This results in a List of Emotional Words (LEW) which becomes a useful resource for later automated mark up. The mark up algorithm in this first approach mirrors closely the steps taken during feature extraction, employing for the actual assignment of emotional features a combination of the LEW resource and WordNet for knowledge-based expansion of words not occurring in LEW. The algorithm for automated mark up is tested against new text samples to test its coverage. The second approach mark up texts during their generation. We have a knowledge base which contains the necessary information for marking up the text. This information is related to actions and characters. The algorithm in this case employ the information of the knowledge database and decides the correct emotion for every sentence. The algorithm for automated mark up is tested against four different texts. The results of the two approaches are compared and discussed with respect to three main issues: relative adequacy of each one of the representations used, correctness and coverage of the proposed algorithms, and additional techniques and solutions that may be employed to improve the results.

A feasibility study on low level techniques for improving parsing accuracy for spanish using maltparser

In the last years dependency parsing has been accomplished by machine learning–based systems showing great accuracy but usually under 90% for Labelled Attachment Score (LAS) Maltparser is one of such systems Machine learning allows to obtain parsers for every language having an adequate training corpus Since generally such systems can not be modified the following question arises: Can we beat this 90% LAS by using better training corpora? Some previous work points that high level techniques are not sufficient for building more accurate training corpora Thus, by analyzing the words that are more frequently incorrectly attached or labelled, we study the feasibility of some low level techniques, based on n–version parsing models, in order to obtain better parsing accuracy.

Assessing the influence of personal preferences on the choice of vocabulary for natural language generation

Referring expression generation is the part of natural language generation that decides how to refer to the entities appearing in an automatically generated text. Lexicalization is the part of this process which involves the choice of appropriate vocabulary or expressions to transform the conceptual content of a referring expression into the corresponding text in natural language. This problem presents an important challenge when we have enough knowledge to allow more than one alternative. In those cases, we need some heuristics to decide which alternatives are more appropriate in a given situation. Whereas most work on natural language generation has focused on a generic way of generating language, in this paper we explore personal preferences as a type of heuristic that has not been properly addressed. We empirically analyze the TUNA corpus, a corpus of referring expression lexicalizations, to investigate the influence of language preferences in how people lexicalize new referring expressions in different situations. We then present two corpus-based approaches to solve the problem of referring expression lexicalization, one that takes preferences into account and one that does not. The results show a decrease of 50% in the similarity error against the reference corpus when personal preferences are used to generate the final referring expression.

Dependency Analysis and CBR to Bridge the Generation Gap in Template-Based NLG

The present paper describes how dependency analysis can be used to automatically extract from a corpus a set of cases - and an accompanying vocabulary - which enable a template-based generator to achieve reasonable coverage over conceptual messages beyond the explicit scope of the templates defined in it. Details are provided on the actual process of partial automation that has been applied to obtain the case base, together with the various ingredients of the template-based generator, which applies case-based reasoning techniques. This module resorts to the taxonomy of concepts in WordNet to compute similarity between concepts involved in the texts. A case retrieval net is used as a memory model. The set of data to be converted into text acts as a query to the system. The process of solving a given query may involve several retrieval processes - to obtain a set of cases that together constitute a good solution for transcribing the data in the query as text messages - and a process of knowledge-intensive adaptation which resorts to a knowledge base to identify appropriate substitutions and completions for the concepts that appear in the cases, using the query as a source. We describe this case-based solution for selecting an appropriate set of templates to render a given set of data as text, we present numeric results of system performance in the domain of press articles, and we discuss its advantages and shortcomings.

EMOTAG: AN APPROACH TO AUTOMATED MARKUP OF EMOTIONS IN TEXTS

This paper presents an approach to the automated markup of texts with emotional labels. The approach considers two possible representations of emotions in parallel: emotional categories (emotional tags used to refer to emotions) and emotional dimensions (measures that try to model the essential aspects of emotions numerically). For each representation, a corpus of example texts previously annotated by human evaluators is mined for an initial assignment of emotional features to words. This results in a list of emotional words (LEW) which becomes a useful resource for later automated markup. The algorithm proposed for the automated markup of text closely mirrors the steps taken during feature extraction, employing a combination of the LEW resource and the ANEW word list for the actual assignment of emotional features, and WordNet for knowledge‐based expansion of words not occurring in either and an ontology of emotional categories. The algorithm for automated markup is tested and the results are discussed with respect to three main issues: the relative adequacy of each of the representations used, correctness and coverage of the proposed algorithm, and additional techniques and solutions that may be employed to improve the results. The average percentage of success obtained by our approach when it marks up with emotional dimensions is around 80% and when it marks up with emotional categories is around 50%. The main contribution of the approach presented in this paper is that it allows dimensions and categories at different levels of abstraction to operate simultaneously during markup.