The concept of an agent has become important in both Artificial Intelligence (AI) and mainstream computer science. Our aim in this paper is to point the reader at what we perceive to be the most important theoretical and practical issues associated with the design and construction of intelligent agents. For convenience, we divide these issues into three areas (though as the reader will see, the divisions are at times somewhat arbitrary). Agent theory is concerned with the question of what an agent is, and the use of mathematical formalisms for representing and reasoning about the properties of agents. Agent architectures can be thought of as software engineering models of agents;researchers in this area are primarily concerned with the problem of designing software or hardware systems that will satisfy the properties specified by agent theorists. Finally, agent languages are software systems for programming and experimenting with agents; these languages may embody principles proposed by theorists. The paper is not intended to serve as a tutorial introduction to all the issues mentioned; we hope instead simply to identify the most important issues, and point to work that elaborates on them. The article includes a short review of current and potential applications of agent technology.

/pdf/intelligent-agents-theory-and-practice-5dchj7p8pc.pdf

Intelligent Agents: Theory and Practice

Sentiment analysis and opinion mining is the field of study that analyzes people's opinions, sentiments, evaluations, attitudes, and emotions from written language. It is one of the most active research areas in natural language processing and is also widely studied in data mining, Web mining, and text mining. In fact, this research has spread outside of computer science to the management sciences and social sciences due to its importance to business and society as a whole. The growing importance of sentiment analysis coincides with the growth of social media such as reviews, forum discussions, blogs, micro-blogs, Twitter, and social networks. For the first time in human history, we now have a huge volume of opinionated data recorded in digital form for analysis. Sentiment analysis systems are being applied in almost every business and social domain because opinions are central to almost all human activities and are key influencers of our behaviors. Our beliefs and perceptions of reality, and the choices we make, are largely conditioned on how others see and evaluate the world. For this reason, when we need to make a decision we often seek out the opinions of others. This is true not only for individuals but also for organizations. This book is a comprehensive introductory and survey text. It covers all important topics and the latest developments in the field with over 400 references. It is suitable for students, researchers and practitioners who are interested in social media analysis in general and sentiment analysis in particular. Lecturers can readily use it in class for courses on natural language processing, social media analysis, text mining, and data mining. Lecture slides are also available online.

/pdf/sentiment-analysis-and-opinion-mining-8314pykwrf.pdf

Sentiment Analysis and Opinion Mining

The study of computational agents capable of rational behaviour has received a great deal of attention in recent years. Theoretical formalizations of such agents and their implementations have proceeded in parallel with little or no connection between them. Tkis paper explores a particular type of rational agent, a BeliefDesire-Intention (BDI) agent. The primary aim of this paper is to integrate (a) the theoretical foundations of BDI agents from both a quantitative decision-theoretic perspective and a symbolic reasoning perspective; (b) the implementations of BDI agents from an ideal theoretical perspective and a more practical perspective; and (c) the building of large-scale applications based on BDI agents. In particular, an air-trafflc management application will be described from both a theoretical and an implementation perspective.

/pdf/bdi-agents-from-theory-to-practice-4cue39s538.pdf

BDI Agents: From Theory to Practice

From the Publisher:
An agent is an entity with domain knowledge, goals and actions. Multi-agent systems are a set of agents which
interact in a common environment. Multi-agent systems deal with the construction of complex systems involving multiple agents and their coordination. A multi-agent system (MAS) is a distributed computing system with
autonomous interacting intelligent agents that coordinate their actions so as to achieve its goal(s) jointly or competitively.

Introduction to Multiagent Systems

We present a lexicon-based approach to extracting sentiment from text. The Semantic Orientation CALculator (SO-CAL) uses dictionaries of words annotated with their semantic orientation (polarity and strength), and incorporates intensification and negation. SO-CAL is applied to the polarity classification task, the process of assigning a positive or negative label to a text that captures the text's opinion towards its main subject matter. We show that SO-CAL's performance is consistent across domains and in completely unseen data. Additionally, we describe the process of dictionary creation, and our use of Mechanical Turk to check dictionaries for consistency and reliability.

Lexicon-based methods for sentiment analysis

Les relations d’arriere-plan jouent un role important dans le discours et sont tres frequentes dans les corpus tant oraux qu’ecrits Ces relations existent sous deux formes: l’arriere-plan apparaissant avant ou apres le premier plan (respectivement appelees Backgroundforwardet Backgroundbackward) La relation d’arriere-plan a ete parmi les premieres etudiees dans le cadre de la SDRT de (Asher, Lascarides, 2003) et a beneficie d’etudes complementaires dans (Vieu, Prevot, 2004) Cependant, le gros de ces travaux concerne Backgroundbackwardalors que Backgroundforwardest relativement meconnue La similarite de sa fonction discursive avec les adverbiaux locatifs anteposes nous a conduit a traiter Backgroundforwardsur la base des solutions proposees pour ces derniers (Vieu et al, 2005) Ces adverbiaux dont le pouvoir locatif depasse les frontieres de la phrase introduisent des structures discursives complexes En resume, cette structure est composee d’un nouveau topique discursif (topique cadratif) qui est elabore par le constituant de la phrase suivante (ou le constituant complexe du segment) Nous exploitons ici ce mecanisme pour traiter uniformement les differents cas ou les relations d’arriere-plan de type Backgroundforward apparaissent

https://journals.openedition.org/discours/pdf/301

Setting the background in discourse

We provide an account of the alignment of linguistic form and discourse function with respect to English tag questions, adopting as a formal framework Segmented Discourse Representation Theory. SDRT models the discourse function of utterances via their rhetorical connection to the antecedent discourse. We pay particular attention to the prosodic features of tag questions and their contribution to interpretation. This approach to tag questions is appropriate, we argue, as the interpretation of a tag comes down to its rhetorical connection to the host sentence.

/pdf/prosody-and-the-interpretation-of-tag-questions-3rd55za62c.pdf

Prosody and the interpretation of tag questions

Les theories cherchant a capturer la coherence discursive (Mann & Thompson, 1987; Asher & Lascarides, 2003) offrent des cadres theoriques stimulants pour analyser de nombreux phenomenes discursifs. Ils peinent parfois cependant a fournir des definitions de relations combinant precision et robustesse pour des travaux d'annotation a grande echelle permettant, par exemple, de constituer des corpus annotes en relations discursives. Le cas des relations d'Elaboration et d'Arriere-plan constitue une parfaite illustration de ce probleme. La plupart des theories discursives les incluent, parfois sous des noms differents, et l'on pourrait penser que leur definition et la maniere de les reconnaitre est maintenant etablie. Cependant, en depit du fait que ce sont les relations les plus courantes dans les corpus, c'est a leur sujet que les annotateurs ont le plus de problemes. Elles sont souvent prises l'une pour l'autre. Dans cet article nous examinons la source de ces problemes et nous proposons une solution basee sur la distinction d'une relation d'Elaboration d'entite, que nous formalisons en SDRT.

Une formalisation plus précise pour une annotation moins confuse: la relation d'Élaboration d'entité

Types, meanings and coercions in lexical semantics

An important challenge for the automatic understanding of natural language texts is the correct computation of the discourse entities that are mentioned therein—persons, locations, abstract objects, and so on. The problem of mapping linguistic expressions into these underlying entities is known as reference resolution. Recent years of research in computational reference resolution have seen the emergence of machine learning approaches, which are much more robust and better performing than their rule-based predecessors. Unfortunately, perfect performance are still out of reach for these systems. Broadly defined, the aim of this dissertation is to improve on these existing systems by exploring more advanced machine learning models, which are: (i) able to more adequately encode the structure of the problem, and (ii) allow a better use of the information sources that are given to the system. 
Starting with the sub-task of anaphora resolution, we propose to model this task as a ranking problem and no longer as a classification problem (as is done in existing systems). A ranker offers a potentially better way to model this task by directly including the comparison between antecedent candidates as part of its training criterion. We find that the ranker delivers significant performance improvements over classification-based systems, and is also computationally more attractive in terms of training time and learning rate than its rivals. 
The ranking approach is then extended to the larger problem of coreference resolution. To main goal is to see whether the better antecedent selection capabilities offered by the ranking approach can also benefit in the larger coreference resolution task. The extension is two-fold. First, we design various specialized ranker models for different types referential expressions (e.g., pronouns, definite descriptions, proper names). Besides its linguistic appeal, this division of labor has also the potential of learning better model parameters. Second, we augment these rankers with a model that determines the discourse status of mentions and that is used to filter the “non-anaphoric” mentions. As shown by various experiments, this combined strategy results in significant performance improvements over the single-model, classification-based approach on the three main coreference metrics: the standard MUC metric, but also the more representative B3 and CEAF metrics. 
Finally, we show how the task of coreference resolution can be recast as a linear optimization problem. In particular, we use the framework of Integer Linear Programming (ILP) to: (i) combine the predictions of three local models (namely, a standard pairwise coreference classifier, a discourse status classifier, and a named entity classifier) in a joint, global inference, and (ii) integrate various other global constraints (such as transitivity constraints) to better capture the dependencies between coreference decisions. Tested on the ACE datasets, our ILP formulations deliver significant f-score improvements over both a standard pairwise model, and various models that employ the discourse status and a named entity classifiers in a cascade. These improvements were again found to hold across the three different evalution metrics: MUC, B3, and CEAF. The fact that B3 and CEAF scores were also improved is of particular importance, since these two metrics are much less lenient than MUC in terms of precision errors.

Nicholas Asher

Papers

Setting the background in discourse

Prosody and the interpretation of tag questions

Une formalisation plus précise pour une annotation moins confuse: la relation d'Élaboration d'entité

Types, meanings and coercions in lexical semantics

New learning models for robust reference resolution