Understanding Computing through Defining its Lexicon

Бойко Банчев - Понятието пресмятане в широкия му смисъл и неговото присъствие в природата, науката, технологията и други области е свързано с редица неизяснени въпроси. Дори в по-тесните рамки на програмирането и използването на компютри то не е адекватно разбрано. Представяме тезата, че един начин за приближаване към такова разбиране е разкриването на дълбинните структури и отношения, свързани с пресмятането, и на тази основа построяване на речник на пресмятането.

Structured Approaches for Exploring Interpersonal Relationships in Natural Language Text

Human relationships have long been studied by scientists from domains like sociology, psychology, literature, etc. for understanding people's desires, goals, actions and expected behaviors. In this dissertation we study inter-personal relationships as expressed in natural language text. Modeling inter-personal relationships from text finds application in general natural language understanding, as well as real-world domains such as social networks, discussion forums, intelligent virtual agents, etc. We propose that the study of relationships should incorporate not only linguistic cues in text, but also the contexts in which these cues appear. Our investigations, backed by empirical evaluation, support this thesis, and demonstrate that the task benefits from using structured models that incorporate both types of information. We present such structured models to address the task of modeling the nature of relationships between any two given characters from a narrative. To begin with, we assume that relationships are of two types: cooperative and non-cooperative. We first describe an approach to jointly infer relationships between all characters in the narrative, and demonstrate how the task of characterizing the relationship between two characters can benefit from including information about their relationships with other characters in the narrative. We next formulate the relationship-modeling problem as a sequence prediction task to acknowledge the evolving nature of human relationships, and demonstrate the need to model the history of a relationship in predicting its evolution. Thereafter, we present a data-driven method to automatically discover various types of relationships such as familial, romantic, hostile, etc. Like before, we address the task of modeling evolving relationships but don't restrict ourselves to two types of relationships. We also demonstrate the need to incorporate not only local historical but also global context while solving this problem. Lastly, we demonstrate a practical application of modeling inter-personal relationships in the domain of online educational discussion forums. Such forums offer opportunities for its users to interact and form deeper relationships. With this view, we address the task of identifying initiation of such deeper relationships between a student and the instructor. Specifically, we analyze contents of the forums to automatically suggest threads to the instructors that require their intervention. By highlighting scenarios that need direct instructor-student interactions, we alleviate the need for the instructor to manually peruse all threads of the forum and also assist students who have limited avenues for communicating with instructors. We do this by incorporating the discourse structure of the thread through latent variables that abstractly represent contents of individual posts and model the flow of information in the thread. Such latent structured models that incorporate the linguistic cues without losing their context can be helpful in other related natural language understanding tasks as well. We demonstrate this by using the model for a very different task: identifying if a stated desire has been fulfilled by the end of a story.

Metáfora Conceptual e Libras: uma abordagem cognitiva da surdez

O percurso histórico das representações da surdez, da educação de surdos e do estatuto da língua de sinais aponta para a necessidade de uma reflexão sobre as relações entre língua, cognição e cultura. Um estudo direcionado à identificação das estruturas conceptuais subjacentes à língua falada pelos surdos -a Libras- pode contribuir com algumas considerações pertinentes sobre a questão surdez/cultura, além de contribuir para desmistificar possíveis preconceitos relacionados à língua de sinais. A linguística cognitiva (LC), ciência que engloba os aspectos cognitivos envolvidos na significação, a influência do contexto para a compreensão/produção da linguagem e a forma como o mundo é experienciado individualmente e culturalmente, revela-se como um embasamento teórico adequado ao desenvolvimento de tal reflexão, uma vez que abarca dentre suas áreas de interesse o estudo dos mecanismos cognitivos de conceptualização e expressão da realidade, dentre os quais se inserem os modelos cognitivos e culturais, a metáfora e a metonímia conceptuais. Levando-se em conta que na LC a concepção de metáfora, estabelecida pela Teoria da Metáfora Conceptual (TMC), à luz de Lakoff e Johnson (2002[1980]) e Kövecses (2002, 2003, 2005), considera a metáfora como um mecanismo conceptual em que os seres humanos empregam um domínio experiencial mais concreto, estreitamente ligado à experiência com o próprio corpo e o mundo em que vivem, para compreender/conceptualizar um domínio mais abstrato; buscou-se, neste estudo, verificar a aplicabilidade de tal teoria na língua brasileira de sinais (Libras), hipotetizando-se que as metáforas conceptuais podem ser identificadas em qualquer língua, mesmo uma língua visuo-espacial, e que as manifestações metafóricas encontradas na Libras podem refletir as especificidades da cultura surda, bem como aspectos provenientes da cultura ouvinte devido à influência cultural gerada por sua inserção nesta cultura. A pesquisa realizada desenvolveu-se sob abordagem qualitativa/descritiva, com análise de um corpus heterogêneo da Libras, composto por sinais isolados, vídeos e transcrições de interações terapêuticas. Os resultados apontam não só para a manifestação da metáfora conceptual na Libras, como também para a manifestação de aspectos semânticos e fonológicos subjacentes à iconicidade cognitiva nos termos de (Wilcox, P. 2004) da Libras. Trata-se de um levantamento inicial, mas que fornece elementos para alguns questionamentos sobre o aspecto conceptual e cognitivo da iconicidade e sobre o alcance da TMC e sua relação com língua e cultura

一个用于机器人自然语言理解的英语句法分析系统

在低挡微机中速度较慢的串行处理硬设备条件下，利用本文提出的启发式概念，分层搜索和匹配策略以及设置最大搜索长度等方法，可使推理速度提高一个数量级以上．此外，通过引入语义信息，分阶段消除歧义，自顶向下与自底向上相结合，以及把一般疑问句一律变成相应陈述句的方法，解决了自动英语句法分析中的一系列难题，缩小了知识库的规模。

运用神经网络完成汉字句子的格角色分配

According to PDP theory, the author tries to use ANN method in sentence understanding. In input layer, distributed knowledge representation and integrate syntactic, semantic information (of the word in Chinese sentence) and context information are used to complete the case role assignment of six types of Chinese sentence by parallel processing. The model is a four-layer forward network, consisting of input layer, two hidden layers, and output layer(case role layer). In addition, the neural network method and the traditional symbol processing method used in natural language understanding is compared and analyzed, and a conclusion could be made: the neural network should be used as a powerful tool in this area.

Building Autonomous Sensitive Artificial Listeners

This paper describes a substantial effort to build a real-time interactive multimodal dialogue system with a focus on emotional and non-verbal interaction capabilities. The work is motivated by the aim to provide technology with competences in perceiving and producing the emotional and non-verbal behaviours required to sustain a conversational dialogue. We present the Sensitive Artificial Listener (SAL) scenario as a setting which seems particularly suited for the study of emotional and non- verbal behaviour, since it requires only very limited verbal understanding on the part of the machine. This scenario allows us to concentrate on non-verbal capabilities without having to address at the same time the challenges of spoken language understanding, task modeling etc. We first report on three prototype versions of the SAL scenario, in which the behaviour of the Sensitive Artificial Listener characters was determined by a human operator. These prototypes served the purpose of verifying the effectiveness of the SAL scenario and allowed us to collect data required for building system components for analysing and synthesising the respective behaviours. We then describe the fully autonomous integrated real-time system we created, which combines incremental analysis of user behaviour, dialogue management, and synthesis of speaker and listener behaviour of a SAL character displayed as a virtual agent. We discuss principles that should underlie the evaluation of SAL-type systems. Since the system is designed for modularity and reuse, and since it is publicly available, the SAL system has potential as a joint research tool in the affective computing research community.

Quel sens faut-il donner à l’universalité de l’herméneutique chez Gadamer? : sa légitimité face aux critiques de Jürgen Habermas

La distance historique qui nous sépare de la publication de Vérité et méthode permet une meilleure intelligence de l’aspect universel de l’herméneutique de Hans-Georg Gadamer qui a suscité tant de débats immédiatement après la parution de son ouvrage. L’herméneute a en effet pu, dans plusieurs textes qu’il a écrits au cours des dernières décennies, préciser sa conception et mieux attester cette universalité, notamment en l’associant à l’universalité de la rhétorique elle-même. Un nouveau regard porté sur les divers débats suscités par cette prétention de l’universalité de l’herméneutique permet aussi de s’en faire une idée plus claire et limpide. Le présent mémoire se penche sur le sens à donner à l’universalité de l’herméneutique en tenant compte des sections décisives de Vérité et méthode qui y sont consacrées, des écrits plus tardifs de Gadamer sur la question et de la littérature secondaire afin de voir si cette prétention à l’universalité peut être défendue face aux critiques formulées par Jürgen Habermas. Nous soutiendrons dans ce mémoire que c’est le cas, mais aussi que la critique de Habermas a aidé Gadamer à mieux formuler et faire comprendre l’universalité de l’herméneutique. C’est précisément en tenant compte de l’apport de ceux qui pensent autrement que s’atteste l’universalité de l’herméneutique.

Chatterbox challenge as a test-bed for synthetic emotions

Chatterbox Challenge is an annual web-based contest for artificial conversational systems, ACE. The 2010 instantiation was the tenth consecutive contest held between March and June in the 60th year following the publication of Alan Turing’s influential disquisition ‘computing machinery and intelligence’. Loosely based on Turing’s viva voca interrogator-hidden witness imitation game, a thought experiment to ascertain a machine’s capacity to respond satisfactorily to unrestricted questions, the contest provides a platform for technology comparison and evaluation. This paper provides an insight into emotion content in the entries since the 2005 Chatterbox Challenge. The authors find that synthetic textual systems, none of which are backed by academic or industry funding, are, on the whole and more than half a century since Weizenbaum’s natural language understanding experiment, little further than Eliza in terms of expressing emotion in dialogue. This may be a failure on the part of the academic AI community for ignoring the Turing test as an engineering challenge.

Testing Turing's five minutes, parallel-paired imitation game

Purpose – The purpose of this paper is to consider Turing's two tests for machine intelligence: the parallel-paired, three-participants game presented in his 1950 paper, and the “jury-service” one-to-one measure described two years later in a radio broadcast. Both versions were instantiated in practical Turing tests during the 18th Loebner Prize for artificial intelligence hosted at the University of Reading, UK, in October 2008. This involved jury-service tests in the preliminary phase and parallel-paired in the final phase. Design/methodology/approach – Almost 100 test results from the final have been evaluated and this paper reports some intriguing nuances which arose as a result of the unique contest. Findings – In the 2008 competition, Turing's 30 per cent pass rate is not achieved by any machine in the parallel-paired tests but Turing's modified prediction: “at least in a hundred years time” is remembered. Originality/value – The paper presents actual responses from “modern Elizas” to human interrogators during contest dialogues that show considerable improvement in artificial conversational entities (ACE). Unlike their ancestor – Weizenbaum's natural language understanding system – ACE are now able to recall, share information and disclose personal interests.

Automatic identification of discourse markers in dialogues: An in-depth study of like and well

The lexical items like and well can serve as discourse markers (DMs), but can also play numerous other roles, such as verb or adverb. Identifying the occurrences that function as DMs is an important step for language understanding by computers. In this study, automatic classifiers using lexical, prosodic/positional and sociolinguistic features are trained over transcribed dialogues, manually annotated with DM information. The resulting classifiers improve state-of-the-art performance of DM identification, at about 90% recall and 79% precision for like (84.5% accuracy, κ = 0.69), and 99% recall and 98% precision for well (97.5% accuracy, κ = 0.88). Automatic feature analysis shows that lexical collocations are the most reliable indicators, followed by prosodic/positional features, while sociolinguistic features are marginally useful for the identification of DM like and not useful for well. The differentiated processing of each type of DM improves classification accuracy, suggesting that these types should be treated individually.

LEGOLANG: técnicas de deconstrucción aplicadas a las tecnologías del lenguaje humano

El objetivo de este proyecto se basa en la necesidad de replantearse la filosofía clásica del TLH para adecuarse tanto a las fuentes disponibles actualmente (datos no estructurados con multi-modalidad, multi-lingualidad y diferentes grados de formalidad) como a las necesidades reales de los usuarios finales. Para conseguir este objetivo es necesario integrar tanto la comprensión como la generación del lenguaje humano en un modelo único (modelo LEGOLANG) basado en técnicas de deconstrucción de la lengua, independiente de su aplicación final y de la variante de lenguaje humano elegida para expresar el conocimiento.

Ontology-based protein-protein interactions extraction from literature using the hidden vector state model

This paper proposes a novel framework of incorporating protein-protein interactions (PPI) ontology knowledge into PPI extraction from biomedical literature in order to address the emerging challenges of deep natural language understanding. It is built upon the existing work on relation extraction using the Hidden Vector State (HVS) model. The HVS model belongs to the category of statistical learning methods. It can be trained directly from un-annotated data in a constrained way whilst at the same time being able to capture the underlying named entity relationships. However, it is difficult to incorporate background knowledge or non-local information into the HVS model. This paper proposes to represent the HVS model as a conditionally trained undirected graphical model in which non-local features derived from PPI ontology through inference would be easily incorporated. The seamless fusion of ontology inference with statistical learning produces a new paradigm to information extraction.

A novel framework of training hidden Markov support vector machines from lightly-annotated data

Natural language understanding (NLU) aims to map sentences to their semantic mean representations. Statistical approaches to NLU normally require fully-annotated training data where each sentence is paired with its word-level semantic annotations. In this paper, we propose a novel learning framework which trains the Hidden Markov Support Vector Machines (HM-SVMs) without the use of expensive fully-annotated data. In particular, our learning approach takes as input a training set of sentences labeled with abstract semantic annotations encoding underlying embedded structural relations and automatically induces derivation rules that map sentences to their semantic meaning representations. The proposed approach has been tested on the DARPA Communicator Data and achieved 93.18% in F-measure, which outperforms the previously proposed approaches of training the hidden vector state model or conditional random fields from unaligned data, with a relative error reduction rate of 43.3% and 10.6% being achieved.

К Вопросу Проектирования Онтологоуправляемой ИС Обработки ЕЯО

В статье рассмотрен формальный подход и основное содержание методологии формализованного проектирования.

Learning Data-Driven Models of Non-Verbal Behaviors for Building Rapport Using an Intelligent Virtual Agent

There is a growing societal need to address the increasing prevalence of behavioral health issues, such as obesity, alcohol or drug use, and general lack of treatment adherence for a variety of health problems. The statistics, worldwide and in the USA, are daunting. Excessive alcohol use is the third leading preventable cause of death in the United States (with 79,000 deaths annually), and is responsible for a wide range of health and social problems. On the positive side though, these behavioral health issues (and associated possible diseases) can often be prevented with relatively simple lifestyle changes, such as losing weight with a diet and/or physical exercise, or learning how to reduce alcohol consumption. Medicine has therefore started to move toward finding ways of preventively promoting wellness, rather than solely treating already established illness. Evidence-based patient-centered Brief Motivational Interviewing (BMI) interven- tions have been found particularly effective in helping people find intrinsic motivation to change problem behaviors after short counseling sessions, and to maintain healthy lifestyles over the long-term. Lack of locally available personnel well-trained in BMI, however, often limits access to successful interventions for people in need. To fill this accessibility gap, Computer-Based Interventions (CBIs) have started to emerge. Success of the CBIs, however, critically relies on insuring engagement and retention of CBI users so that they remain motivated to use these systems and come back to use them over the long term as necessary. Because of their text-only interfaces, current CBIs can therefore only express limited empathy and rapport, which are the most important factors of health interventions. Fortunately, in the last decade, computer science research has progressed in the design of simulated human characters with anthropomorphic communicative abilities. Virtual characters interact using humans’ innate communication modalities, such as facial expressions, body language, speech, and natural language understanding. By advancing research in Artificial Intelligence (AI), we can improve the ability of artificial agents to help us solve CBI problems. To facilitate successful communication and social interaction between artificial agents and human partners, it is essential that aspects of human social behavior, especially empathy and rapport, be considered when designing human-computer interfaces. Hence, the goal of the present dissertation is to provide a computational model of rapport to enhance an artificial agent’s social behavior, and to provide an experimental tool for the psychological theories shaping the model. Parts of this thesis were already published in [LYL+12, AYL12, AL13, ALYR13, LAYR13, YALR13, ALY14].