To build Sounding Board, we develop a system architecture that is capable of accommodating dialog strategies that we designed for socialbot conversations. The architecture consists of a multi-dimensional language understanding module for analyzing user utterances, a hierarchical dialog management framework for dialog context tracking and complex dialog control, and a language generation process that realizes the response plan and makes adjustments for speech synthesis. Additionally, we construct a new knowledge base to power the socialbot by collecting social chat content from a variety of sources. An important contribution of the system is the synergy between the knowledge base and the dialog management, i.e., the use of a graph structure to organize the knowledge base that makes dialog control very efficient in bringing related content to the discussion. Using the data collected from Sounding Board during the competition, we carry out in-depth analyses of socialbot conversations and user ratings which provide valuable insights in evaluation methods for socialbots. We additionally investigate a new approach for system evaluation and diagnosis that allows scoring individual dialog segments in the conversation. Finally, observing that socialbots suffer from the issue of shallow conversations about topics associated with unstructured data, we study the problem of enabling extended socialbot conversations grounded on a document. To bring together machine reading and dialog control techniques, a graph-based document representation is proposed, together with methods for automatically constructing the graph. Using the graph-based representation, dialog control can be carried out by retrieving nodes or moving along edges in the graph. To illustrate the usage, a mixed-initiative dialog strategy is designed for socialbot conversations on news articles.

Association learning is a rule based machine learning and data mining technique that finds important relations between variables or features in a data set. Unlike conventional association algorithms measuring degrees of similarity, association rule learning identifies hidden correlations in databases by applying some measure of interestingness to generate an association rule for new searches.

Walk-based models have shown their unique advantages in knowledge graph (KG) reasoning by achieving state-of-the-art performance while allowing for explicit visualization of the decision sequence. However, the sparse reward signals offered by the KG during a traversal are often insufficient to guide a sophisticated reinforcement learning (RL) model. An alternate approach to KG reasoning is using traditional symbolic methods (e.g., rule induction), which achieve high precision without learning but are hard to generalize due to the limitation of symbolic representation. In this paper, we propose to fuse these two paradigms to get the best of both worlds. Our method leverages high-quality rules generated by symbolic-based methods to provide reward supervision for walk-based agents. Due to the structure of symbolic rules with their entity variables, we can separate our walk-based agent into two sub-agents thus allowing for additional efficiency. Experiments on public datasets demonstrate that walk-based models can benefit from rule guidance significantly.

Traditionally, industry solutions for building a task-oriented dialog system have relied on helping dialog authors define rule-based dialog managers, represented as dialog flows. While dialog flows are intuitively interpretable and good for simple scenarios, they fall short of performance in terms of the flexibility needed to handle complex dialogs. On the other hand, purely machine-learned models can handle complex dialogs, but they are considered to be black boxes and require large amounts of training data. In this demonstration, we showcase Conversation Learner, a machine teaching tool for building dialog managers. It combines the best of both approaches by enabling dialog authors to create a dialog flow using familiar tools, converting the dialog flow into a parametric model (e.g., neural networks), and allowing dialog authors to improve the dialog manager (i.e., the parametric model) over time by leveraging user-system dialog logs as training data through a machine teaching interface.

Decision making in real-life scenarios may often be modeled as an optimization problem. It requires the consideration of various attributes like human preferences and thinking, which constrain achieving the optimal value of the problem objectives. The value of the objectives may be maximized or minimized, depending on the situation. Numerous times, the values of these problem parameters are in linguistic form, as human beings naturally understand and express themselves using words. These problems are therefore termed as linguistic optimization problems (LOPs), and are of two types, namely single objective linguistic optimization problems (SOLOPs) and multi-objective linguistic optimization problems (MOLOPs). In these LOPs, the value of the objective function(s) may not be known at all points of the decision space, and therefore, the objective function(s) as well as problem constraints are linked by the if-then rules. Tsukamoto inference method has been used to solve these LOPs; however, it suffers from drawbacks. As, the use of linguistic information inevitably calls for the utilization of computing with words (CWW), and therefore, 2-tuple linguistic model based solution methodologies were proposed for LOPs. However, we found that 2-tuple linguistic model based solution methodologies represent the semantics of the linguistic information using a combination of type-1 fuzzy sets and ordinal term sets. As, the semantics of linguistic information are best modeled using the interval type-2 fuzzy sets, hence we propose solution methodologies for LOPs based on CWW approach of perceptual computing, in this paper. The perceptual computing based solution methodologies use a novel design of CWW engine, called the perceptual reasoning (PR). PR in the current form is suitable for solving SOLOPs and, hence, we have also extended it to the MOLOPs.

This book explains and explores the principal techniques of Data Mining, the automatic extraction of implicit and potentially useful information from data, which is increasingly used in commercial, scientific and other application areas. It focuses on classification, association rule mining and clustering. Each topic is clearly explained, with a focus on algorithms not mathematical formalism, and is illustrated by detailed worked examples. The book is written for readers without a strong background in mathematics or statistics and any formulae used are explained in detail. It can be used as a textbook to support courses at undergraduate or postgraduate levels in a wide range of subjects including Computer Science, Business Studies, Marketing, Artificial Intelligence, Bioinformatics and Forensic Science.

Human vision is able to compensate imperfections in sensory inputs from the real world by reasoning based on prior knowledge about the world. Machine learning has had a significant impact on computer vision due to its inherent ability in handling imprecision, but the absence of a reasoning framework based on domain knowledge limits its ability to interpret complex scenarios. We propose semi-lexical languages as a formal basis for dealing with imperfect tokens provided by the real world. The power of machine learning is used to map the imperfect tokens into the alphabet of the language and symbolic reasoning is used to determine the membership of input in the language. Semi-lexical languages also have bindings that prevent the variations in which a semi-lexical token is interpreted in different parts of the input, thereby leaning on deduction to enhance the quality of recognition of individual tokens. We present case studies that demonstrate the advantage of using such a framework over pure machine learning and pure symbolic methods.

A major goal of machine learning is to create techniques that abstract away irrelevant information. The generalisation property of standard Learning Classifier System (LCS) removes such information at the feature level but not at the feature interaction level. Code Fragments (CFs), a form of tree-based programs, introduced feature manipulation to discover important interactions, but they often contain irrelevant information, which causes structural inefficiency. XOF is a recently introduced LCS that uses CFs to encode building blocks of knowledge about feature interaction. This paper aims to optimise the structural efficiency of CFs in XOF. We propose two measures to improve constructing CFs to achieve this goal. Firstly, a new CF-fitness update estimates the applicability of CFs that also considers the structural complexity. The second measure we can use is a niche-based method of generating CFs. These approaches were tested on Even-parity and Hierarchical problems, which require highly complex combinations of input features to capture the data patterns. The results show that the proposed methods significantly increase the structural efficiency of CFs, which is estimated by the rule "generality rate". This results in faster learning performance in the Hierarchical Majority-on problem. Furthermore, a user-set depth limit for CF generation is not needed as the learning agent will not adopt higher-level CFs once optimal CFs are constructed.

Existential rules are a positive fragment of first-order logic that generalizes function-free Horn rules by allowing existentially quantified variables in rule heads. This family of languages has recently attracted significant interest in the context of ontology-mediated query answering. Forward chaining, also known as the chase, is a fundamental tool for computing universal models of knowledge bases, which consist of existential rules and facts. Several chase variants have been defined, which differ on the way they handle redundancies. A set of existential rules is bounded if it ensures the existence of a bound on the depth of the chase, independently from any set of facts. Deciding if a set of rules is bounded is an undecidable problem for all chase variants. Nevertheless, when computing universal models, knowing that a set of rules is bounded for some chase variant does not help much in practice if the bound remains unknown or even very large. Hence, we investigate the decidability of the k-boundedness problem, which asks whether the depth of the chase for a given set of rules is bounded by an integer k. We identify a general property which, when satisfied by a chase variant, leads to the decidability of k-boundedness. We then show that the main chase variants satisfy this property, namely the oblivious, semi-oblivious (aka Skolem), and restricted chase, as well as their breadth-first versions. This paper is under consideration for publication in Theory and Practice of Logic Programming.

Have you ever wondered how your personal assistant (e.g: Siri) is built? Do you want to build your own? Let's talk about Natural Language Processing. NLP is an interdisciplinary field concerned with the interactions between computers and human natural languages (e.g: English) -- speech or text. Okay, now we get it, NLP plays a major role in our daily computer interactions, let's see more business-related NLP use-cases: NLP is divided into two fields: Linguistics and Computer Science.