Classifying and resolving coreferences of objects (e.g., product names) and attributes (e.g., product aspects) in opinionated reviews is crucial for improving the opinion mining performance. However, the task is challenging as one often needs to consider domain-specific knowledge (e.g., iPad is a tablet and has aspect resolution) to identify coreferences in opinionated reviews. Also, compiling a handcrafted and curated domain-specific knowledge base for each domain is very time consuming and arduous. This paper proposes an approach to automatically mine and leverage domain-specific knowledge for classifying objects and attribute coreferences. The approach extracts domain-specific knowledge from unlabeled review data and trains a knowledgeaware neural coreference classification model to leverage (useful) domain knowledge together with general commonsense knowledge for the task. Experimental evaluation on realworld datasets involving five domains (product types) shows the effectiveness of the approach.

The endoscopic camera of a surgical robot provides surgeons with a magnified 3D view of the surgical field, but repositioning it increases mental workload and operation time. Poor camera placement contributes to safety-critical events when surgical tools move out of the view of the camera. This paper presents a proof of concept of an autonomous camera system for the Raven II surgical robot that aims to reduce surgeon workload and improve safety by providing an optimal view of the workspace showing all objects of interest. This system uses transfer learning to localize and classify objects of interest within the view of a stereoscopic camera. The positions and centroid of the objects are estimated and a set of control rules determines the movement of the camera towards a more desired view. Our perception module had an accuracy of 61.21% overall for identifying objects of interest and was able to localize both graspers and multiple blocks in the environment. Comparison of the commands proposed by our system with the desired commands from a survey of 13 participants indicates that the autonomous camera system proposes appropriate movements for the tilt and pan of the camera.

The goal of text generation is to make machines express in human language. It is one of the most important yet challenging tasks in natural language processing (NLP). Since 2014, various neural encoder-decoder models pioneered by Seq2Seq have been proposed to achieve the goal by learning to map input text to output text. However, the input text alone often provides limited knowledge to generate the desired output, so the performance of text generation is still far from satisfaction in many real-world scenarios. To address this issue, researchers have considered incorporating various forms of knowledge beyond the input text into the generation models. This research direction is known as knowledge-enhanced text generation. In this survey, we present a comprehensive review of the research on knowledge enhanced text generation over the past five years. The main content includes two parts: (i) general methods and architectures for integrating knowledge into text generation; (ii) specific techniques and applications according to different forms of knowledge data. This survey can have broad audiences, researchers and practitioners, in academia and industry.

Decisions made nowadays by Artificial Intelligence powered systems are usually hard for users to understand. One of the more important issues faced by developers is exposed as how to create more explainable Machine Learning models. In line with this, more explainable techniques need to be developed, where visual explanation also plays a more important role. This technique could also be applied successfully for explaining the results of Association Rule Mining.This Chapter focuses on two issues: (1) How to discover the relevant association rules, and (2) How to express relations between more attributes visually. For the solution of the first issue, the proposed method uses Differential Evolution, while Sankey diagrams are adopted to solve the second one. This method was applied to a transaction database containing data generated by an amateur cyclist in past seasons, using a mobile device worn during the realization of training sessions that is divided into four time periods. The results of visualization showed that a trend in improving performance of an athlete can be indicated by changing the attributes appearing in the selected association rules in different time periods.

Various model-based diagnosis scenarios require the computation of most preferred fault explanations. Existing algorithms that are sound (i.e., output only actual fault explanations) and complete (i.e., can return all explanations), however, require exponential space to achieve this task. As a remedy, we propose two novel diagnostic search algorithms, called RBF-HS (Recursive Best-First Hitting Set Search) and HBF-HS (Hybrid Best-First Hitting Set Search), which build upon tried and tested techniques from the heuristic search domain. RBF-HS can enumerate an arbitrary predefined finite number of fault explanations in best-first order within linear space bounds, without sacrificing the desirable soundness or completeness properties. The idea of HBF-HS is to find a trade-off between runtime optimization and a restricted space consumption that does not exceed the available memory. In extensive experiments on real-world diagnosis cases we compared our approaches to Reiter's HS-Tree, a state-of-the-art method that gives the same theoretical guarantees and is as general(ly applicable) as the suggested algorithms. For the computation of minimum-cardinality fault explanations, we find that (1) RBF-HS reduces memory requirements substantially in most cases by up to several orders of magnitude, (2) in more than a third of the cases, both memory savings and runtime savings are achieved, and (3) given the runtime overhead is significant, using HBF-HS instead of RBF-HS reduces the runtime to values comparable with HS-Tree while keeping the used memory reasonably bounded. When computing most probable fault explanations, we observe that RBF-HS tends to trade memory savings more or less one-to-one for runtime overheads. Again, HBF-HS proves to be a reasonable remedy to cut down the runtime while complying with practicable memory bounds.

Predicting missing facts in a knowledge graph (KG) is a crucial task in knowledge base construction and reasoning, and it has been the subject of much research in recent works using KG embeddings. While existing KG embedding approaches mainly learn and predict facts within a single KG, a more plausible solution would benefit from the knowledge in multiple language-specific KGs, considering that different KGs have their own strengths and limitations on data quality and coverage. This is quite challenging, since the transfer of knowledge among multiple independently maintained KGs is often hindered by the insufficiency of alignment information and the inconsistency of described facts. In this paper, we propose KEnS, a novel framework for embedding learning and ensemble knowledge transfer across a number of language-specific KGs. KEnS embeds all KGs in a shared embedding space, where the association of entities is captured based on self-learning. Then, KEnS performs ensemble inference to combine prediction results from embeddings of multiple language-specific KGs, for which multiple ensemble techniques are investigated. Experiments on five real-world language-specific KGs show that KEnS consistently improves state-of-the-art methods on KG completion, via effectively identifying and leveraging complementary knowledge.

A major strength of frame-based knowledge representation languages is their ability to provide the knowledge base designer with a concise and intuitively appealing means expression. The claim of intuitive appeal is based on the observation that the object -centered style of description provided by these languages often closely matches a designer's understanding of the domain being modeled and therefore lessens the burden of reformulation involved in developing a formal description. To be effective as a knowledge base development tool, a language needs to be supported by an implementation that facilitates creating, browsing, debugging, and editing the descriptions in the knowledge base. We have focused on providing such support in a SmallTalk (Ingalls, 1978) implementation of the KL-ONE knowledge representation language (Brachman, 1978), called KloneTalk, that has been in use by several projects for over a year at Xerox PARC. In this note, we describe those features of KloneTalk's displaybased interface that have made it an effective knowledge base development tool, including the use of constraints to automatically determine descriptions of newly created data base items.

Our group's work in medical decision making has led us to formulate a framework for expert system design, in particular about how the domain knowledge may be decomposed into substructures. We propose that there exist different problem-solving types, i.e., uses of knowledge, and corresponding to each is a separate substructure specializing in that type of problem-solving. Each substructure is in turn further decomposed into a hierarchy of specialist which differ from each other not in the type of problem-solving, but in the conceptual content of their knowledge; e.g.; one of them may specialize in "heart disease," while another may do so in "liver," though both of them are doing the same type of problem solving. Thus ultimately all the knowledge in the system is distributed among problem-solvers which know how to use that knowledge. This is in contrast to the currently dominant expert system paradigm which proposes a common knowledge base accessed by knowledge-free problem-solvers of various kinds. In our framework there is no distinction between knowledge bases and problem-solvers: each knowledge source is a problem-solver.

Schlumberger is a large, multinational corporation concerned primarily with the measurement, collection, and interpretation of data. For the past fifty years, most of the activities have been related to hydrocarbon exploration. The efficient location and production of hydrocarbons from an underground formation requires a great deal of knowledge about the formation, ranging in scale from the size and shape of the rock's pore spaces to the size and shape of the entire reservoir. Schlumberger provides its clients with two types of information: measurements, called logs, of the petrophysical properties of the rock around the borehole, such as its electrical, acoustical, and radioactive characteristics; and in terpretations of these logs in terms of geophysical properties such as porosity and mineral composition. Since log interpretation is expert skill, the emergence of expert systems technology prompted Schlumberger's initial interest in Artificial Intelligence.

The TRW Defense Systems Group develops large man-machine networks that solve problems for government agencies. Until a few years ago these networks were either tightly-coupled humans loosely supported by machines -- like our ballistic missile system engineering organization, which provides technical advice to the Air Force, or tightly-coupled machines loosely controlled by humans- like the ground station for the NASA Tracking and Data Relay Satellite System. Because we have been producing first-of- a kind systems like these since the early 1950s, we consider ourselves leaders in the social art of assembling effective teams of diverse experts, and in the engineering art of conceiving and developing networks of interacting machines. But in the mid-1970s we began building systems in which humans and machines must be tightly coupled to each other-systems like the Sensor Data Fusion Center. Then we found that our well-worked system development techniques did not completely apply, and that our system engineering handbook needed a new chapter on communication between people and machines.