Reasoning on defeasible knowledge is a topic of interest in the area of description logics, as it is related to the need of representing exceptional instances in knowledge bases. In this direction, in our previous works we presented a framework for representing (contextualized) OWL RL knowledge bases with a notion of justified exceptions on defeasible axioms: reasoning in such framework is realized by a translation into ASP programs. The resulting reasoning process for OWL RL, however, introduces a complex encoding in order to capture reasoning on the negative information needed for reasoning on exceptions. In this paper, we apply the justified exception approach to knowledge bases in $\textit{DL-Lite}_{\cal R}$, i.e., the language underlying OWL QL. We provide a definition for $\textit{DL-Lite}_{\cal R}$ knowledge bases with defeasible axioms and study their semantic and computational properties. In particular, we study the effects of exceptions over unnamed individuals. The limited form of $\textit{DL-Lite}_{\cal R}$ axioms allows us to formulate a simpler ASP encoding, where reasoning on negative information is managed by direct rules. The resulting materialization method gives rise to a complete reasoning procedure for instance checking in $\textit{DL-Lite}_{\cal R}$ with defeasible axioms. Under consideration in Theory and Practice of Logic Programming (TPLP).

Current domain-independent, classical planners require symbolic models of the problem domain and instance as input, resulting in a knowledge acquisition bottleneck. Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners. We propose Latplan, an unsupervised architecture combining deep learning and classical planning. Given only an unlabeled set of image pairs showing a subset of transitions allowed in the environment (training inputs), Latplan learns a complete propositional PDDL action model of the environment. Later, when a pair of images representing the initial and the goal states (planning inputs) is given, Latplan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution. We evaluate Latplan using image-based versions of 6 planning domains: 8-puzzle, 15-Puzzle, Blocksworld, Sokoban and Two variations of LightsOut.

We present ASDiv (Academia Sinica Diverse MWP Dataset), a diverse (in terms of both language patterns and problem types) English math word problem (MWP) corpus for evaluating the capability of various MWP solvers. Existing MWP corpora for studying AI progress remain limited either in language usage patterns or in problem types. We thus present a new English MWP corpus with 2,305 MWPs that cover more text patterns and most problem types taught in elementary school. Each MWP is annotated with its problem type and grade level (for indicating the level of difficulty). Furthermore, we propose a metric to measure the lexicon usage diversity of a given MWP corpus, and demonstrate that ASDiv is more diverse than existing corpora. Experiments show that our proposed corpus reflects the true capability of MWP solvers more faithfully.

What does it take to deliver a machine learning (ML) application that provides real business value to your company? Once you've done that and proved the substantial benefit that ML can bring to the company, how do you expand that effort to additional use cases, and really start to fulfill the promise of ML? And then, how do you scale up ML across the organization and streamline the ML development and delivery process to standardize ML initiatives, share and reuse work and iterate quickly? What are the best practices that some of the world's leading tech companies have adopted? Over a series of articles, my goal is to explore these fascinating questions and understand the challenges and learnings along the way.

Graphs have become the best way we know of representing knowledge. The computing community has investigated and developed the support for managing graphs by means of digital technology. Graph databases and knowledge graphs surface as the most successful solutions to this program. This tutorial will provide a conceptual map of the data management tasks underlying these developments, paying particular attention to data models and query languages for graphs.

Artificial Intelligence (AI) is gradually and inexorably entering into the legal profession. There is the use of Natural Language Processing (NLP), which we already experience in everyday ordinary interaction with Alexa and Siri and has been increasingly added into various LegalTech systems such as used for contract management, e-Discovery, and the like. Another avenue of AI consists of Machine Learning and Deep Learning. These computational pattern matching techniques are being used to predict court rulings and are also employed to ferret out prior relevant cases amongst a large-scale corpus of online court records. One of the most fascinating and likely law-disruptive AI technologies involves AI-based legal reasoning systems. The notion is that the AI simulates the legal argumentation precepts of human attorneys and essentially carries out a limited form of legal reasoning. Initially, these AI-based legal reasoners would be used as an aid for lawyers and jurists seeking to craft legal arguments. In this semi-autonomous mode, the AI works hand-in-hand with the human legal expert and they jointly establish a robust legal argument or legal posture. Some assert that this capability by the AI will inevitably be further advanced and we will have available fully autonomous AI-based legal reasoning systems that can act in lieu of needing any human legal guidance.

Reasoning about the behaviour of physical objects is a key capability of agents operating in physical worlds. Humans are very experienced in physical reasoning while it remains a major challenge for AI. To facilitate research addressing this problem, several benchmarks have been proposed recently. However, these benchmarks do not enable us to measure an agent's granular physical reasoning capabilities when solving a complex reasoning task. In this paper, we propose a new benchmark for physical reasoning that allows us to test individual physical reasoning capabilities. Inspired by how humans acquire these capabilities, we propose a general hierarchy of physical reasoning capabilities with increasing complexity. Our benchmark tests capabilities according to this hierarchy through generated physical reasoning tasks in the video game Angry Birds. This benchmark enables us to conduct a comprehensive agent evaluation by measuring the agent's granular physical reasoning capabilities. We conduct an evaluation with human players, learning agents, and heuristic agents and determine their capabilities. Our evaluation shows that learning agents, with good local generalization ability, still struggle to learn the underlying physical reasoning capabilities and perform worse than current state-of-the-art heuristic agents and humans. We believe that this benchmark will encourage researchers to develop intelligent agents with advanced, human-like physical reasoning capabilities. URL: https://github.com/Cheng-Xue/Hi-Phy

World models improve a learning agent's ability to efficiently operate in interactive and situated environments. This work focuses on the task of building world models of text-based game environments. Text-based games, or interactive narratives, are reinforcement learning environments in which agents perceive and interact with the world using textual natural language. These environments contain long, multi-step puzzles or quests woven through a world that is filled with hundreds of characters, locations, and objects. Our world model learns to simultaneously: (1) predict changes in the world caused by an agent's actions when representing the world as a knowledge graph; and (2) generate the set of contextually relevant natural language actions required to operate in the world. We frame this task as a Set of Sequences generation problem by exploiting the inherent structure of knowledge graphs and actions and introduce both a transformer-based multi-task architecture and a loss function to train it. A zero-shot ablation study on never-before-seen textual worlds shows that our methodology significantly outperforms existing textual world modeling techniques as well as the importance of each of our contributions.

Most prior work on task-oriented dialogue systems are restricted to limited coverage of domain APIs. However, users oftentimes have requests that are out of the scope of these APIs. This work focuses on responding to these beyond-API-coverage user turns by incorporating external, unstructured knowledge sources. Our approach works in a pipelined manner with knowledge-seeking turn detection, knowledge selection, and response generation in sequence. We introduce novel data augmentation methods for the first two steps and demonstrate that the use of information extracted from dialogue context improves the knowledge selection and end-to-end performances. Through experiments, we achieve state-of-the-art performance for both automatic and human evaluation metrics on the DSTC9 Track 1 benchmark dataset, validating the effectiveness of our contributions.

The study of architectures and methods for artificial neural networks so that they can learn and perform tasks from the realm of logic-based knowledge representation and reasoning has a long-standing tradition Besold et al. [2017]. This research area is sometimes referred to as "neuro-symbolic integration" (or "neural-symbolic integration") and there are at least two primary rationales that can be found in the literature on the subject. The first is the desire to arrive at systems that combine the robustness and trainability of artificial neural networks with the transparency and interpretability of knowledge-based systems, while at the same time making use of structured background knowledge. The second rationale is more prevalent in cognitive science and lies in addressing the fundamental gap between symbolic and subsymbolic representation and processing, based on the observation that humans perceive much of their own thinking, introspectively, as symbolic, while the physical structure of the brain gives rise to artificial neural networks as a mathematical and computational abstraction. Many of the earlier lines of research on neuro-symbolic integration, discussed primarily from a cognitive science perspective, can be found in Besold et al. [2017]. Of particular interest is the integration of deep learning with logics that are not propositional in nature, since propositional logic is of limited applicability to knowledge representation and reasoning tasks. In the wake of deep learning breakthroughs, fundamental issues around neuro-symbolic integration have recently received increased attention with some progress being made as new approaches emerge. In particular, there has been progress in developing neural networks that can learn to reason.