Knowledge that Everyone Knows. "People do not walk on their heads." The assertion comes about 900 statements deep into the 527,308 items that comprise the Open Mind common sense database. It's after "Laws are the rules of society" and before "The sky is blue during the day." This collection of mundane facts, which would take more than 20,000 pages to print out, consists entirely of statements so unremarkable they are barely worth stating. Most of us would correctly dismiss them as common sense.
– from D.C. Denison, Guess who's smarter. Boston Globe Online (page hosted at MIT), May 26, 2003.
Commonsense reasoning has long been considered as one of the holy grails of artificial intelligence. Most of the recent progress in the field has been achieved by novel machine learning algorithms for natural language processing. However, without incorporating logical reasoning, these algorithms remain arguably shallow. With some notable exceptions, developers of practical automated logic-based reasoners have mostly avoided focusing on the problem. The paper argues that the methods and algorithms used by existing automated reasoners for classical first-order logic can be extended towards commonsense reasoning. Instead of devising new specialized logics we propose a framework of extensions to the mainstream resolution-based search methods to make these capable of performing search tasks for practical commonsense reasoning with reasonable efficiency. The proposed extensions mostly rely on operating on ordinary proof trees and are devised to handle commonsense knowledge bases containing inconsistencies, default rules, taxonomies, topics, relevance, confidence and similarity measures. We claim that machine learning is best suited for the construction of commonsense knowledge bases while the extended logic-based methods would be well-suited for actually answering queries from these knowledge bases.
Question answering (QA) in natural language (NL) has been an important aspect of AI from its early days. Winograd's ``councilmen'' example in his 1972 paper and McCarthy's Mr. Hug example of 1976 highlights the role of external knowledge in NL understanding. While Machine Learning has been the go-to approach in NL processing as well as NL question answering (NLQA) for the last 30 years, recently there has been an increasingly emphasized thread on NLQA where external knowledge plays an important role. The challenges inspired by Winograd's councilmen example, and recent developments such as the Rebooting AI book, various NLQA datasets, research on knowledge acquisition in the NLQA context, and their use in various NLQA models have brought the issue of NLQA using ``reasoning'' with external knowledge to the forefront. In this paper, we present a survey of the recent work on them. We believe our survey will help establish a bridge between multiple fields of AI, especially between (a) the traditional fields of knowledge representation and reasoning and (b) the field of NL understanding and NLQA.
We describe a detailed analysis of a sample of large benchmark of commonsense reasoning problems that has been automatically obtained from WordNet, SUMO and their mapping. The objective is to provide a better assessment of the quality of both the benchmark and the involved knowledge resources for advanced commonsense reasoning tasks. By means of this analysis, we are able to detect some knowledge misalignments, mapping errors and lack of knowledge and resources. Our final objective is the extraction of some guidelines towards a better exploitation of this commonsense knowledge framework by the improvement of the included resources.
Natural language understanding (NLU) of text is a fundamental challenge in AI, and it has received significant attention throughout the history of NLP research. This primary goal has been studied under different tasks, such as Question Answering (QA) and Textual Entailment (TE). In this thesis, we investigate the NLU problem through the QA task and focus on the aspects that make it a challenge for the current state-of-the-art technology. This thesis is organized into three main parts: In the first part, we explore multiple formalisms to improve existing machine comprehension systems. We propose a formulation for abductive reasoning in natural language and show its effectiveness, especially in domains with limited training data. Additionally, to help reasoning systems cope with irrelevant or redundant information, we create a supervised approach to learn and detect the essential terms in questions. In the second part, we propose two new challenge datasets. In particular, we create two datasets of natural language questions where (i) the first one requires reasoning over multiple sentences; (ii) the second one requires temporal common sense reasoning. We hope that the two proposed datasets will motivate the field to address more complex problems. In the final part, we present the first formal framework for multi-step reasoning algorithms, in the presence of a few important properties of language use, such as incompleteness, ambiguity, etc. We apply this framework to prove fundamental limitations for reasoning algorithms. These theoretical results provide extra intuition into the existing empirical evidence in the field.
This paper summarizes some of the technical background, research ideas, and possible development strategies for achieving machine common sense. Machine common sense has long been a critical-but-missing component of Artificial Intelligence (AI). Recent advances in machine learning have resulted in new AI capabilities, but in all of these applications, machine reasoning is narrow and highly specialized. Developers must carefully train or program systems for every situation. General commonsense reasoning remains elusive. The absence of common sense prevents intelligent systems from understanding their world, behaving reasonably in unforeseen situations, communicating naturally with people, and learning from new experiences. Its absence is perhaps the most significant barrier between the narrowly focused AI applications we have today and the more general, human-like AI systems we would like to build in the future. Machine common sense remains a broad, potentially unbounded problem in AI. There are a wide range of strategies that could be employed to make progress on this difficult challenge. This paper discusses two diverse strategies for focusing development on two different machine commonsense services: (1) a service that learns from experience, like a child, to construct computational models that mimic the core domains of child cognition for objects (intuitive physics), agents (intentional actors), and places (spatial navigation); and (2) service that learns from reading the Web, like a research librarian, to construct a commonsense knowledge repository capable of answering natural language and image-based questions about commonsense phenomena.
In 'Winograd Schema' (WS) sentences like "The city councilmen refused the demonstrators a permit because they feared violence" and "The city councilmen refused the demonstrators a permit because they advocated revolution", it is easy for adults to understand what "they" refers to but can be difficult for AI systems. This paper describes how the SP System -- outlined in an appendix -- may solve this kind of problem of interpretation. The central idea is that a knowledge of discontinuous associations amongst linguistic features, and an ability to recognise such patterns of associations, provides a robust means of determining what a pronoun like "they" refers to. For any AI system to solve this kind of problem, it needs appropriate knowledge of relevant syntax and semantics which, ideally, it should learn for itself. Although the SP System has some strengths in unsupervised learning, its capabilities in this area are not yet good enough to learn the kind of knowledge needed to interpret WS examples, so it must be supplied with such knowledge at the outset. However, its existing strengths in unsupervised learning suggest that it has potential to learn the kind of knowledge needed for the interpretation of WS examples. In particular, it has potential to learn the kind of discontinuous association of linguistic features mentioned earlier.
We present Web-STAR, an online platform for story understanding built on top of the STAR reasoning engine for STory comprehension through ARgumentation. The platform includes a web-based IDE, integration with the STAR system, and a web service infrastructure to support integration with other systems that rely on story understanding functionality to complete their tasks. The platform also delivers a number of "social" features, including a community repository for public story sharing with a built-in commenting system, and tools for collaborative story editing that can be used for team development projects and for educational purposes.
Reasoning is a crucial part of natural language argumentation. To comprehend an argument, one must analyze its warrant, which explains why its claim follows from its premises. As arguments are highly contextualized, warrants are usually presupposed and left implicit. Thus, the comprehension does not only require language understanding and logic skills, but also depends on common sense. In this paper we develop a methodology for reconstructing warrants systematically. We operationalize it in a scalable crowdsourcing process, resulting in a freely licensed dataset with warrants for 2k authentic arguments from news comments. On this basis, we present a new challenging task, the argument reasoning comprehension task. Given an argument with a claim and a premise, the goal is to choose the correct implicit warrant from two options. Both warrants are plausible and lexically close, but lead to contradicting claims. A solution to this task will define a substantial step towards automatic warrant reconstruction. However, experiments with several neural attention and language models reveal that current approaches do not suffice.
Machine learning has become pervasive in multiple domains, impacting a wide variety of applications, such as knowledge discovery and data mining, natural language processing, information retrieval, computer vision, social and health informatics, ubiquitous computing, etc. Two essential problems of machine learning are how to generate features and how to acquire labels for machines to learn. Particularly, labeling large amount of data for each domain-specific problem can be very time consuming and costly. It has become a key obstacle in making learning protocols realistic in applications. In this paper, we will discuss how to use the existing general-purpose world knowledge to enhance machine learning processes, by enriching the features or reducing the labeling work. We start from the comparison of world knowledge with domain-specific knowledge, and then introduce three key problems in using world knowledge in learning processes, i.e., explicit and implicit feature representation, inference for knowledge linking and disambiguation, and learning with direct or indirect supervision. Finally we discuss the future directions of this research topic.
Commonsense reasoning is in principle a central problem in artificial intelligence, but it is a very difficult one. One approach that has been pursued since the earliest days of the field has been to encode commonsense knowledge as statements in a logic-based representation language and to implement commonsense reasoning as some form of logical inference. This paper surveys the use of logic-based representations of commonsense knowledge in artificial intelligence research.