The KNEXT system produces a large volume of factoids from text, expressing possibilistic general claims such as that 'A PERSON MAY HAVE A HEAD' or 'PEOPLE MAY SAY SOMETHING'. We present a rule-based method to sharpen certain classes of factoids into stronger, quantified claims such as 'ALL OR MOST PERSONS HAVE A HEAD' or 'ALL OR MOST PERSONS AT LEAST OCCASIONALLY SAY SOMETHING' -- statements strong enough to be used for inference. The judgement of whether and how to sharpen a factoid depends on the semantic categories of the terms involved and the strength of the quantifier depends on how strongly the subject is associated with what is predicated of it. We provide an initial assessment of the quality of such automatic strengthening of knowledge and examples of reasoning with multiple sharpened premises.

We present CrossBridge, a practical algorithm for retrieving analogies in large, sparse semantic networks. Other algorithms adopt a generate-and-test approach, retrieving candidate analogies by superficial similarity of concepts, then testing them for the particular relations involved in the analogy. CrossBridge adopts a global approach. It organizes the entire knowledge space at once, as a matrix of small concept-and-relation subgraph patterns versus actual occurrences of subgraphs from the knowledge base. It uses the familiar mathematics of dimensionality reduction to reorganize this space along dimensions representing approximate semantic similarity of these subgraphs. Analogies can then be retrieved by simple nearest-neighbor comparison. CrossBridge also takes into account not only knowledge directly related to the source and target domains, but also a large background Commonsense knowledge base. Commonsense influences the mapping between domains, preserving important relations while ignoring others. This property allows CrossBridge to find more intuitive and extensible analogies. We compare our approach with an implementation of structure mapping and show that our algorithm consistently finds analogies in cases where structure mapping fails. We also present some discovered analogies.

How do reasoning systems that learn evolve over time? Characterizing the evolution of these systems is important for understanding their limitations and gaining insights into the interplay between learning and reasoning. We describe an inverse ablation model for studying how learning and reasoning interact: Create a small knowledge base by ablation, and incrementally re-add facts, collecting snapshots of reasoning performance of the system to measure properties of interest. Experiments with this model suggest that different concepts show different rates of growth, and that the density of facts is an important parameter for modulating the rate of learning.

By extending Cyc’s ontology and KB approximately 2%, Cycorp and Cleveland Clinic Foundation (CCF) have built a system to answer clinical researchers’ ad hoc queries. The query may be long and complex, hence only partially understood at first, parsed into a set of CycL (higher-order logic) fragments with open variables. But, surprisingly often, after applying various constraints (medical domain knowledge, common sense, discourse pragmatics, syntax), there is only one single way to fit those fragments together, one semantically meaningful formal query P. The system, SRA (for Semantic Research Assistant), dispatches a series of database calls and then combines, logically and arithmetically, their results into answers to P. Seeing the first few answers stream back, the user may realize that they need to abort, modify, and re-ask their query. Even before they push ASK, just knowing approximately how many answers would be returned can spark such editing. Besides real-time ad hoc query-answering, queries can be bundled and persist over time. One bundle of 275 queries is rerun quarterly by CCF to produce the procedures and outcomes data it needs to report to STS (Society of Thoracic Surgeons, an external hospital accreditation and ranking body); another bundle covers ACC (American College of Cardiology) reporting. Until full articulation/answering of precise, analytical queries becomes as straight-forward and ubiquitous as text search, even partial understanding of a query empowers semantic search over semi-structured data (ontology-tagged text), avoiding many of the false positives and false negatives that standard text searching suffers from.

Much of the ongoing explosion of digital content is in the form of text. This content is a virtual gold-mine of information that can inform a range of social, governmental, and business decisions. For example, using content available on blogs and social networking sites businesses can find out what its customers are saying about their products and services. In the digital age where customer is king, the business value of ascertaining consumer sentiment cannot be overstated. People express sentiments in myriad ways. At times, they use simple, direct assertions, but most often they use sentences involving comparisons, conjunctions expressing multiple and possibly opposing sentiments about multiple features and entities,and pronominal references whose resolution requires discourse level context. Frequently people use abbreviations, slang, SMSese, idioms and metaphors. Understanding the latter also requires common sense reasoning. In this paper, we present iSEE, a fully implemented sentiment extraction engine, which makes use of statistical methods, classical NLU techniques, common sense reasoning, and probabilistic inference to extract entity and feature specific sentiment from complex sentences and dialog. Most of the components of iSEE are domain independent and the system can be generalized to new domains by simply adding domain relevant lexicons.

Good and generous knowledge sources, reliable and efficient induction patterns, and automatic and controllable quality assertion approaches are three critical issues to commonsense knowledge (CSK) acquisition. This paper employs Open Mind Common Sense (OMCS), a volunteers-contributed CSK database, to study the first and the third issues. For those stylized CSK, our result shows that over 40% of CSK for four predicate types in OMCS can be found in the web, which contradicts to the assumption that CSK is not communicated in texts. Moreover, we propose a commonsense knowledge classifier trained from OMCS, and achieve high precision in some predicate types, e.g., 82.6% in HasProperty. The promising results suggest new ways of analyzing and utilizing volunteer-contributed knowledge to design systems automatically mining commonsense knowledge from the web.

Present-day programs are brittle as computers are notoriously lacking in common sense. While significant progress has been made in building large common sense knowledge bases, they are intrinsically incomplete and inconsistent. This paper presents a novel approach to bridging the gaps between multiple knowledge bases, making it possible to answer queries based on knowledge collected from multiple sources without a common ontology. New assertions are found by computing graph similarity with principle component analysis to draw analogies across multiple knowledge bases. Experiments are designed to find new assertions for a Chinese commonsense knowledge base using the OMCS ConceptNet and similarly for WordNet. The assertions are voted by online users to verify that 75.77% / 77.59% for Chinese ConceptNet / WordNet respectively are good, despite the low overlap in coverage among the knowledge bases.

Our goal is for an autonomous learning agent to acquire the knowledge that serves as the foundations of common sense from its own experience without outside guidance. This requires the agent to (1) learn the structure of its own sensors and effectors; (2) learn a model of space around itself; (3) learn to move effectively in that space; (4) identify and describe objects, as distinct from the static environment; (5) learn and represent actions for affecting those objects, including preconditions and postconditions, and so on. We will provide examples of progress we have made, and the roadmap we envision for future research.

Comirit is a framework for commonsense reasoning that combines simulation, logical deduction and passive machine learning. While a passive, observation-driven approach to learning is safe and highly conservative, it is limited to inte-raction only with those objects that it has previously ob-served. In this paper we describe a preliminary exploration of methods for extending Comirit to allow safe action selection in uncertain situations, and to allow reward-maximizing selection of behaviors.

Over two decades ago a "quite revolution" overwhelmingly replaced knowledgebased approaches in natural language processing (NLP) by quantitative (e.g., statistical, corpus-based, machine learning) methods. Although it is our firm belief that purely quantitative approaches cannot be the only paradigm for NLP, dissatisfaction with purely engineering approaches to the construction of large knowledge bases for NLP are somewhat justified. In this paper we hope to demonstrate that both trends are partly misguided and that the time has come to enrich logical semantics with an ontological structure that reflects our commonsense view of the world and the way we talk about in ordinary language. In this paper it will be demonstrated that assuming such an ontological structure a number of challenges in the semantics of natural language (e.g., metonymy, intensionality, copredication, nominal compounds, etc.) can be properly and uniformly addressed.