A referring expression in linguistics is any noun phrase identifying an object in a way that will be useful to interlocutors. In the context of a query over a first order knowledge base K, constant symbols occurring in K are the artifacts usually used as referring expressions in certain answers to the query. In this paper, we begin to explore how this can be usefully extended by allowing a class of more general formulas, called Singular Referring Expressions, to replace constants in this role. In particular, we lay a foundation for admitting Singular Referring Expressions in certain answer computation for queries over K. An integral part of this foundation are characterization theorems for identification properties of Singular Referring Expressions for queries annotated with a domain specific language for referring concept types. Finally, we apply this framework in the context of tractable description logic dialects, showing how identification properties can be determined at compile-time for conjunctive queries, and how off-the-shelf conjunctive query evaluation for these dialects can be used in query evaluations, preserving, in all cases, underlying tractability.

Classical inconsistency-tolerant query answering relies on selecting maximal components of an ABox/database which are consistent with the ontology. However, some rules in ontologies might be unreliable if they are extracted from ontology learning or written by unskillful knowledge engineers. In this paper we present a framework of handling inconsistent existential rules under stable model semantics, which is defined by a notion called rule repairs to select maximal components of the existential rules. Surprisingly, for R-acyclic existential rules with R-stratified or guarded existential rules with stratified negations, both the data complexity and combined complexity of query answering under the rule repair semantics remain the same as that under the conventional query answering semantics. This leads us to propose several approaches to handle the rule repair semantics by calling answer set programming solvers. An experimental evaluation shows that these approaches have good scalability of query answering under rule repairs on realistic cases.

We developed a course in which students train an instance of Watson and develop an application that interacts with the trained instance. Additionally, students learn technical in-formation about the Jeopardy! version of Watson and they discuss a future infused with cognitive assistants. In this poster, we justify this course, characterize major assessment items and provide advice on choosing a domain.

As the amount of knowledge bases (KBs) grows rapidly, the problem of question answering (QA) over multiple KBs has drawn more attention. The most significant distinction between multiple KB-QA and single KB-QA is that the former must consider the alignments between KBs. The pipeline strategy first constructs the alignments independently, and then uses the obtained alignments to construct queries. However, alignment construction is not a trivial task, and the introduced noises would be passed on to query construction. By contrast, we notice that alignment construction and query construction are interactive steps, and jointly considering them would be beneficial. To this end, we present a novel joint model based on integer linear programming (ILP), uniting these two procedures into a uniform framework. The experimental results demonstrate that the proposed approach outperforms state-of-the-art systems, and is able to improve the performance of both alignment construction and query construction.

We study tag recommendation for questions in community question answering (CQA). Tags represent the semantic summarization of questions are useful for navigation and expert finding in CQA and can facilitate content consumption such as searching and mining in these web sites. The task is challenging, as both questions and tags are short and a large fraction of tags are tail tags which occur very infrequently. To solve these problems, we propose matching questions and tags not only by themselves, but also by similar questions and similar tags. The idea is then formalized as a model in which we calculate question-tag similarity using a linear combination of similarity with similar questions and tags weighted by tag importance.Question similarity, tag similarity, and tag importance are learned in a supervised random walk framework by fusing multiple features. Our model thus can not only accurately identify question-tag similarity for head tags, but also improve the accuracy of recommendation of tail tags. Experimental results show that the proposed method significantly outperforms state-of-the-art methods on tag recommendation for questions. Particularly, it improves tail tag recommendation accuracy by a large margin.

Community-based question answering (cQA) sites have accumulated vast amount of questions and corresponding crowdsourced answers over time. How to efficiently share the underlying information and knowledge from reliable (usually highly-reputable) answerers has become an increasingly popular research topic. A major challenge in cQA tasks is the accurate matching of high-quality answers w.r.t given questions. Many of traditional approaches likely recommend corresponding answers merely depending on the content similarity between questions and answers, therefore suffer from the sparsity bottleneck of cQA data. In this paper, we propose a novel framework which encodes not only the contents of question-answer(Q-A) but also the social interaction cues in the community to boost the cQA tasks. More specifically, our framework collaboratively utilizes the rich interaction among questions, answers and answerers to learn the relative quality rank of different answers w.r.t a same question. Moreover, the information in heterogeneous social networks is comprehensively employed to enhance the quality of question-answering (QA) matching by our deep random walk learning framework. Extensive experiments on a large-scale dataset from a real world cQA site show that leveraging the heterogeneous social information indeed achieves better performance than other state-of-the-art cQA methods.

AlchemyLanguage is a collection of APIs that offer text analysis through natural language processing. The AlchemyLanguage APIs can analyze text and help you to understand its sentiment, keywords, entities, high-level concepts and more.

Not every startup CEO can say they were able to grow their business to a point where they were acquired. Even fewer can say they did it twice. But that is exactly the case for AlchemyAPI Founder and CEO Elliot Turner. Turner launched his first startup, MimeStar, a software development company focused on network intrusion detection, while a sophomore in high school. Inc. acquired it by the time he was twenty-one. He quickly saw the shift in the market to the need to democratize artificial intelligence (A.I.), and decided to venture out on his own to start AlchemyAPI.

I would like to propose that Watson could solve one of the biggest challenges facing anyone trying to innovate and product their innovation with a US patent - the USPTO first office action. While everyone is working hard and I know the patent office is overloaded, here how three problems I've seen over my years of working that perhaps Watson could address: 1) Speed - it can take 6-12 months to get a first office action 2) Almost any patent application is nowadays first rejected due to obviousness. But the patents cited to create this argument are often taken out of context. To me, these seem like challenges that Watson would be perfectly designed to addressed. And all the literature to be reviewed is, by definition, in the public domain.

This is the direction of the future. Useful AI that can do the research of a thoudand men instantly. It's definitely worth noting that Watson is capable of learning (a point I didn't touch on in this video), so what you see here is the "baby phase" so to speak. I tried to leave out the technical jargon in this video but for those who want to know more, a wiki dump on Watson is below: According to John Rennie, Watson can process 500 gigabytes, the equivalent of a million books, per second. Software Watson uses IBM's DeepQA software and the Apache UIMA (Unstructured Information Management Architecture) framework.