This paper describes a baseline question answering system for Swedish on which we measured the contribution brought by syntactic features. The system includes modules to carry out the question analysis, hypothesis generation, and reranking of answers. It was trained and evaluated on questions from a data set inspired by Swedish television quiz show Kvitt eller Dubbelt -- Tiotusenkronorsfrågan. We used a HTML dump of the Swedish version of Wikipedia as knowledge source and we show in this paper that paragraph retrieval from this corpus gives an acceptable coverage of answers when targeting Kvitt eller Dubbelt questions, especially single-word answer questions. Given a question, the hypothesis generation module retrieves a list of paragraphs, ranks them using a vector space model score, and extract a set of candidates. The question analysis part performs a lexical answer type prediction. To compute a baseline ranking, we sorted answer candidates according to their frequencies in the most relevant paragraphs. The reranker module makes use of information from the previous stages to estimate the correctness of the generated answer candidates as well a grammatical information from a dependency parser. The correctness estimate is then used to re-weight the baseline ranking. A 5-fold cross-validation showed that the median ranking of the correct candidate went from rank 21 in the baseline version to 10 using the reranker.

This workshop seeks to augment human decision making by exploiting synergies across two areas of AI research where exciting research progress has been made in recent years, but which so far have not had an explicit common venue. The first area has to do with powerful new learning techniques that may have the potential to automatically learn complex tasks by directly training on massive amounts of raw data, much of which may be unlabeled, unstructured, and multi-modal in form (natural language text/speech, audio, video, and others). These techniques include deep learning, manifold learning, sparsity-based techniques, and transfer/cross-modal learning and inference methods. Researchers employing such techniques have recently achieved quantum performance leaps in speech and image recognition tasks, and have also demonstrated the ability to learn complex feature representations entirely from unlabeled data. The second area has to do with enabling computers to understand and work with naturalistic input from humans, in the form of natural language speech or text, visual input such as gestures or facial expressions, and haptic (touch-based) inputs. The most exciting demonstrations of these capabilities in the last few years include Question-Answering systems such as Watson and Wolfram Alpha, and commercially deployed personal assistant technology such as Siri, Google Now, Dragon Mobile Assistant, Nina, and TellMe. Synergistic advances in these two trends could vastly improve human decision making in many scenarios, including information overload (such as driving), cognition impairment (for example Alzheimer's) or collective (multi-objective) decision-making (such as conference program scheduling, disaster response). Cognitive computing is an emerging research topic inspired by

We leverage crowd wisdom for multiple-choice question answering, and employ lightweight machine learning techniques to improve the aggregation accuracy of crowdsourced answers to these questions. In order to develop more effective aggregation methods and evaluate them empirically, we developed and deployed a crowdsourced system for playing the "Who wants to be a millionaire?" quiz show.Analyzing our data (which consist of more than 200,000 answers), we find that by just going with the most selected answer in the aggregation, we can answer over 90% of the questions correctly, but the success rate of this technique plunges to 60% for the later/harder questions in the quiz show. To improve the success rates of these later/harder questions, we investigate novel weighted aggregation schemes for aggregating the answers obtained from the crowd.By using weights optimized for reliability of participants (derived from the participants' confidence), we show that we can pull up the accuracy rate for the harder questions by 15%, and to overall 95% average accuracy.Our results provide a good case for the benefits of applying machine learning techniques for building more accurate crowdsourced question answering systems.

This paper describes USI Answers -- a natural language question answering system for enterprise data. We report on the progress towards the goal of offering easy access to enterprise data to a large number of business users, most of whom are not familiar with the specific syntax or semantics of the underlying data sources. Additional complications come from the nature of the data, which comes both as structured and unstructured. The proposed solution allows users to express questions in natural language, makes apparent the system's interpretation of the query, and allows easy query adjustment and reformulation.

This paper describes USI Answers — a natural language question answering system for enterprise data. We report on the progress towards the goal of offering easy access to enterprise data to a large number of business users, most of whom are not familiar with the specific syntax or semantics of the underlying data sources. Additional complications come from the nature of the data, which comes both as structured and unstructured. The proposed solution allows users to express questions in natural language, makes apparent the system's interpretation of the query, and allows easy query adjustment and reformulation. The application is in use by more than 1500 users from Siemens Energy. We evaluate our approach on a data set consisting of fleet data.

In order to meet usability requirements, most logic-based applications provide explanation facilities for reasoning services. This holds also for Description Logics, where research has focused on the explanation of both TBox reasoning and, more recently, query answering. Besides explaining the presence of a tuple in a query answer, it is important to explain also why a given tuple is missing. We address the latter problem for instance and conjunctive query answering over DL-Lite ontologies by adopting abductive reasoning; that is, we look for additions to the ABox that force a given tuple to be in the result. As reasoning tasks we consider existence and recognition of an explanation, and relevance and necessity of a given assertion for an explanation. We characterize the computational complexity of these problems for arbitrary, subset minimal, and cardinality minimal explanations.

The chase algorithm is a fundamental tool for query evaluation and for testing query containment under tuple-generating dependencies (TGDs) and equality-generating dependencies (EGDs). So far, most of the research on this topic has focused on cases where the chase procedure terminates. This paper introduces expressive classes of TGDs defined via syntactic restrictions: guarded TGDs (GTGDs) and weakly guarded sets of TGDs (WGT-GDs). For these classes, the chase procedure is not guaranteed to terminate and thus may have an infinite outcome. Nevertheless, we prove that the problems of conjunctive-query answering and query containment under such TGDs are decidable. We provide decision procedures and tight complexity bounds for these problems. Then we show how EGDs can be incorporated into our results by providing conditions under which EGDs do not harmfully interact with TGDs and do not affect the decidability and complexity of query answering. We show applications of the aforesaid classes of constraints to the problem of answering conjunctive queries in F-Logic Lite, an object-oriented ontology language, and in some tractable Description Logics.

Inquire Biology is a prototype of a new kind of intelligent textbook — one that answers students’ questions, engages their interest, and improves their understanding. Inquire Biology provides unique capabilities via a knowledge representation that captures conceptual knowledge from the textbook and uses inference procedures to answer students’ questions. Students ask questions by typing free-form natural language queries or by selecting passages of text. The system then attempts to answer the question and also generates suggested questions related to the query or selection. The questions supported by the system were chosen to be educationally useful, for example: what is the structure of X? compare X and Y? how does X relate to Y? In user studies, students found this question-answering capability to be extremely useful while reading and while doing problem solving. In an initial controlled experiment, community college students using the Inquire Biology prototype outperformed students using either a hardcopy or conventional E-book version of the same biology textbook. While additional research is needed to fully develop Inquire Biology, the initial prototype clearly demonstrates the promise of applying knowledge representation and question-answering technology to electronic textbooks.

This is a Ph.D summary focusing on ontology based query answering with existential rules.

Community question answering (cQA), which providesa platform for people with diverse backgroundto share information and knowledge, hasbecome an increasingly popular research topic. Inthis paper, we focus on the task of question retrieval.The key problem of question retrieval is tomeasure the similarity between the queried questionsand the historical questions which have beensolved by other users. The traditional methodsmeasure the similarity based on the bag-of-words(BOWs) representation. This representation neithercaptures dependencies between related words, norhandles synonyms or polysemous words. In thiswork, we first propose a way to build a conceptthesaurus based on the semantic relations extractedfrom the world knowledge of Wikipedia. Then, wedevelop a unified framework to leverage these semanticrelations in order to enhance the questionsimilarity in the concept space. Experiments conductedon a real cQA data set show that with thehelp of Wikipedia thesaurus, the performance ofquestion retrieval is improved as compared to thetraditional methods.