Knowledge bases (KBs), pragmatic collections of knowledge about notable entities, are an important asset in applications such as search, question answering and dialogue. Rooted in a long tradition in knowledge representation, all popular KBs only store positive information, while they abstain from taking any stance towards statements not contained in them. In this paper, we make the case for explicitly stating interesting statements which are not true. Negative statements would be important to overcome current limitations of question answering, yet due to their potential abundance, any effort towards compiling them needs a tight coupling with ranking. We introduce two approaches towards compiling negative statements. (i) In peer-based statistical inferences, we compare entities with highly related entities in order to derive potential negative statements, which we then rank using supervised and unsupervised features. (ii) In query-log-based text extraction, we use a pattern-based approach for harvesting search engine query logs. Experimental results show that both approaches hold promising and complementary potential. Along with this paper, we publish the first datasets on interesting negative information, containing over 1.1M statements for 100K popular Wikidata entities.

It's impossible to talk about artificial intelligence without mentioning IBM's Watson. A pioneer in cognitive computing, the American computer giant has found multiple health applications for Watson. Pascal Sempé, senior sales consultant for Watson Health Solutions in France, explained how Watson functions and what's at stake. ME e-mag: Could Watson ever replace doctors? Pascal Sempé: Watson is a tool that helps the doctor, certainly not one that tells the doctor what to do.

Google says it only records interactions with connected devices like the Google Home speaker when we use the "wake word," of "Hey, Google," or "OK, Google." But when using many of the Google smartphone apps with a microphone for voice search, or even Google on the desktop with voice commands, it can actually record every word you say to it – whether you use the wake word or not. The fine print is that you have to click on the microphone in the apps to communicate with Google. Once you do that, Google will start transcribing you, word for word, and storing your commands, in text and audio, as USA TODAY discovered in tests this week. This is similar to Google's monitoring of our keystrokes.

Wong's Mandarin class meets four times a week. On Mondays and Fridays, he attends a class in a traditional classroom with Helen Zhou, Associate Professor at the RPI. There he learns new vocabulary and gets an introduction to phrases and grammatical structures. On Tuesdays and Thursdays, the class meets in the CIR, where students conduct conversations with virtual agents. In a restaurant environment, Wong said students can go through the entire process of sitting down in the restaurant, looking at a menu, ordering food, speaking with a waiter on how the food is prepared, and paying the bill.

The IBM Developer NYC team will be hosting a Holiday Tech Showcase & Party! Please join us & the community for a fun-filled night of food & drinks, networking, IBM's BIG IDEAS for 2020, exclusive project demos using IBM technologies, & a special holiday gift from IBM Developer as a token of appreciation. Sign up for IBM Cloud (here: http://ibm.biz/IBMHolidayParty) to receive a special IBM holiday gift. Pooja, Roger, Grant, Nigel, Jenna, & Mofi Special Message: The IBM Developer NYC team would like to thank you ALL for being the best part of our events this year! This year, IBM Developer New York has grown over 70%! Thank you for showing up, participating & being excited to learn with us!

Taking an answer and its context as input, sequence-to- sequence models have made considerable progress on question generation. However, we observe that these approaches often generate wrong question words or keywords and copy answer-irrelevant words from the input. We believe that lacking global question semantics and exploiting answer position-awareness not well are the key root causes. In this paper, we propose a neural question generation model with two concrete modules: sentence-level semantic matching and answer position inferring. Further, we enhance the initial state of the decoder by leveraging the answer-aware gated fusion mechanism. Experimental results demonstrate that our model outperforms the state-of-the-art (SOT A) models on SQuAD and MARCO datasets. Owing to its generality, our work also improves the existing models significantly.

Assist AI doesn't need data scientists to train or refine models for maintenance work.

In the community question answering (CQA) system, the answer selection task aims to identify the best answer for a specific question, and thus is playing a key role in enhancing the service quality through recommending appropriate answers for new questions. Recent advances in CQA answer selection focus on enhancing the performance by incorporating the community information, particularly the expertise (previous answers) and authority (position in the social network) of an answerer. However, existing approaches for incorporating such information are limited in (a) only considering either the expertise or the authority, but not both; (b) ignoring the domain knowledge to differentiate topics of previous answers; and (c) simply using the authority information to adjust the similarity score, instead of fully utilizing it in the process of measuring the similarity between segments of the question and the answer. We propose the Knowledge-enhanced Attentive Answer Selection (KAAS) model, which enhances the performance through (a) considering both the expertise and the authority of the answerer; (b) utilizing the human-labeled tags, the taxonomy of the tags, and the votes as the domain knowledge to infer the expertise of the answer; (c) using matrix decomposition of the social network (formed by following-relationship) to infer the authority of the answerer and incorporating such information in the process of evaluating the similarity between segments. Besides, for vertical community, we incorporate an external knowledge graph to capture more professional information for vertical CQA systems. Then we adopt the attention mechanism to integrate the analysis of the text of questions and answers and the aforementioned community information. Experiments with both vertical and general CQA sites demonstrate the superior performance of the proposed KAAS model.

Abstract--In medicine, a communicating virtual patient or doctor allows students to train in medical diagnosis and dev elop skills to conduct a medical consultation. In this paper, we describe a conversational virtual standardized patient sy stem to allow medical students to simulate a diagnosis strategy o f an abdominal surgical emergency. We exploited the semantic properties captured by distributed word representations t o search for similar questions in the virtual patient dialogue syste m. We created two dialogue systems that were evaluated on dataset s collected during tests with students. The first system based on handcrafted rules obtains 92.29% as F 1-score on the studied clinical case while the second system that combines rules an d semantic similarity achieves 94.88%. It represents an error reduction of 9.70% as compared to the rules-only-based system. The medical diagnosis practice is traditionally bedside taught. Theoretical courses are supplemented by internshi ps in hospital services. The medical student observes the practi ce of doctors and interns and practices himself under their contr ol. This type of learning has the disadvantage to confront immediately the medical student with complex situations withou t practical training (technical and human) beforehand.