As my Masters is coming to an end, I wanted to work on an interesting NLP project where I can use all the techniques(not exactly) I have learned at USF. With the help of my professors and discussions with the batch mates, I decided to build a question-answering model from scratch. I am using the Stanford Question Answering Dataset (SQuAD). The problem is pretty famous with all the big companies trying to jump up at the leaderboard and using advanced techniques like attention based RNN models to get the best accuracy. All the GitHub repositories that I found related to SQuAD by other people have also used RNNs. However, my goal is not to reach the state of the art accuracy but to learn different NLP concepts, implement them and explore more solutions.

About Jen Booton Jen is a senior writer at SportTechie covering the many ways technology is disrupting sports. On any given day she may cover a wide variety of stories ranging from the newest virtual reality training tools for the NFL, the rise of eSports leagues and the infiltration of drones in extreme sports. Prior to joining SportTechie, Jen was a technology reporter at MarketWatch, where she covered major Silicon Valley companies, such as Apple, Amazon, Google and Facebook. Jen is a licensed skydiver who jumps out of planes, helicopters and hot air balloons for fun in her spare time. She's a former NCAA cross country athlete and currently lives in Hoboken, New Jersey.

Two years after originally announcing it, Medtronic and IBM Watson have launched their joint platform the Sugar.IQ, a digital diabetes assistant. "It is designed for people who are currently using Guardian Connect; so made for people on multiple daily injections. It is a personal assistant a little bit like Alexa or Siri," Huzefa Neemuchwala, global head of digital health solutions and AI at Medtronic, said in a Facebook live informational session. "It is an intelligent assistant that keeps track of all of your information and has all of your information in one place. Then through Watson technology we use this information to power insights so we can better manage your diabetes so that you can spend more time in range."

Many question answering systems over knowledge graphs rely on entity and relation linking components in order to connect the natural language input to the underlying knowledge graph. Traditionally, entity linking and relation linking have been performed either as dependent sequential tasks or as independent parallel tasks. In this paper, we propose a framework called EARL, which performs entity linking and relation linking as a joint task. EARL implements two different solution strategies for which we provide a comparative analysis in this paper: The first strategy is a formalisation of the joint entity and relation linking tasks as an instance of the Generalised Travelling Salesman Problem (GTSP). In order to be computationally feasible, we employ approximate GTSP solvers. The second strategy uses machine learning in order to exploit the connection density between nodes in the knowledge graph. It relies on three base features and re-ranking steps in order to predict entities and relations. We compare the strategies and evaluate them on a dataset with 5000 questions. Both strategies significantly outperform the current state-of-the-art approaches for entity and relation linking.

IBM is deploying sophisticated technology under its Watson Financial Services brand to improve risk management across financial firms. The initiative has several components, said Michael Curry, vice president of engineering for Watson Financial Services at IBM. "One piece is more focused on financial risk -- market, credit and liquidity risk that are associated with portfolios. The Armanta acquisition we announced a few months ago sits in portfolio management but we are applying it in other places too. "The second piece would be more operational risk, and there you have two components. One is some of the areas of financial crimes and fraud where we have our Financial Crimes Insight Engine, a platform for finding patterns of fraud and market abuse.

Crowdsourcing can identify high-quality solutions to problems; however, individual decisions are constrained by cognitive biases. We investigate some of these biases in an experimental model of a question-answering system. We observe a strong position bias in favor of answers appearing earlier in a list of choices. This effect is enhanced by three cognitive factors: the attention an answer receives, its perceived popularity, and cognitive load, measured by the number of choices a user has to process. While separately weak, these effects synergistically amplify position bias and decouple user choices of best answers from their intrinsic quality. We end our paper by discussing the novel ways we can apply these findings to substantially improve how high-quality answers are found in question-answering systems.

In this paper we introduce the task of misflagged duplicate question detection for question pairs in community question-answer (cQA) archives and compare it to the more standard task of detecting valid duplicate questions. A misflagged duplicate is a question that has been erroneously hand-flagged by the community as a duplicate of an archived one, where the two questions are not actually the same. We find that form is flagged duplicate detection, meta data features that capture user authority, question quality, and relational data between questions, outperform pure text-based methods, while for regular duplicate detection a combination of meta data features and semantic features gives the best results. We show that misflagged duplicate questions are even more challenging to model than regular duplicate question detection, but that good results can still be obtained.

We present LearningQ, a challenging educational question generation dataset containing over 230K document-question pairs. It includes 7K instructor-designed questions assessing knowledge concepts being taught and 223K learner-generated questions seeking in-depth understanding of the taught concepts. We show that, compared to existing datasets that can be used to generate educational questions, LearningQ (i) covers a wide range of educational topics and (ii) contains long and cognitively demanding documents for which question generation requires reasoning over the relationships between sentences and paragraphs. As a result, a significant percentage of LearningQ questions (~30%) require higher-order cognitive skills to solve (such as applying, analyzing), in contrast to existing question-generation datasets that are designed mostly for the lowest cognitive skill level (i.e. remembering). To understand the effectiveness of existing question generation methods in producing educational questions, we evaluate both rule-based and deep neural network based methods on LearningQ. Extensive experiments show that state-of-the-art methods which perform well on existing datasets cannot generate useful educational questions. This implies that LearningQ is a challenging test bed for the generation of high-quality educational questions and worth further investigation. We open-source the dataset and our codes at https://dataverse.mpi-sws.org/dataverse/icwsm18.

In this paper, we present a framework for Question Difficulty and Expertise Estimation (QDEE) in Community Question Answering sites (CQAs) such as Yahoo! Answers and Stack Overflow, which tackles a fundamental challenge in crowdsourcing: how to appropriately route and assign questions to users with the suitable expertise. This problem domain has been the subject of much research and includes both language-agnostic as well as language conscious solutions. We bring to bear a key language-agnostic insight: that users gain expertise and therefore tend to ask as well as answer more difficult questions over time. We use this insight within the popular competition (directed) graph model to estimate question difficulty and user expertise by identifying key hierarchical structure within said model. An important and novel contribution here is the application of ``social agony'' to this problem domain. Difficulty levels of newly posted questions (the cold-start problem) are estimated by using our QDEE framework and additional textual features. We also propose a model to route newly posted questions to appropriate users based on the difficulty level of the question and the expertise of the user. Extensive experiments on real world CQAs such as Yahoo! Answers and Stack Overflow data demonstrate the improved efficacy of our approach over contemporary state-of-the-art models.

Deep learning has improved performance on many natural language processing (NLP) tasks individually. However, general NLP models cannot emerge within a paradigm that focuses on the particularities of a single metric, dataset, and task. We introduce the Natural Language Decathlon (decaNLP), a challenge that spans ten tasks: question answering, machine translation, summarization, natural language inference, sentiment analysis, semantic role labeling, zero-shot relation extraction, goal-oriented dialogue, semantic parsing, and commonsense pronoun resolution. We cast all tasks as question answering over a context. Furthermore, we present a new Multitask Question Answering Network (MQAN) jointly learns all tasks in decaNLP without any task-specific modules or parameters in the multitask setting. MQAN shows improvements in transfer learning for machine translation and named entity recognition, domain adaptation for sentiment analysis and natural language inference, and zero-shot capabilities for text classification. We demonstrate that the MQAN's multi-pointer-generator decoder is key to this success and performance further improves with an anti-curriculum training strategy. Though designed for decaNLP, MQAN also achieves state of the art results on the WikiSQL semantic parsing task in the single-task setting. We also release code for procuring and processing data, training and evaluating models, and reproducing all experiments for decaNLP.