In this paper, we study automatic question generation, the task of creating questions from corresponding text passages where some certain spans of the text can serve as the answers. We propose an Extended Answer-aware Network (EAN) which is trained with Word-based Coverage Mechanism (WCM) and decodes with Uncertainty-aware Beam Search (UBS). The EAN represents the target answer by its surrounding sentence with an encoder, and incorporates the information of the extended answer into paragraph representation with gated paragraph-to-answer attention to tackle the problem of the inadequate representation of the target answer. To reduce undesirable repetition, the WCM penalizes repeatedly attending to the same words at different time-steps in the training stage. The UBS aims to seek a better balance between the model confidence in copying words from an input text paragraph and the confidence in generating words from a vocabulary. We conduct experiments on the SQuAD dataset, and the results show our approach achieves significantly performance improvement. Introduction Question generation (QG) aims to automatically generate questions from corresponding natural language text passages.

Question Answering (QA) systems are used to provide proper responses to users' questions automatically. Sentence matching is an essential task in the QA systems and is usually reformulated as a Paraphrase Identification (PI) problem. Given a question, the aim of the task is to find the most similar question from a QA knowledge base. In this paper, we propose a Multi-task Sentence Encoding Model (MSEM) for the PI problem, wherein a connected graph is employed to depict the relation between sentences, and a multi-task learning model is applied to address both the sentence matching and sentence intent classification problem. In addition, we implement a general semantic retrieval framework that combines our proposed model and the Approximate Nearest Neighbor (ANN) technology, which enables us to find the most similar question from all available candidates very quickly during online serving. The experiments show the superiority of our proposed method as compared with the existing sentence matching models.

In 2007 Joel Davis founded Europe's first social media agency, agency:2. The agency has rapidly grown to become an award-winning business with a wide range of leading global clients including Mattel, Microsoft, Sony, Turner and Hillarys. Joel Davis is also co-founder and CEO of Mighty Social, a social ad tech company that takes social ad performance to the next level. Mighty Social creates leading edge digital strategies that push the boundaries of what brands can achieve with innovative social media advertising. Mighty Social has won the Red Herring 100 Europe for the last two years for their use of a patent-pending AI super-tool - The Atom - that is building smarter custom audiences at scale.

Woodside and IBM will work together to re-imagine the way work is done using next-generation technologies such as artificial intelligence (AI) and quantum computing to help Woodside realize its vision of an "intelligent plant." Announced today at IBM's Cloud Innovation Exchange in Sydney by Woodside CEO Peter Coleman and IBM Chairman, President and CEO Ginni Rometty, the collaboration will include Woodside becoming a member of the MIT-IBM Watson AI Lab, which is a collaborative industrial-academic laboratory focused on advancing fundamental AI research. Woodside will also join the IBM Q Network, making it the first commercial organization in Australia to join IBM's quantum computing network. Woodside and IBM will use quantum computing to conduct deep computational simulations across the value chain of Woodside's business. During the past five years Woodside and IBM have worked together to implement cognitive solutions, enabling advances in health and safety, planning and operations, and project engineering.

Most of the existing question answering models can be largely compiled into two categories: i) open domain question answering models that answer generic questions and use large-scale knowledge base along with the targeted web-corpus retrieval and ii) closed domain question answering models that address focused questioning area and use complex deep learning models. Both the above models derive answers through textual comprehension methods. Due to their inability to capture the pedagogical meaning of textual content, these models are not appropriately suited to the educational field for pedagogy. In this paper, we propose an on-the-fly conceptual network model that incorporates educational semantics. The proposed model preserves correlations between conceptual entities by applying intelligent indexing algorithms on the concept network so as to improve answer generation. This model can be utilized for building interactive conversational agents for aiding classroom learning.

The latest report titled global Artificial Intelligence Platform Software market includes the comprehensive study of the present market scope and based on the research that is being carried out the analysts at The Research Insights state that the newest developments that are presently affecting the changing scenario products and services that have high rankings and great feedback are described wisely. The Artificial Intelligence platform provides tools and technologies to build applications with AI-rich capabilities. The algorithms used for formulating the AI platform provide logical models for application developers to fabricate various innovative applications with capabilities, such as speech and voice recognition, text recognition, and predictive analytics. The factors likely to drive the Artificial Intelligence platform market are the substantial increase in data generation, high demand for AI-based solutions, the need to enhance customer experience, and the increasing operational efficiency & reduced cost that AI platforms offer. Among end users, the BFSI segment is projected to have the largest share, while healthcare is expected to have the highest growth rate during the forecast period.

Climbing the AI ladder: How does that affect my business? Businesses love the idea of putting data to work. Building and scaling AI with trust and transparency -- sounds great, right? As enterprises adopt machine learning to streamline customer service and remedial tasks, their employees can provide better customer experience while freeing themselves up to work on more interesting problems. IBM leads the industry in empowering enterprises to accelerate the journey to AI.

Answering complex questions involving multiple entities and relations is a challenging task. Logically, the answer to a complex question should be derived by decomposing the complex question into multiple simple sub-questions and then answering those sub-questions. Existing work has followed this strategy but has not attempted to optimize the order how those sub-questions are answered. As a result, the sub-questions are answered in an arbitrary order, leading to larger search space and higher risk of missing an answer. In this paper, we propose a novel reinforcement learning (RL) approach to answering complex questions that can learn a policy to dynamically decide which sub-question should be answered at each state of reasoning. We leverage the expected value-variance criterion to enable the learned policy to balance between the risk and utility of answering a sub-question. Experiment results show that the RL approach can substantially improve the optimal-ity of ordering the sub-questions, leading to improved accuracy of question answering. The proposed method for learning to order sub-questions is general and can thus be potentially combined with many existing ideas for answering complex questions to enhance their performance. Introduction Real-world questions can be complex, involving multiple interrelated entities and relations, which we refer to as complex questions . For example, "who writes Harry Potter" is a simple question that only involves a single entity and a relation, while "Which city is the filming location of the book written by J.K.Rowling and held Olympics?" is a complex question, which consists of multiple entities and relations. How to automatically answer such complex questions is a significant scientific challenge because it requires a system to capture the dependencies between different components of the questions and reason over them. Recently, some recent work has attempted to tackle such complex questions (Talmor and Berant 2018; Iyyer, Yih, and Chang 2016; Min et al. 2019; Zhang et al. 2019), usually by decomposing a complex question into a sequence of simple questions and answering them based on a computation tree derived from the original question that can capture the dependency between sub-questions as shown in Figure 1.

We investigate a framework for machine reading, inspired by real world information-seeking problems, where a meta question answering system interacts with a black box environment. The environment encapsulates a competitive machine reader based on BERT, providing candidate answers to questions, and possibly some context. To validate the realism of our formulation, we ask humans to play the role of a meta-answerer. With just a small snippet of text around an answer, humans can outperform the machine reader, improving recall. Similarly, a simple machine meta-answerer outperforms the environment, improving both precision and recall on the Natural Questions dataset. The system relies on joint training of answer scoring and the selection of conditioning information.

This paper presents a general approach for open-domain question answering (QA) that models interactions between paragraphs using structural information from a knowledge base. We first describe how to construct a graph of passages from a large corpus, where the relations are either from the knowledge base or the internal structure of Wikipedia. We then introduce a reading comprehension model which takes this graph as an input, to better model relationships across pairs of paragraphs. This approach consistently outperforms competitive baselines in three open-domain QA datasets, WebQuestions, Natural Questions and TriviaQA, improving the pipeline-based state-of-the-art by 3--13%.