To help bridge the gap between internet vision-style problems and the goal of vision for embodied perception we instantiate a large-scale navigation task - Embodied Question Answering [1] in photo-realistic environments (Matterport 3D). We thoroughly study navigation policies that utilize 3D point clouds, RGB images, or their combination. Our analysis of these models reveals several key findings. We find that two seemingly naive navigation baselines, forward-only and random, are strong navigators and challenging to outperform, due to the specific choice of the evaluation setting presented by [1]. We find a novel lossweighting Figure 1: We extend EmbodiedQA [1] to photorealstic environments, scheme we call Inflection Weighting to be important our agent is spawned in a perceptually and semantically when training recurrent models for navigation with behavior novel environment and tasked with answering a cloning and are able to out perform the baselines question about that environment. We examine the agent's with this technique. We find that point clouds provide a ability to navigate the environment and answer the question richer signal than RGB images for learning obstacle avoidance, by perceiving its environment through point clouds, RGB motivating the use (and continued study) of 3D deep images, or a combination of the two.

In 2014, IBM opened swanky new headquarters for its artificial intelligence division, known as IBM Watson. Inside the glassy tower in lower Manhattan, IBMers can bring prospective clients and visiting journalists into the "immersion room," which resembles a miniature planetarium. There, in the darkened space, visitors sit on swiveling stools while fancy graphics flash around the curved screens covering the walls. It's the closest you can get, IBMers sometimes say, to being inside Watson's electronic brain. One dazzling 2014 demonstration of Watson's brainpower showed off its potential to transform medicine using AI--a goal that IBM CEO Virginia Rometty often calls the company's moon shot. In the demo, Watson took a bizarre collection of patient symptoms and came up with a list of possible diagnoses, each annotated with Watson's confidence level and links to supporting medical literature. Within the comfortable confines of the dome, Watson never failed to impress: Its memory banks held knowledge of every rare disease, and its processors weren't susceptible to the kind of cognitive bias that can throw off doctors. It could crack a tough case in mere seconds. If Watson could bring that instant expertise to hospitals and clinics all around the world, it seemed possible that the AI could reduce diagnosis errors, optimize treatments, and even alleviate doctor shortages--not by replacing doctors but by helping them do their jobs faster and better.

Knowledge graph based simple question answering (KBSQA) is a major area of research within question answering. Although only dealing with simple questions, i.e., questions that can be answered through a single knowledge base (KB) fact, this task is neither simple nor close to being solved. Targeting on the two main steps, subgraph selection and fact selection, the research community has developed sophisticated approaches. However, the importance of subgraph ranking and leveraging the subject--relation dependency of a KB fact have not been sufficiently explored. Motivated by this, we present a unified framework to describe and analyze existing approaches. Using this framework as a starting point, we focus on two aspects: improving subgraph selection through a novel ranking method and leveraging the subject--relation dependency by proposing a joint scoring CNN model with a novel loss function that enforces the well-order of scores. Our methods achieve a new state of the art (85.44% in accuracy) on the SimpleQuestions dataset.

In order to answer semantically-complicated questions about an image, a Visual Question Answering (VQA) model needs to fully understand the visual scene in the image, especially the interactive dynamics between different objects. We propose a Relation-aware Graph Attention Network (ReGAT), which encodes each image into a graph and models multi-type inter-object relations via a graph attention mechanism, to learn question-adaptive relation representations. Two types of visual object relations are explored: (i) Explicit Relations that represent geometric positions and semantic interactions between objects; and (ii) Implicit Relations that capture the hidden dynamics between image regions. Experiments demonstrate that ReGAT outperforms prior state-of-the-art approaches on both VQA 2.0 and VQA-CP v2 datasets. We further show that ReGAT is compatible to existing VQA architectures, and can be used as a generic relation encoder to boost the model performance for VQA.

We consider a novel question answering (QA) task where the machine needs to read from large streaming data (long documents or videos) without knowing when the questions will be given, in which case the existing QA methods fail due to lack of scalability. To tackle this problem, we propose a novel end-to-end reading comprehension method, which we refer to as Episodic Memory Reader (EMR) that sequentially reads the input contexts into an external memory, while replacing memories that are less important for answering unseen questions. Specifically, we train an RL agent to replace a memory entry when the memory is full in order to maximize its QA accuracy at a future timepoint, while encoding the external memory using the transformer architecture to learn representations that considers relative importance between the memory entries. We validate our model on a real-world large-scale textual QA task (TriviaQA) and a video QA task (TVQA), on which it achieves significant improvements over rule-based memory scheduling policies or an RL-based baseline that learns the query-specific importance of each memory independently.

Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage, or the question might be unanswerable. To do well on SQuAD2.0, SQuAD2.0 is a challenging natural language understanding task for existing models, and we release SQuAD2.0 to the community as the successor to SQuAD1.1. We are optimistic that this new dataset will encourage the development of reading comprehension systems that know what they don't know. SQuAD 1.1, the previous version of the SQuAD dataset, contains 100,000 question-answer pairs on 500 articles.

Customer experience management (CXM) programs are necessarily a quantitative endeavor, requiring CX professionals to decipher insights from a sea of customer data. In this post, I will illustrate how you can use IBM Watson Studio to analyze one source of customer data, customer survey responses, to answer two important questions about the health of your customer relationship: 1) what is the current level of satisfaction across the CX touch points and 2) which of these touch points is responsible for ensuring customers are loyal? Customer Experience Management (CXM) programs rely on different types of data that come from a variety of sources. The most popular source of customer feedback is surveys. These two questions will help you understand how well you are meeting the needs of your customers and, more importantly, understand what you need to do to improve customer loyalty.

Artificial intelligence (AI) works as the driver of exponential economic value creation by making its way into our lives. You can assume the development of AI through Amazon's Alexa and Facebook's M to Google's Now and Apple's Siri and thus you can track your future growth, incredible opportunities and expected problems. Today, you can take the example of IBM's Watson. Watson is a question-answering computer system which can give answers to questions created in natural language, hypothesis generation and evaluation; and dynamic learning that is developed in IBM's DeepQA project by a research team led by principal investigator David Ferrucci. Watson was named after IBM's first CEO, industrialist Thomas J. Watson.

Question Answering (QnA) model is one of the very basic systems of Natural Language Processing. In QnA, the Machin Learning based system generates answers from the knowledge base or text paragraphs for the questions posed as input. Various machine learning methods can be implemented to build Question Answering systems. Create a Question Answering Machine Learning model system which will take comprehension and questions as input, process the comprehension and prepare answers from it. With the Concept of Natural Language Processing, we can achieve this objective.

Several inconsistency-tolerant semantics have been introduced for querying inconsistent description logic knowledge bases. The first contribution of this paper is a practical approach for computing the query answers under three well-known such semantics, namely the AR, IAR and brave semantics, in the lightweight description logic DL-LiteR. We show that query answering under the intractable AR semantics can be performed efficiently by using IAR and brave semantics as tractable approximations and encoding the AR entailment problem as a propositional satisfiability (SAT) problem. The second issue tackled in this work is explaining why a tuple is a (non-)answer to a query under these semantics. We define explanations for positive and negative answers under the brave, AR and IAR semantics. We then study the computational properties of explanations in DL-LiteR. For each type of explanation, we analyze the data complexity of recognizing (preferred) explanations and deciding if a given assertion is relevant or necessary. We establish tight connections between intractable explanation problems and variants of SAT, enabling us to generate explanations by exploiting solvers for Boolean satisfaction and optimization problems. Finally, we empirically study the efficiency of our query answering and explanation framework using a benchmark we built upon the well-established LUBM benchmark.