scholarly journals Translucent Answer Predictions in Multi-Hop Reading Comprehension

2020 ◽  
Vol 34 (05) ◽  
pp. 7700-7707
Author(s):  
G P Shrivatsa Bhargav ◽  
Michael Glass ◽  
Dinesh Garg ◽  
Shirish Shevade ◽  
Saswati Dana ◽  
...  
Keyword(s):  
Reading Comprehension ◽  
Question Answering ◽  
State Of The Art ◽  
Local Context ◽  
The Novel ◽  
Loose Coupling ◽  
Loosely Coupled ◽  
Neural Architecture ◽  
Coupled Networks ◽  
Novel Design

Research on the task of Reading Comprehension style Question Answering (RCQA) has gained momentum in recent years due to the emergence of human annotated datasets and associated leaderboards, for example CoQA, HotpotQA, SQuAD, TriviaQA, etc. While state-of-the-art has advanced considerably, there is still ample opportunity to advance it further on some important variants of the RCQA task. In this paper, we propose a novel deep neural architecture, called TAP (Translucent Answer Prediction), to identify answers and evidence (in the form of supporting facts) in an RCQA task requiring multi-hop reasoning. TAP comprises two loosely coupled networks – Local and Global Interaction eXtractor (LoGIX) and Answer Predictor (AP). LoGIX predicts supporting facts, whereas AP consumes these predicted supporting facts to predict the answer span. The novel design of LoGIX is inspired by two key design desiderata – local context and global interaction– that we identified by analyzing examples of multi-hop RCQA task. The loose coupling between LoGIX and the AP reveals the set of sentences used by the AP in predicting an answer. Therefore, answer predictions of TAP can be interpreted in a translucent manner. TAP offers state-of-the-art performance on the HotpotQA (Yang et al. 2018) dataset – an apt dataset for multi-hop RCQA task – as it occupies Rank-1 on its leaderboard (https://hotpotqa.github.io/) at the time of submission.

scholarly journals Capturing Greater Context for Question Generation

2020 ◽  
Vol 34 (05) ◽  
pp. 9065-9072
Author(s):  
Luu Anh Tuan ◽  
Darsh Shah ◽  
Regina Barzilay
Keyword(s):  
Reading Comprehension ◽  
Question Answering ◽  
State Of The Art ◽  
Attention Mechanism ◽  
Dialogue Systems ◽  
Question Generation ◽  
Multi Stage ◽  
Art Methods ◽  
Relevant Context ◽  
Automatic Question Generation

Automatic question generation can benefit many applications ranging from dialogue systems to reading comprehension. While questions are often asked with respect to long documents, there are many challenges with modeling such long documents. Many existing techniques generate questions by effectively looking at one sentence at a time, leading to questions that are easy and not reflective of the human process of question generation. Our goal is to incorporate interactions across multiple sentences to generate realistic questions for long documents. In order to link a broad document context to the target answer, we represent the relevant context via a multi-stage attention mechanism, which forms the foundation of a sequence to sequence model. We outperform state-of-the-art methods on question generation on three question-answering datasets - SQuAD, MS MARCO and NewsQA. 1

scholarly journals Getting Closer to AI Complete Question Answering: A Set of Prerequisite Real Tasks

2020 ◽  
Vol 34 (05) ◽  
pp. 8722-8731
Author(s):  
Anna Rogers ◽  
Olga Kovaleva ◽  
Matthew Downey ◽  
Anna Rumshisky
Keyword(s):  
Reading Comprehension ◽  
Question Answering ◽  
State Of The Art ◽  
Question Type ◽  
World Knowledge ◽  
Commonsense Reasoning ◽  
Missing Information ◽  
Reasoning Strategies ◽  
Current State

The recent explosion in question answering research produced a wealth of both factoid reading comprehension (RC) and commonsense reasoning datasets. Combining them presents a different kind of task: deciding not simply whether information is present in the text, but also whether a confident guess could be made for the missing information. We present QuAIL, the first RC dataset to combine text-based, world knowledge and unanswerable questions, and to provide question type annotation that would enable diagnostics of the reasoning strategies by a given QA system. QuAIL contains 15K multi-choice questions for 800 texts in 4 domains. Crucially, it offers both general and text-specific questions, unlikely to be found in pretraining data. We show that QuAIL poses substantial challenges to the current state-of-the-art systems, with a 30% drop in accuracy compared to the most similar existing dataset.

scholarly journals The NarrativeQA Reading Comprehension Challenge

2018 ◽  
Vol 6 ◽  
pp. 317-328 ◽  
Author(s):  
Tomáš Kočiský ◽  
Jonathan Schwarz ◽  
Phil Blunsom ◽  
Chris Dyer ◽  
Karl Moritz Hermann ◽  
...  
Keyword(s):  
Information Retrieval ◽  
Reading Comprehension ◽  
Pattern Matching ◽  
Question Answering ◽  
Local Context ◽  
Artificial Agents ◽  
Learning To Read ◽  
Term Frequency ◽  
Context Similarity

Reading comprehension (RC)—in contrast to information retrieval—requires integrating information and reasoning about events, entities, and their relations across a full document. Question answering is conventionally used to assess RC ability, in both artificial agents and children learning to read. However, existing RC datasets and tasks are dominated by questions that can be solved by selecting answers using superficial information (e.g., local context similarity or global term frequency); they thus fail to test for the essential integrative aspect of RC. To encourage progress on deeper comprehension of language, we present a new dataset and set of tasks in which the reader must answer questions about stories by reading entire books or movie scripts. These tasks are designed so that successfully answering their questions requires understanding the underlying narrative rather than relying on shallow pattern matching or salience. We show that although humans solve the tasks easily, standard RC models struggle on the tasks presented here. We provide an analysis of the dataset and the challenges it presents.

scholarly journals Reinforced Mnemonic Reader for Machine Reading Comprehension

2018 ◽  
Author(s):  
Minghao Hu ◽  
Yuxing Peng ◽  
Zhen Huang ◽  
Xipeng Qiu ◽  
Furu Wei ◽  
...  
Keyword(s):  
Reading Comprehension ◽  
Reinforcement Learning ◽  
Question Answering ◽  
State Of The Art ◽  
Learning Algorithms ◽  
Optimization Approach ◽  
Exact Match ◽  
Machine Reading

In this paper, we introduce the Reinforced Mnemonic Reader for machine reading comprehension tasks, which enhances previous attentive readers in two aspects. First, a reattention mechanism is proposed to refine current attentions by directly accessing to past attentions that are temporally memorized in a multi-round alignment architecture, so as to avoid the problems of attention redundancy and attention deficiency. Second, a new optimization approach, called dynamic-critical reinforcement learning, is introduced to extend the standard supervised method. It always encourages to predict a more acceptable answer so as to address the convergence suppression problem occurred in traditional reinforcement learning algorithms. Extensive experiments on the Stanford Question Answering Dataset (SQuAD) show that our model achieves state-of-the-art results. Meanwhile, our model outperforms previous systems by over 6% in terms of both Exact Match and F1 metrics on two adversarial SQuAD datasets.

scholarly journals Generating Well-Formed Answers by Machine Reading with Stochastic Selector Networks

2020 ◽  
Vol 34 (05) ◽  
pp. 7424-7431
Author(s):  
Bin Bi ◽  
Chen Wu ◽  
Ming Yan ◽  
Wei Wang ◽  
Jiangnan Xia ◽  
...  
Keyword(s):  
Reading Comprehension ◽  
Bayesian Inference ◽  
Latent Variables ◽  
Question Answering ◽  
High Quality ◽  
Neural Architecture ◽  
Public Datasets ◽  
Machine Reading

Question answering (QA) based on machine reading comprehension has been a recent surge in popularity, yet most work has focused on extractive methods. We instead address a more challenging QA problem of generating a well-formed answer by reading and summarizing the paragraph for a given question.For the generative QA task, we introduce a new neural architecture, LatentQA, in which a novel stochastic selector network composes a well-formed answer with words selected from the question, the paragraph and the global vocabulary, based on a sequence of discrete latent variables. Bayesian inference for the latent variables is performed to train the LatentQA model. The experiments on public datasets of natural answer generation confirm the effectiveness of LatentQA in generating high-quality well-formed answers.

scholarly journals Plant-Based Alternatives to Yogurt: State-of-the-Art and Perspectives of New Biotechnological Challenges

Foods ◽  
2021 ◽  
Vol 10 (2) ◽  
pp. 316
Author(s):  
Marco Montemurro ◽  
Erica Pontonio ◽  
Rossana Coda ◽  
Carlo Giuseppe Rizzello
Keyword(s):  
Lactic Acid ◽  
Lactic Acid Bacteria ◽  
State Of The Art ◽  
Protein Digestibility ◽  
The Novel ◽  
Sensory Features ◽  
Long Time ◽  
Biotechnological Processes ◽  
Nutritional Compounds ◽  
Increasing Demand

Due to the increasing demand for milk alternatives, related to both health and ethical needs, plant-based yogurt-like products have been widely explored in recent years. With the main goal to obtain snacks similar to the conventional yogurt in terms of textural and sensory properties and ability to host viable lactic acid bacteria for a long-time storage, several plant-derived ingredients (e.g., cereals, pseudocereals, legumes, and fruits) as well as technological solutions (e.g., enzymatic and thermal treatments) have been investigated. The central role of fermentation in yogurt-like production led to specific selections of lactic acid bacteria strains to be used as starters to guarantee optimal textural (e.g., through the synthesis of exo-polysaccharydes), nutritional (high protein digestibility and low content of anti-nutritional compounds), and functional (synthesis of bioactive compounds) features of the products. This review provides an overview of the novel insights on fermented yogurt-like products. The state-of-the-art on the use of unconventional ingredients, traditional and innovative biotechnological processes, and the effects of fermentation on the textural, nutritional, functional, and sensory features, and the shelf life are described. The supplementation of prebiotics and probiotics and the related health effects are also reviewed.

scholarly journals Question-aware memory network for multi-hop question answering in human–robot interaction

2021 ◽  
Author(s):  
Xinmeng Li ◽  
Mamoun Alazab ◽  
Qian Li ◽  
Keping Yu ◽  
Quanjun Yin
Keyword(s):  
Question Answering ◽  
State Of The Art ◽  
Human Robot Interaction ◽  
Knowledge Graph ◽  
Robot Interaction ◽  
Natural Language Question ◽  
Memory Network ◽  
The Given ◽  
Fine Tune ◽  
Language Question

AbstractKnowledge graph question answering is an important technology in intelligent human–robot interaction, which aims at automatically giving answer to human natural language question with the given knowledge graph. For the multi-relation question with higher variety and complexity, the tokens of the question have different priority for the triples selection in the reasoning steps. Most existing models take the question as a whole and ignore the priority information in it. To solve this problem, we propose question-aware memory network for multi-hop question answering, named QA2MN, to update the attention on question timely in the reasoning process. In addition, we incorporate graph context information into knowledge graph embedding model to increase the ability to represent entities and relations. We use it to initialize the QA2MN model and fine-tune it in the training process. We evaluate QA2MN on PathQuestion and WorldCup2014, two representative datasets for complex multi-hop question answering. The result demonstrates that QA2MN achieves state-of-the-art Hits@1 accuracy on the two datasets, which validates the effectiveness of our model.

Calculation and Measurement of the Stiffness and Damping Coefficients for a Low Impedance Hydrodynamic Bearing

1997 ◽  
Vol 119 (1) ◽  
pp. 57-63 ◽  
Author(s):  
M. J. Goodwin ◽  
P. J. Ogrodnik ◽  
M. P. Roach ◽  
Y. Fang
Keyword(s):  
Experimental Data ◽  
Dynamic Stiffness ◽  
Perturbation Technique ◽  
The Novel ◽  
Oil Film ◽  
Hydrodynamic Bearing ◽  
Damping Coefficients ◽  
Stiffness And Damping ◽  
Film Stiffness ◽  
Novel Design

This paper describes a combined theoretical and experimental investigation of the eight oil film stiffness and damping coefficients for a novel low impedance hydrodynamic bearing. The novel design incorporates a recess in the bearing surface which is connected to a standard commercial gas bag accumulator; this arrangement reduces the oil film dynamic stiffness and leads to improved machine response and stability. A finite difference method was used to solve Reynolds equation and yield the pressure distribution in the bearing oil film. Integration of the pressure profile then enabled the fluid film forces to be evaluated. A perturbation technique was used to determine the dynamic pressure components, and hence to determine the eight oil film stiffness and damping coefficients. Experimental data was obtained from a laboratory test rig in which a test bearing, floating on a rotating shaft, was excited by a multi-frequency force signal. Measurements of the resulting relative movement between bearing and journal enabled the oil film coefficients to be measured. The results of the work show good agreement between theoretical and experimental data, and indicate that the oil film impedance of the novel design is considerably lower than that of a conventional bearing.

scholarly journals A novel flexible tool with rotary ultrasonic spindle for fine grinding of tungsten carbide

2018 ◽  
Vol 185 ◽  
pp. 00018
Author(s):  
Albert Wen-Jeng Hsue ◽  
Yi-Zhong Zheng
Keyword(s):  
Tungsten Carbide ◽  
The Novel ◽  
Machining Processes ◽  
Flexible Tool ◽  
Operational Conditions ◽  
Cnc Grinding ◽  
Grinding Conditions ◽  
Novel Design ◽  
Conventional Machining ◽  
Tungsten Steel

Tungsten carbide is a typical difficult-to-cut material by conventional machining processes. In this paper, a novel design of flexible abrasives tool combined with a rotary ultrasonic machining (RUM) spindle is conducted to reduce the labor force significantly. The newly designed flexibility of tool-tip is aimed at preventing overcutting from the CNC grinding. The grinding conditions with resulted surface morphology of the tungsten steel were investigated through Taguchi design of experiment and ANOVA analysis. The machining capability of the novel flexible tool is compared with conventional tools through specific grinding paths under proper operational conditions.

Sign in / Sign up

Export Citation Format

Share Document