We apply a general deep learning framework to address the non-factoid question answering task. Our approach does not rely on any linguistic tools and can be applied to different languages or domains. Various architectures are presented and compared. We create and release a QA corpus and setup a new QA task in the insurance domain. Experimental results demonstrate superior performance compared to the baseline methods and various technologies give further improvements. For this highly challenging task, the top-1 accuracy can reach up to 65.3% on a test set, which indicates a great potential for practical use.
In this paper, a novel design space exploration approach is proposed that enables a concurrent optimization of the topology, the process binding, and the communication routing of a system. Given an application model written in SystemC TLM 2.0, the proposed approach performs a fully automatic optimization by a simultaneous resource allocation, task binding, data mapping, and transaction routing for MPSoC platforms. To cope with the huge complexity of the design space, a transformation of the transaction level model to a graph-based model and symbolic representation that allows multi-objective optimization is presented. Results from optimizing a Motion-JPEG decoder illustrate the effectiveness of the proposed approach.
The FlexRay bus is the prospective automotive standard communication system. For the sake of a high flexibility, the protocol includes a static time-triggered and a dynamic event-triggered segment. This paper is dedicated to the scheduling of the static segment in compliance with the automotive-specific AUTOSAR standard. For the determination of an optimal schedule in terms of the number of used slots, a fast greedy heuristic as well as a complete approach based on Integer Linear Programming are presented. For this purpose, a scheme for the transformation of the scheduling problem into a bin packing problem is proposed. Moreover, a metric and optimization method for the extensibility of partially used slots is introduced. Finally, the provided experimental results give evidence of the benefits of the proposed methods. On a realistic case study, the proposed methods are capable of obtaining better results in a significantly smaller amount of time compared to a commercial tool. Additionally, the experimental results provide a case study on incremental scheduling, a scalability analysis, an exploration use case, and an additional test case to emphasis the robustness and flexibility of the proposed methods.
BERT (Bidirectional Encoder Representations from Transformers) and related pre-trained Transformers have provided large gains across many language understanding tasks, achieving a new state-of-the-art (SOTA). BERT is pretrained on two auxiliary tasks: Masked Language Model and Next Sentence Prediction. In this paper we introduce a new pre-training task inspired by reading comprehension to better align the pre-training from memorization to understanding. Span Selection Pre-Training (SSPT) poses cloze-like training instances, but rather than draw the answer from the model's parameters, it is selected from a relevant passage. We find significant and consistent improvements over both BERT BASE and BERT LARGE on multiple Machine Reading Comprehension (MRC) datasets. Specifically, our proposed model has strong empirical evidence as it obtains SOTA results on Natural Questions, a new benchmark MRC dataset, outperforming BERT LARGE by 3 F1 points on short answer prediction. We also show significant impact in HotpotQA, improving answer prediction F1 by 4 points and supporting fact prediction F1 by 1 point and outperforming the previous best system. Moreover, we show that our pre-training approach is particularly effective when training data is limited, improving the learning curve by a large amount.
Abstract-For complex optimization problems, several population-based heuristics like Multi-Objective Evolutionary Algorithms have been developed. These algorithms are aiming to deliver sufficiently good solutions in an acceptable time. However, for discrete problems that are restricted by several constraints it is mostly a hard problem to even find a single feasible solution. In these cases, the optimization heuristics typically perform poorly as they mainly focus on searching feasible solutions rather than optimizing the objectives.In this paper, we propose a novel methodology to obtain feasible solutions from constrained discrete problems in populationbased optimization heuristics. At this juncture, the constraints have to be converted into the Propositional Satisfiability Problem (SAT). Obtaining a feasible solution is done by the DPLL algorithm which is the core of most modern SAT solvers. It is shown in detail how this methodology is implemented in Multiobjective Evolutionary Algorithms. The SAT solver is used to obtain feasible solutions from the genetic encoded information on arbitrarily hard solvable problems where common methods like penalty functions or repair strategies are failing. Handmade test cases are used to compare various configurations of the SAT solver. On an industrial example, the proposed methodology is compared to common strategies which are used to obtain feasible solutions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.