Related papers: Stochastic Answer Networks for Machine Reading Com…
We present a principled approach for designing stochastic Newton methods for solving finite sum optimization problems. Our approach has two steps. First, we re-write the stationarity conditions as a system of nonlinear equations that…
Large language models (LLMs) achieve strong reasoning performance by allocating substantial computation at inference time, often generating long and verbose reasoning traces. While recent work on efficient reasoning reduces this overhead…
Artificial Neural Networks (ANN) have been popularized in many science and technological areas due to their capacity to solve many complex pattern matching problems. That is the case of Virtual Screening, a research area that studies how to…
Abstract reasoning refers to the ability to analyze information, discover rules at an intangible level, and solve problems in innovative ways. Raven's Progressive Matrices (RPM) test is typically used to examine the capability of abstract…
We present STARC (Structured Annotations for Reading Comprehension), a new annotation framework for assessing reading comprehension with multiple choice questions. Our framework introduces a principled structure for the answer choices and…
Multiple-choice machine reading comprehension is difficult task as its required machines to select the correct option from a set of candidate or possible options using the given passage and question.Reading Comprehension with Multiple…
This paper contributes to a development of randomized methods for neural networks. The proposed learner model is generated incrementally by stochastic configuration (SC) algorithms, termed as Stochastic Configuration Networks (SCNs). In…
For natural language understanding tasks, either machine reading comprehension or natural language inference, both semantics-aware and inference are favorable features of the concerned modeling for better understanding performance. Thus we…
Today's deep learning systems deliver high performance based on end-to-end training. While they deliver strong performance, these systems are hard to interpret. To address this issue, we propose Semantic Bottleneck Networks (SBN): deep…
Although existing machine reading comprehension models are making rapid progress on many datasets, they are far from robust. In this paper, we propose an understanding-oriented machine reading comprehension model to address three kinds of…
Machine Comprehension (MC) is a challenging task in Natural Language Processing field, which aims to guide the machine to comprehend a passage and answer the given question. Many existing approaches on MC task are suffering the inefficiency…
Self-attention networks (SANs) with selective mechanism has produced substantial improvements in various NLP tasks by concentrating on a subset of input words. However, the underlying reasons for their strong performance have not been well…
We present a new method for scaling automatic configuration of computer networks. The key idea is to relax the computationally hard search problem of finding a configuration that satisfies a given specification into an approximate objective…
We consider the problem of interpretable network representation learning for samples of network-valued data. We propose the Principal Component Analysis for Networks (PCAN) algorithm to identify statistically meaningful low-dimensional…
Recent years have witnessed great progress in deep neural networks for real-time applications. However, most existing works do not explicitly consider the general case where the device's state and the available resources fluctuate over…
Reading strategies have been shown to improve comprehension levels, especially for readers lacking adequate prior knowledge. Just as the process of knowledge accumulation is time-consuming for human readers, it is resource-demanding to…
In this paper we propose a neural network model with a novel Sequential Attention layer that extends soft attention by assigning weights to words in an input sequence in a way that takes into account not just how well that word matches a…
Recent development in fully convolutional neural network enables efficient end-to-end learning of semantic segmentation. Traditionally, the convolutional classifiers are taught to learn the representative semantic features of labeled…
This paper studies the task of matching image and sentence, where learning appropriate representations across the multi-modal data appears to be the main challenge. Unlike previous approaches that predominantly deploy symmetrical…
Robot locomotion learning using reinforcement learning suffers from training sample inefficiency and exhibits the non-understandable/black-box nature. Thus, this work presents a novel SME-AGOL to address such problems. Firstly, Sequential…