arXiv subjects

Guangtao Wang

Publications and source records attributed to Guangtao Wang.

25 records · Page 2Linked to original sources

arXiv2020

Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents

Interpretable multi-hop reading comprehension (RC) over multiple documents is a challenging problem because it demands reasoning over multiple information sources and explaining the answer prediction by providing supporting evidences. In this paper, we propose an effective and interpretable Select, Answer and Explain (SAE) system to solve the multi-document RC problem. Our system first filters out answer-unrelated documents and thus reduce the amount of distraction information. This is achieved by a document classifier trained with a novel pairwise learning-to-rank loss. The selected answer-related documents are then input to a model to jointly predict the answer and supporting sentences. The model is optimized with a multi-task learning objective on both token level for answer prediction and sentence level for supporting sentences prediction, together with an attention-based interaction between these two tasks. Evaluated on HotpotQA, a challenging multi-hop RC data set, the proposed SAE system achieves top competitive performance in distractor setting compared to other existing systems on the leaderboard.

cs.CL↗

arXiv2019

Improving Graph Attention Networks with Large Margin-based Constraints

Graph Attention Networks (GATs) are the state-of-the-art neural architecture for representation learning with graphs. GATs learn attention functions that assign weights to nodes so that different nodes have different influences in the feature aggregation steps. In practice, however, induced attention functions are prone to over-fitting due to the increasing number of parameters and the lack of direct supervision on attention weights. GATs also suffer from over-smoothing at the decision boundary of nodes. Here we propose a framework to address their weaknesses via margin-based constraints on attention during training. We first theoretically demonstrate the over-smoothing behavior of GATs and then develop an approach using constraint on the attention weights according to the class boundary and feature aggregation pattern. Furthermore, to alleviate the over-fitting problem, we propose additional constraints on the graph structure. Extensive experiments and ablation studies on common benchmark datasets demonstrate the effectiveness of our method, which leads to significant improvements over the previous state-of-the-art graph attention methods on all datasets.

cs.LG↗

arXiv2019

Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs

Multi-hop reading comprehension (RC) across documents poses new challenge over single-document RC because it requires reasoning over multiple documents to reach the final answer. In this paper, we propose a new model to tackle the multi-hop RC problem. We introduce a heterogeneous graph with different types of nodes and edges, which is named as Heterogeneous Document-Entity (HDE) graph. The advantage of HDE graph is that it contains different granularity levels of information including candidates, documents and entities in specific document contexts. Our proposed model can do reasoning over the HDE graph with nodes representation initialized with co-attention and self-attention based context encoders. We employ Graph Neural Networks (GNN) based message passing algorithms to accumulate evidences on the proposed HDE graph. Evaluated on the blind test set of the Qangaroo WikiHop data set, our HDE graph based single model delivers competitive result, and the ensemble model achieves the state-of-the-art performance.

cs.CL↗

arXiv2017

Topological Phase Transition in Layered XIn$_2$P$_2$ (X = Ca, Sr)

Based on fully relativistic first-principles calculations, we studied the topological properties of layered XIn$_2$P$_2$ (X = Ca, Sr). Band inversion can be induced by strain without SOC, forming one nodal ring in the k$_z$ = 0 plane, which is protected by the coexistence of time-reversal and mirror-reflection symmetry. Including SOC, a substantial band gap is opened along the nodal line and the line-node semimetal would evolve into a topological insulator. These results reveal a category of materials showing quantum phase transition from trivial semiconductor and topologically nontrivial insulator by the tuneable elastic strain engineering. Our investigations provide a new perspective about the formation of topological line-node semimetal under stain.

cond-mat.mtrl-sci↗

arXiv2014

A Feature Subset Selection Algorithm Automatic Recommendation Method

Many feature subset selection (FSS) algorithms have been proposed, but not all of them are appropriate for a given feature selection problem. At the same time, so far there is rarely a good way to choose appropriate FSS algorithms for the problem at hand. Thus, FSS algorithm automatic recommendation is very important and practically useful. In this paper, a meta learning based FSS algorithm automatic recommendation method is presented. The proposed method first identifies the data sets that are most similar to the one at hand by the k-nearest neighbor classification algorithm, and the distances among these data sets are calculated based on the commonly-used data set characteristics. Then, it ranks all the candidate FSS algorithms according to their performance on these similar data sets, and chooses the algorithms with best performance as the appropriate ones. The performance of the candidate FSS algorithms is evaluated by a multi-criteria metric that takes into account not only the classification accuracy over the selected features, but also the runtime of feature selection and the number of selected features. The proposed recommendation method is extensively tested on 115 real world data sets with 22 well-known and frequently-used different FSS algorithms for five representative classifiers. The results show the effectiveness of our proposed FSS algorithm recommendation method.

cs.LG↗

arXiv2010

Electronic Structure of Weakly Correlated Antiferromagnetic Metal SrCrO3: First-principles calculations

By systematic first-principles calculations, we study the electronic structure and magnetic property of SrCrO$_3$. Our results suggest that SrCrO$_3$ is a weakly correlated antiferromagnetic (AF) metal, a very rare situation in transition-metal oxides. Among various possible AF states, the C-type spin ordering with small amount of orbital polarization (dxy orbital is more occupied than the d_{yz/zx} orbital) is favored. The detailed mechanism to stabilize the C-type AF state is analyzed based on the competition between the itinerant Stoner instability and superexchange, and our results suggest that the magnetic instability rather than the orbital or lattice instabilities plays an important role in this system. The experimentally observed compressive tetragonal distortion can be naturally explained from the C-type AF state. By applying the LDA+$U$ method to study this system, we show that wrong ground state will be obtained if $U$ is large.

cond-mat.mtrl-sci↗

arXiv2008

Phase Diagram of Na$_x$CoO$_2$ Studied by Gutzwiller Density Functional Theory

The ground states of Na$_x$CoO$_2$ ($0.0 0.6$ due to $a_{1g}$ van-Hove singularity near band top; (2) correlated non-magnetic metal without $e_g^{\prime}$ pockets for $0.3<x<0.6$; (3) $e_g^{\prime}$ pockets appear for $x<0.3$, and additional magnetic instability involves. Experimental quasi-particle properties is well explained, and the $a_{1g}$-$e_g^{\prime}$ anti-crossing is attributed to spin-orbital coupling.

cond-mat.str-el↗