Interactive Machine Comprehension with Dynamic Knowledge Graphs
- URL: http://arxiv.org/abs/2109.00077v1
- Date: Tue, 31 Aug 2021 21:05:22 GMT
- Title: Interactive Machine Comprehension with Dynamic Knowledge Graphs
- Authors: Xingdi Yuan
- Abstract summary: Interactive machine reading comprehension (iMRC) is machine comprehension tasks where knowledge sources are partially observable.
We hypothesize that graph representations are good inductive biases, which can serve as an agent's memory mechanism in iMRC tasks.
We describe methods that dynamically build and update these graphs during information gathering, as well as neural models to encode graph representations in RL agents.
- Score: 9.599169515136436
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Interactive machine reading comprehension (iMRC) is machine comprehension
tasks where knowledge sources are partially observable. An agent must interact
with an environment sequentially to gather necessary knowledge in order to
answer a question. We hypothesize that graph representations are good inductive
biases, which can serve as an agent's memory mechanism in iMRC tasks. We
explore four different categories of graphs that can capture text information
at various levels. We describe methods that dynamically build and update these
graphs during information gathering, as well as neural models to encode graph
representations in RL agents. Extensive experiments on iSQuAD suggest that
graph representations can result in significant performance improvements for RL
agents.
Related papers
- When Graph Data Meets Multimodal: A New Paradigm for Graph Understanding
and Reasoning [54.84870836443311]
The paper presents a new paradigm for understanding and reasoning about graph data by integrating image encoding and multimodal technologies.
This approach enables the comprehension of graph data through an instruction-response format, utilizing GPT-4V's advanced capabilities.
The study evaluates this paradigm on various graph types, highlighting the model's strengths and weaknesses, particularly in Chinese OCR performance and complex reasoning tasks.
arXiv Detail & Related papers (2023-12-16T08:14:11Z) - NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics [10.294767093317404]
We introduce NeuroGraph, a collection of graph-based neuroimaging datasets.
We demonstrate its utility for predicting multiple categories of behavioral and cognitive traits.
arXiv Detail & Related papers (2023-06-09T19:10:16Z) - Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directions [58.220137936626315]
This paper extensively discusses automated graph machine learning approaches.
We introduce AutoGL, our dedicated and the world's first open-source library for automated graph machine learning.
Also, we describe a tailored benchmark that supports unified, reproducible, and efficient evaluations.
arXiv Detail & Related papers (2022-01-04T18:31:31Z) - Learning Representation over Dynamic Graph using Aggregation-Diffusion
Mechanism [4.729833950299859]
We propose an aggregation-diffusion (AD) mechanism that actively propagates information to its neighbor by diffusion after the node updates its embedding through the aggregation mechanism.
In experiments on two real-world datasets in the dynamic link prediction task, the AD mechanism outperforms the baseline models that only use aggregation to propagate information.
arXiv Detail & Related papers (2021-06-03T08:25:42Z) - TCL: Transformer-based Dynamic Graph Modelling via Contrastive Learning [87.38675639186405]
We propose a novel graph neural network approach, called TCL, which deals with the dynamically-evolving graph in a continuous-time fashion.
To the best of our knowledge, this is the first attempt to apply contrastive learning to representation learning on dynamic graphs.
arXiv Detail & Related papers (2021-05-17T15:33:25Z) - Learning to Coordinate via Multiple Graph Neural Networks [16.226702761758595]
MGAN is a new algorithm that combines graph convolutional networks and value-decomposition methods.
We show the amazing ability of the graph network in representation learning by visualizing the output of the graph network.
arXiv Detail & Related papers (2021-04-08T04:33:00Z) - Dynamic Emotion Modeling with Learnable Graphs and Graph Inception
Network [0.0]
We present the Learnable Graph Inception Network (L-GrIN) that jointly learns to recognize emotion and to identify the underlying graph structure in the dynamic data.
We evaluate the proposed architecture on five benchmark emotion recognition databases spanning three different modalities.
arXiv Detail & Related papers (2020-08-06T13:51:31Z) - Jointly Cross- and Self-Modal Graph Attention Network for Query-Based
Moment Localization [77.21951145754065]
We propose a novel Cross- and Self-Modal Graph Attention Network (CSMGAN) that recasts this task as a process of iterative messages passing over a joint graph.
Our CSMGAN is able to effectively capture high-order interactions between two modalities, thus enabling a further precise localization.
arXiv Detail & Related papers (2020-08-04T08:25:24Z) - GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training [62.73470368851127]
Graph representation learning has emerged as a powerful technique for addressing real-world problems.
We design Graph Contrastive Coding -- a self-supervised graph neural network pre-training framework.
We conduct experiments on three graph learning tasks and ten graph datasets.
arXiv Detail & Related papers (2020-06-17T16:18:35Z) - Graph Representation Learning via Graphical Mutual Information
Maximization [86.32278001019854]
We propose a novel concept, Graphical Mutual Information (GMI), to measure the correlation between input graphs and high-level hidden representations.
We develop an unsupervised learning model trained by maximizing GMI between the input and output of a graph neural encoder.
arXiv Detail & Related papers (2020-02-04T08:33:49Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.