Challenge: Recent large-scale datasets specify that external knowledge is required to answer questions.
Approach: They propose a model that leverages external knowledge to construct sub-graphs for entities in machine comprehension context.
Outcome: The proposed model achieves state-of-the-art performance on the ReCoRD dataset.

Similar Papers

Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension (P19-1)

Copied to clipboard

Challenge: Recent results show pre-trained language models (LMs) can improve machine reading comprehension (MRC) Experimental results indicate that KT-NET offers significant and consistent improvements over BERT .
Approach: They propose a method that leverages external knowledge bases to improve machine reading comprehension (MRC) KT-NET employs an attention mechanism to select desired knowledge from KBs and fuses selected knowledge with BERT to enable context- and knowledge-aware predictions.
Outcome: The proposed model outperforms baseline models on ReCoRD and SQuAD1.1 benchmarks and ranks 1st on the ReCoDR and SQUAD1.1 leaderboards.
Interactive Machine Comprehension with Dynamic Knowledge Graphs (2021.emnlp-main)

Copied to clipboard

Challenge: Extensive experiments on iSQuAD suggest that graph representations can result in significant performance improvements for RL agents.
Approach: They propose to use graph representations to build and update graphs during information gathering and neural models to encode graph representation in RL agents.
Outcome: Extensive experiments on iSQuAD show that graph representations can improve performance for RL agents.
Document Modeling with Graph Attention Networks for Multi-grained Machine Reading Comprehension (2020.acl-main)

Copied to clipboard

Challenge: Existing approaches to machine reading comprehension treat documents at their hierarchical nature, ignoring their dependencies.
Approach: They propose a machine reading comprehension benchmark with two-grained answers . they use graph attention networks to model documents at their hierarchical nature .
Outcome: The proposed framework outperforms existing systems at long and short answer criteria.
KagNet: Knowledge-Aware Graph Networks for Commonsense Reasoning (D19-1)

Copied to clipboard

Challenge: empowering machines with the ability to perform commonsense reasoning has been seen as the bottleneck of artificial general intelligence .
Approach: They propose a textual inference framework that uses external commonsense knowledge graphs to answer commonsensical questions.
Outcome: The proposed framework is based on graph convolutional networks and LSTMs with a hierarchical path-based attention mechanism.
Automated Graph Generation at Sentence Level for Reading Comprehension Based on Conceptual Graphs (2020.coling-main)

Copied to clipboard

Challenge: Using conceptual graphs, we can embed a sentence into a knowledge embedding in a graph to solve slot-filling challenges in question answering and capture neighbouring connections of reference concept nodes.
Approach: They propose a miscellaneous-context-based method to embed a sentence into a directed graph and a task-agnostic semantics module which integrates the syntactic-semantic information.
Outcome: The proposed method can accommodate slot-filling challenges in typical question answering and capture the neighbouring connections of reference concept nodes.
ReasoningLM: Enabling Structural Subgraph Reasoning in Pre-trained Language Models for Question Answering over Knowledge Graph (2023.emnlp-main)

Copied to clipboard

Challenge: Question Answering over Knowledge Graph (KGQA) aims to find answer entities for natural language questions based on knowledge graphs.
Approach: They propose a subgraph-aware self-attention mechanism to imitate the graph neural network (GNN) based module to perform multi-hop reasoning on KG.
Outcome: The proposed method surpasses state-of-the-art models by a large margin even with fewer updated parameters and less training data.
BERT-MK: Integrating Graph Contextualized Knowledge into Pre-trained Language Models (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing knowledge representation learning methods do not use graph contextualized knowledge.
Approach: They propose to model subgraphs in a medical KG and integrate it with a pre-trained language model to do knowledge generalization.
Outcome: The proposed model achieves state-of-the-art on several medical NLP tasks . it improves on MedERNIE, and the proposed model is effective .
Learning beyond Datasets: Knowledge Graph Augmented Neural Networks for Natural Language Processing (N18-1)

Copied to clipboard

Challenge: Currently, machine learning is limited in scalability and is limited to specific training data.
Approach: They propose to enhance learning models with world knowledge in the form of Knowledge Graph fact triples for natural language processing tasks.
Outcome: The proposed method is highly scalable to the amount of prior information that has to be processed and can be applied to any generic NLP task.
Dynamic Relevance Graph Network for Knowledge-Aware Question Answering (2022.coling-1)

Copied to clipboard

Challenge: Existing approaches to solve commonsense question answering problems often miss some edges between entities, which breaks the reasoning chain.
Approach: They propose a graph neural network architecture that uses relevance as graph edges to establish new edges dynamically for learning node representations in the graph network.
Outcome: The proposed approach shows competitive performance on two QA benchmarks, CommonsenseQA and OpenbookQA, compared to the state-of-the-art published results.
Double-Branch Multi-Attention based Graph Neural Network for Knowledge Graph Completion (2023.acl-long)

Copied to clipboard

Challenge: Existing knowledge graph embedding methods cannot capture local and global information and are not designed well to learn representations of seen entities with sparse neighborhoods in isolated subgraphs.
Approach: They propose a double-branch multi-attention based graph neural network to learn more expressive entity representations which contain rich global-local structural information.
Outcome: The proposed method outperforms a general GNN-based approach for KGC.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations