GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering

• URL: http://arxiv.org/abs/2303.12320v2
• Date: Tue, 18 Apr 2023 05:11:47 GMT
• Title: GrapeQA: GRaph Augmentation and Pruning to Enhance Question-Answering
• Authors: Dhaval Taunk, Lakshya Khanna, Pavan Kandru, Vasudeva Varma, Charu Sharma and Makarand Tapaswi
• Abstract summary: Commonsense question-answering (QA) methods combine the power of pre-trained Language Models (LM) with the reasoning provided by Knowledge Graphs (KG) A typical approach collects nodes relevant to the QA pair from a KG to form a Working Graph followed by reasoning using Graph Neural Networks(GNNs) We propose GrapeQA with two simple improvements on the WG: (i) Prominent Entities for Graph Augmentation identifies relevant text chunks from the QA pair and augments the WG with corresponding latent representations from the LM, and (ii) Context-Aware Node Pruning removes nodes that are less relevant to the QA
• Score: 19.491275771319074
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Commonsense question-answering (QA) methods combine the power of pre-trained Language Models (LM) with the reasoning provided by Knowledge Graphs (KG). A typical approach collects nodes relevant to the QA pair from a KG to form a Working Graph (WG) followed by reasoning using Graph Neural Networks(GNNs). This faces two major challenges: (i) it is difficult to capture all the information from the QA in the WG, and (ii) the WG contains some irrelevant nodes from the KG. To address these, we propose GrapeQA with two simple improvements on the WG: (i) Prominent Entities for Graph Augmentation identifies relevant text chunks from the QA pair and augments the WG with corresponding latent representations from the LM, and (ii) Context-Aware Node Pruning removes nodes that are less relevant to the QA pair. We evaluate our results on OpenBookQA, CommonsenseQA and MedQA-USMLE and see that GrapeQA shows consistent improvements over its LM + KG predecessor (QA-GNN in particular) and large improvements on OpenBookQA.

Related papers

• GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning [21.057810495833063]
  We introduce GNN-RAG, a novel method for combining language understanding abilities of LLMs with the reasoning abilities of GNNs in a retrieval-augmented generation (RAG) style. In our GNN-RAG framework, the GNN acts as a dense subgraph reasoner to extract useful graph information. Experiments show that GNN-RAG achieves state-of-the-art performance in two widely used KGQA benchmarks.
  arXiv  Detail & Related papers  (2024-05-30T15:14:24Z)
• Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation [64.64849950642619]
  We develop an evaluation framework inspired by formal semantics for evaluating text-to-image models. We show that Davidsonian Scene Graph (DSG) produces atomic and unique questions organized in dependency graphs. We also present DSG-1k, an open-sourced evaluation benchmark that includes 1,060 prompts.
  arXiv  Detail & Related papers  (2023-10-27T16:20:10Z)
• Exploiting Abstract Meaning Representation for Open-Domain Question Answering [18.027908933572203]
  We utilize Abstract Meaning Representation (AMR) graphs to assist the model in understanding complex semantic information. Results from Natural Questions (NQ) and TriviaQA (TQ) demonstrate that our GST method can significantly improve performance.
  arXiv  Detail & Related papers  (2023-05-26T16:00:16Z)
• Dynamic Relevance Graph Network for Knowledge-Aware Question Answering [22.06211725256875]
  This work investigates the challenge of learning and reasoning for Commonsense Question Answering given an external source of knowledge. We propose a novel graph neural network architecture, called Dynamic Relevance Graph Network (DRGN) DRGN operates on a given KG subgraph based on the question and answers entities and uses the relevance scores between the nodes to establish new edges.
  arXiv  Detail & Related papers  (2022-09-20T18:52:05Z)
• Question-Answer Sentence Graph for Joint Modeling Answer Selection [122.29142965960138]
  We train and integrate state-of-the-art (SOTA) models for computing scores between question-question, question-answer, and answer-answer pairs. Online inference is then performed to solve the AS2 task on unseen queries.
  arXiv  Detail & Related papers  (2022-02-16T05:59:53Z)
• Relation-Guided Pre-Training for Open-Domain Question Answering [67.86958978322188]
  We propose a Relation-Guided Pre-Training (RGPT-QA) framework to solve complex open-domain questions. We show that RGPT-QA achieves 2.2%, 2.4%, and 6.3% absolute improvement in Exact Match accuracy on Natural Questions, TriviaQA, and WebQuestions.
  arXiv  Detail & Related papers  (2021-09-21T17:59:31Z)
• QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering [122.84513233992422]
  We propose a new model, QA-GNN, which addresses the problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) We show its improvement over existing LM and LM+KG models, as well as its capability to perform interpretable and structured reasoning.
  arXiv  Detail & Related papers  (2021-04-13T17:32:51Z)
• Harvesting and Refining Question-Answer Pairs for Unsupervised QA [95.9105154311491]
  We introduce two approaches to improve unsupervised Question Answering (QA) First, we harvest lexically and syntactically divergent questions from Wikipedia to automatically construct a corpus of question-answer pairs (named as RefQA) Second, we take advantage of the QA model to extract more appropriate answers, which iteratively refines data over RefQA.
  arXiv  Detail & Related papers  (2020-05-06T15:56:06Z)
• Toward Subgraph-Guided Knowledge Graph Question Generation with Graph Neural Networks [53.58077686470096]
  Knowledge graph (KG) question generation (QG) aims to generate natural language questions from KGs and target answers. In this work, we focus on a more realistic setting where we aim to generate questions from a KG subgraph and target answers.
  arXiv  Detail & Related papers  (2020-04-13T15:43:22Z)

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.