CLMay 26, 2023

Exploiting Abstract Meaning Representation for Open-Domain Question Answering

arXiv:2305.17050v1224 citations
Originality Highly original
AI Analysis

This addresses the challenge of complex semantic understanding in ODQA for users needing accurate answers, though it is incremental as it builds on existing PLM methods with a novel graph integration.

The paper tackles the problem of surface form diversity hindering accurate correlations in Open-Domain Question Answering by using Abstract Meaning Representation graphs to assist models, resulting in up to 2.44/3.17 Exact Match score improvements on Natural Questions and TriviaQA datasets.

The Open-Domain Question Answering (ODQA) task involves retrieving and subsequently generating answers from fine-grained relevant passages within a database. Current systems leverage Pretrained Language Models (PLMs) to model the relationship between questions and passages. However, the diversity in surface form expressions can hinder the model's ability to capture accurate correlations, especially within complex contexts. Therefore, we utilize Abstract Meaning Representation (AMR) graphs to assist the model in understanding complex semantic information. We introduce a method known as Graph-as-Token (GST) to incorporate AMRs into PLMs. Results from Natural Questions (NQ) and TriviaQA (TQ) demonstrate that our GST method can significantly improve performance, resulting in up to 2.44/3.17 Exact Match score improvements on NQ/TQ respectively. Furthermore, our method enhances robustness and outperforms alternative Graph Neural Network (GNN) methods for integrating AMRs. To the best of our knowledge, we are the first to employ semantic graphs in ODQA.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes