Exploiting Abstract Meaning Representation for Open-Domain Question Answering
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 27 of its 36 references that are in the map. First posted on arXiv 26 May 2023.
Builds on
27 of 36 references.
References · 27
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
- 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
- 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
- 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
- 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
- 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,210
- 2017Reading Wikipedia to Answer Open-Domain Questionscited by 777
- 2019Graph Transformer Networkscited by 523
15 more
- 2022Generate rather than Retrieve: Large Language Models are Strong Context Generatorscited by 298
- 2020Distilling Knowledge from Reader to Retriever for Question Answeringcited by 226
- 2022Pure Transformers are Powerful Graph Learnerscited by 188
- 2022Re2G: Retrieve, Rerank, Generatecited by 102
- 2021KG-FiD: Infusing Knowledge Graph in Fusion-in-Decoder for Open-Domain Question Answeringcited by 67
- 2021Can Generative Pre-trained Language Models Serve as Knowledge Bases for Closed-book QA?cited by 62
- 2022Graph Pre-training for AMR Parsing and Generationcited by 55
- 2020Pre-Training Transformers as Energy-Based Cloze Modelscited by 52
- 2021Structural Adapters in Pretrained Language Models for AMR-to-text Generationcited by 48
- 2021R2-D2: A Modular Baseline for Open-Domain Question Answeringcited by 37
- 2021Semantic Representation for Dialogue Modelingcited by 24
- 2022Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answeringcited by 22
- 2021DocAMR: Multi-Sentence AMR Representation and Evaluationcited by 12
- 2020Studying Strategically: Learning to Mask for Closed-book QAcited by 10
- 2022Semantic-based Pre-training for Dialogue Understandingcited by 3
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.