Exploiting Abstract Meaning Representation for Open-Domain Question Answering
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 (1)
Tasks
Abstract Meaning RepresentationDiversityGraph Neural NetworkNatural QuestionsOpen-Domain Question AnsweringQuestion AnsweringTriviaQAMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Robust Subgraph Generation Improves Abstract Meaning Representation Parsing
The Abstract Meaning Representation (AMR) is a representation for open-domain rich semantics, with potential use in fields like event extraction and machine translation. Node generation, typically done using a simple dic…
Abstract Meaning RepresentationAMR ParsingEvent ExtractionMachine Translation+1Emphasising Structured Information: Integrating Abstract Meaning Representation into LLMs for Enhanced Open-Domain Dialogue Evaluation
Automatic open-domain dialogue evaluation has attracted increasing attention. Trainable evaluation metrics, typically trained with true positive and randomly selected negative responses, tend to assign higher scores to r…
Abstract Meaning RepresentationDialogue EvaluationIn-Context LearningRepresentation LearningCross-lingual Abstract Meaning Representation Parsing
Abstract Meaning Representation (AMR) annotation efforts have mostly focused on English. In order to train parsers on other languages, we propose a method based on annotation projection, which involves exploiting annotat…
Abstract Meaning RepresentationStreamSide: A Fully-Customizable Open-Source Toolkit for Efficient Annotation of Meaning Representations
This demonstration paper presents StreamSide, an open-source toolkit for annotating multiple kinds of meaning representations. StreamSide supports frame-based annotation schemes e.g., Abstract Meaning Representation (AMR…
Abstract Meaning RepresentationSentenceAnalogical Reasoning Inside Large Language Models: Concept Vectors and the Limits of Abstraction
Analogical reasoning relies on conceptual abstractions, but it is unclear whether Large Language Models (LLMs) harbor such internal representations. We explore distilled representations from LLM activations and find that…
In-Context LearningMultiple-choice