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.

文章介绍了一种将 Abstract Meaning Representation 引入 Pretrained Language Models 中的方法 Graph-as-Token（GST），用于提高 Open-Domain Question Answering 任务的性能。实验结果表明，该方法能显著提升系统的性能，并且在集成 AMRs 方面优于替代的 Graph Neural Network 方法。

利用抽象意义表示进行开放域问答

Exploiting Abstract Meaning Representation for Open-Domain Question  Answering

Generative models for open domain question answering have proven to be
competitive, without resorting to external knowledge. While promising, this
approach requires to use models with billions of parameters, which are
expensive to train and query. In this paper, we investigate how much these
models can benefit from retrieving text passages, potentially containing
evidence. We obtain state-of-the-art results on the Natural Questions and
TriviaQA open benchmarks. Interestingly, we observe that the performance of
this method significantly improves when increasing the number of retrieved
passages. This is evidence that generative models are good at aggregating and
combining evidence from multiple passages.

研究使用生成模型在开放领域问答中的表现，发现利用文本段落检索可以显著提高性能，证明生成模型擅长聚合和组合多个段落的证据，同时在 Natural Questions 和 TriviaQA 开放式基准测试中取得最好的结果。

利用生成模型结合段落检索进行开放域问答

Leveraging Passage Retrieval with Generative Models for Open Domain  Question Answering

We present TriviaQA, a challenging reading comprehension dataset containing
over 650K question-answer-evidence triples. TriviaQA includes 95K
question-answer pairs authored by trivia enthusiasts and independently gathered
evidence documents, six per question on average, that provide high quality
distant supervision for answering the questions. We show that, in comparison to
other recently introduced large-scale datasets, TriviaQA (1) has relatively
complex, compositional questions, (2) has considerable syntactic and lexical
variability between questions and corresponding answer-evidence sentences, and
(3) requires more cross sentence reasoning to find answers. We also present two
baseline algorithms: a feature-based classifier and a state-of-the-art neural
network, that performs well on SQuAD reading comprehension. Neither approach
comes close to human performance (23% and 40% vs. 80%), suggesting that
TriviaQA is a challenging testbed that is worth significant future study. Data
and code available at -- this http URL

TriviaQA 是一个具有挑战性的阅读理解数据集，包含超过 650k 个问题 - 答案 - 证据三元组，该数据集需要进行跨句子推理和包含看似复杂、组合式、句法和词汇变化巨大的问题，并提供了两种基线算法：基于特征的分类器和最先进的神经网络，它们在 SQuAD 阅读理解上表现良好，但都无法接近人类表现（23％和 40％与 80％），因此需要进一步的研究。