paper-with-me

Papers

Can Open-Domain QA Reader Utilize External Knowledge Efficiently like Humans?

2022-11-23 · Neeraj Varshney, Man Luo, Chitta Baral

Recent state-of-the-art open-domain QA models are typically based on a two stage retriever-reader approach in which the retriever first finds the relevant knowledge/passages and the reader then leverages that to predict the answer. Prior work has shown that the performance of the reader usually tends to improve with the increase in the number of these passages. Thus, state-of-the-art models use a large number of passages (e.g. 100) for inference. While the reader in this approach achieves high prediction performance, its inference is computationally very expensive. We humans, on the other hand, use a more efficient strategy while answering: firstly, if we can confidently answer the question using our already acquired knowledge then we do not even use the external knowledge, and in the case when we do require external knowledge, we don't read the entire knowledge at once, instead, we only read that much knowledge that is sufficient to find the answer. Motivated by this procedure, we ask a research question "Can the open-domain QA reader utilize external knowledge efficiently like humans without sacrificing the prediction performance?" Driven by this question, we explore an approach that utilizes both 'closed-book' (leveraging knowledge already present in the model parameters) and 'open-book' inference (leveraging external knowledge). Furthermore, instead of using a large fixed number of passages for open-book inference, we dynamically read the external knowledge in multiple 'knowledge iterations'. Through comprehensive experiments on NQ and TriviaQA datasets, we demonstrate that this dynamic reading approach improves both the 'inference efficiency' and the 'prediction accuracy' of the reader. Comparing with the FiD reader, this approach matches its accuracy by utilizing just 18.32% of its reader inference cost and also outperforms it by achieving up to 55.10% accuracy on NQ Open.

📄 PDF Abstract BibTeX arXiv:2211.12707

Code (0)

등록된 구현이 없습니다.

Tasks

Open-Domain Question AnsweringTriviaQA

Similar Papers 제목 키워드 기반

Towards Better Generalization in Open-Domain Question Answering by Mitigating Context Memorization

2024-04-02 · Zixuan Zhang, Revanth Gangi Reddy, Kevin Small, Tong Zhang 외

Open-domain Question Answering (OpenQA) aims at answering factual questions with an external large-scale knowledge corpus. However, real-world knowledge is not static; it updates and evolves continually. Such a dynamic c…

MemorizationOpen-Domain Question AnsweringQuestion AnsweringWorld Knowledge

Grape: Knowledge Graph Enhanced Passage Reader for Open-domain Question Answering

2022-10-06 · Mingxuan Ju, Wenhao Yu, Tong Zhao, Chuxu Zhang 외

A common thread of open-domain question answering (QA) models employs a retriever-reader pipeline that first retrieves a handful of relevant passages from Wikipedia and then peruses the passages to produce an answer. How…

Entity EmbeddingsGraph Neural NetworkOpen-Domain Question AnsweringQuestion Answering

You Only Need One Model for Open-domain Question Answering

2021-12-14 · Haejun Lee, Akhil Kedia, Jongwon Lee, Ashwin Paranjape 외

Recent approaches to Open-domain Question Answering refer to an external knowledge base using a retriever model, optionally rerank passages with a separate reranker model and generate an answer using another reader model…

Hard AttentionNatural QuestionsOpen-Domain Question AnsweringQuestion Answering+1

REAR: A Relevance-Aware Retrieval-Augmented Framework for Open-Domain Question Answering

2024-02-27 · Yuhao Wang, Ruiyang Ren, Junyi Li, Wayne Xin Zhao 외

Considering the limited internal parametric knowledge, retrieval-augmented generation (RAG) has been widely used to extend the knowledge scope of large language models (LLMs). Despite the extensive efforts on RAG researc…

Open-Domain Question AnsweringQuestion AnsweringRAGRetrieval+1

Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering

2019-11-10 · Sewon Min, Danqi Chen, Luke Zettlemoyer, Hannaneh Hajishirzi

We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships that are derived from an external knowledge…

Natural QuestionsOpen-Domain Question AnsweringQuestion AnsweringReading Comprehension+4