← Search

Kosuke Akimoto

2 accepted papers

2023

Context Quality Matters in Training Fusion-in-Decoder for Extractive Open-Domain Question Answering

EMNLP 2023long findings

Retrieval-augmented generation models augment knowledge encoded in a language model by providing additional relevant external knowledge (context) during generation. Although it has been shown that the quantity and quality of context impact the performance of retrieval-augmented generation models dur…

Cited by 0SourceScholar
2021

Low-resource Taxonomy Enrichment with Pretrained Language Models

EMNLP 2021main

Taxonomies are symbolic representations of hierarchical relationships between terms or entities. While taxonomies are useful in broad applications, manually updating or maintaining them is labor-intensive and difficult to scale in practice. Conventional supervised methods for this enrichment task fa…

Cited by 35SourcePDFScholar