18 min listen
Relevance-guided Supervision for OpenQA with ColBERT
Relevance-guided Supervision for OpenQA with ColBERT
ratings:
Length:
46 minutes
Released:
Feb 11, 2024
Format:
Podcast episode
Description
Abstract Systems for Open-Domain Question Answering (OpenQA) generally depend on a retriever for finding candidate passages in a large corpus and a reader for extracting answers from those passages. In much recent work, the retriever is a learned component that uses coarse-grained vector representations of questions and passages. We argue that this modeling choice is insufficiently expressive for dealing with the complexity of natural language questions. To address this, we define ColBERT-QA, which adapts the scalable neural retrieval model ColBERT to OpenQA. ColBERT creates fine-grained interactions between questions and passages. We propose an efficient weak supervision strategy that iteratively uses ColBERT to create its own training data. This greatly improves OpenQA retrieval on Natural Questions, SQuAD, and TriviaQA, and the resulting system attains state-of-the-art extractive OpenQA performance on all three datasets.
2020: O. Khattab, Christopher Potts, M. Zaharia
https://arxiv.org/pdf/2007.00814.pdf
2020: O. Khattab, Christopher Potts, M. Zaharia
https://arxiv.org/pdf/2007.00814.pdf
Released:
Feb 11, 2024
Format:
Podcast episode
Titles in the series (100)
Flacuna: Unleashing the Problem Solving Power of Vicuna using FLAN Fine-Tuning: Recently, the release of INSTRUCTEVAL has provided valuable insights into the performance of large language models (LLMs) that utilize encoder-decoder or decoder-only architecture. Interestingly, despite being introduced four years ago, T5-based LLMs... by Papers Read on AI