# A Study of BERT for Non-Factoid Question-Answering under Passage Length Constraints

arXiv: https://arxiv.org/abs/1908.06780 · HTML: https://mlsanity.com/paper/1908.06780/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2019.

## Built on by (most cited first, 2 of 2)

- [Interactive Question Answering Systems: Literature Review](https://mlsanity.com/paper/2209.01621/) (2022)
- [Conversational Search with Mixed-Initiative -- Asking Good Clarification Questions backed-up by Passage Retrieval](https://mlsanity.com/paper/2112.07308/) (2021)

## Abstract (arXiv)

We study the use of BERT for non-factoid question-answering, focusing on the passage re-ranking task under varying passage lengths. To this end, we explore the fine-tuning of BERT in different learning-to-rank setups, comprising both point-wise and pair-wise methods, resulting in substantial improvements over the state-of-the-art. We then analyze the effectiveness of BERT for different passage lengths and suggest how to cope with large passages.