Douwe Kiela, Kyunghyun Cho, Patrick Lewis, Ethan Perez, Wen-Tau Yih
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We aim to improve question answering (QA) by decomposing hard questions into simpler sub-questions that existing QA systems are capable of answering. Since labeling questions with decompositions is cumbersome, we take an unsupervised approach to produce sub-questions, also enabling us to leverage millions of questions from the internet. Specifically, we propose an algorithm for One-to-N Unsupervised Sequence transduction (ONUS) that learns to map one hard, multi-hop question to many simpler, singlehop sub-questions. We answer sub-questions with an off-the-shelf QA model and give the resulting answers to a recomposition model that combines them into a final answer. We show large QA improvements on HOTPOTQA over a strong baseline on the original, out-ofdomain, and multi-hop dev sets. ONUS automatically learns to decompose different kinds of questions, while matching the utility of supervised and heuristic decomposition methods for QA and exceeding those methods in fluency. Qualitatively, we find that using subquestions is promising for shedding light on why a QA system makes a prediction. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2002.09758")
get_code_for_paper("2002.09758")
have("2002.09758")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2002.09758.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2002.09758)
Connect an agent — have() is free.