Open Domain Question Answering over Tables via Dense Retrieval

Understand

Recent advances in open-domain QA have led to strong models based on dense retrieval, but only focused on retrieving textual passages.

• In this work, we tackle open-domain QA over tables for the first time, and show that retrieval can be improved by a retriever designed to handle tabular context.
• We present an effective pre-training procedure for our retriever and improve retrieval quality with mined hard negatives.
• As relevant datasets are missing, we extract a subset of Natural Questions (Kwiatkowski et al., 2019) into a Table QA dataset.