Table Search Using a Deep Contextualized Language Model
This work addresses table search for users needing efficient data retrieval, but it is incremental as it builds on existing BERT and table retrieval methods.
The paper tackled the problem of ad hoc table retrieval by using BERT to encode table content while considering structure and input limits, and incorporating prior features; the result showed that their best approach outperformed previous state-of-the-art methods and BERT baselines by a large margin across different metrics.
Pretrained contextualized language models such as BERT have achieved impressive results on various natural language processing benchmarks. Benefiting from multiple pretraining tasks and large scale training corpora, pretrained models can capture complex syntactic word relations. In this paper, we use the deep contextualized language model BERT for the task of ad hoc table retrieval. We investigate how to encode table content considering the table structure and input length limit of BERT. We also propose an approach that incorporates features from prior literature on table retrieval and jointly trains them with BERT. In experiments on public datasets, we show that our best approach can outperform the previous state-of-the-art method and BERT baselines with a large margin under different evaluation metrics.