A Mixed Hierarchical Attention based Encoder-Decoder Approach for Standard Table Summarization
Computation and Language
2019-07-16 v1 Artificial Intelligence
Abstract
Structured data summarization involves generation of natural language summaries from structured input data. In this work, we consider summarizing structured data occurring in the form of tables as they are prevalent across a wide variety of domains. We formulate the standard table summarization problem, which deals with tables conforming to a single predefined schema. To this end, we propose a mixed hierarchical attention based encoder-decoder model which is able to leverage the structure in addition to the content of the tables. Our experiments on the publicly available WEATHERGOV dataset show around 18 BLEU (~ 30%) improvement over the current state-of-the-art.
Cite
@article{arxiv.1804.07790,
title = {A Mixed Hierarchical Attention based Encoder-Decoder Approach for Standard Table Summarization},
author = {Parag Jain and Anirban Laha and Karthik Sankaranarayanan and Preksha Nema and Mitesh M. Khapra and Shreyas Shetty},
journal= {arXiv preprint arXiv:1804.07790},
year = {2019}
}
Comments
Accepted in NAACL-HLT 2018 (Short paper)