A Mixed Hierarchical Attention Based Encoder-Decoder Approach for Standard Table Summarization
TL
TL;DR
This work forms the standard table summarization problem, which deals with tables conforming to a single predefined schema, and proposes a mixed hierarchical attention based encoder-decoder model which is able to leverage the structure in addition to the content of the tables.
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 (around 30%) improvement over the current state-of-the-art.
References17 items
1
Coarse-to-Fine Attention Models for Document Summarization
2
Challenges in Data-to-Document Generation
3
Image-to-Markup Generation with Coarse-to-Fine Attention
4
The WebNLG Challenge: Generating Text from DBPedia Data
5