CLAIApr 20, 2018

A Mixed Hierarchical Attention based Encoder-Decoder Approach for Standard Table Summarization

arXiv:1804.07790v11101 citations
Originality Incremental advance
AI Analysis

This work addresses table summarization for domains with standardized schemas, representing an incremental advance in structured data processing.

The authors tackled the problem of generating natural language summaries from structured tables conforming to a single schema, proposing a mixed hierarchical attention encoder-decoder model that leverages both table structure and content, achieving an 18 BLEU (~30%) improvement over state-of-the-art on the WEATHERGOV dataset.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes