Order-Planning Neural Text Generation From Structured Data
This work addresses the need for more fluent text generation in NLP tasks like question answering and dialog systems, but it is incremental as it builds on existing encoder-decoder frameworks.
The paper tackles the problem of generating text from structured data by addressing the lack of content order modeling in neural approaches, proposing an order-planning model that improves fluency and achieves higher BLEU, ROUGE, and NIST scores on the WikiBio dataset.
Generating texts from structured data (e.g., a table) is important for various natural language processing tasks such as question answering and dialog systems. In recent studies, researchers use neural language models and encoder-decoder frameworks for table-to-text generation. However, these neural network-based approaches do not model the order of contents during text generation. When a human writes a summary based on a given table, he or she would probably consider the content order before wording. In a biography, for example, the nationality of a person is typically mentioned before occupation in a biography. In this paper, we propose an order-planning text generation model to capture the relationship between different fields and use such relationship to make the generated text more fluent and smooth. We conducted experiments on the WikiBio dataset and achieve significantly higher performance than previous methods in terms of BLEU, ROUGE, and NIST scores.