Does Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needs
This work addresses complex information retrieval tasks for users needing structured answers, but it is incremental as it builds on existing data-to-text generation methods.
The paper tackled the problem of generating structured natural language answers to complex information needs by using a content selection and planning pipeline, showing that planning-based models outperform a text-to-text model on the TREC CAR dataset.
In this work, our aim is to provide a structured answer in natural language to a complex information need. Particularly, we envision using generative models from the perspective of data-to-text generation. We propose the use of a content selection and planning pipeline which aims at structuring the answer by generating intermediate plans. The experimental evaluation is performed using the TREC Complex Answer Retrieval (CAR) dataset. We evaluate both the generated answer and its corresponding structure and show the effectiveness of planning-based models in comparison to a text-to-text model.