Does Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needs

Hanane Djeddal (1) , Thomas Gérald (1) , Laure Soulier (1) , Karen Pinel-Sauvagnat (2) , Lynda Tamine (2)

1 MLIA - Machine Learning and Information Access
2 IRIT-IRIS - Recherche d’Information et Synthèse d’Information

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.

Mots clés: Answer generation; Complex search tasks; Data-to-text generation

Domaines: Traitement du texte et du document; Intelligence artificielle [cs.AI]; Recherche d'information [cs.IR]

Hanane Djeddal, Thomas Gérald, Laure Soulier, Karen Pinel-Sauvagnat, Lynda Tamine. Does Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needs. 44th European Conference on Information Retrieval (ECIR 2022), Apr 2022, Stavanger, Norway. ⟨10.48550/arXiv.2112.04344⟩. ⟨hal-03563311⟩