Skip to Main content Skip to Navigation
Conference papers

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
ISIR - Institut des Systèmes Intelligents et de Robotique
2 IRIT-IRIS - Recherche d’Information et Synthèse d’Information
IRIT - Institut de recherche en informatique de Toulouse
Abstract : 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.
Complete list of metadata

https://hal.sorbonne-universite.fr/hal-03563311
Contributor : Laure Soulier Connect in order to contact the contributor
Submitted on : Wednesday, February 9, 2022 - 3:58:51 PM
Last modification on : Monday, June 27, 2022 - 12:30:28 PM
Long-term archiving on: : Tuesday, May 10, 2022 - 7:04:20 PM

File

ECIR2022_ComplexAnswerGenerati...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03563311, version 1
  • ARXIV : 2112.04344

Citation

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. ⟨hal-03563311⟩

Share

Metrics

Record views

23

Files downloads

13