Papers accepted to EMNLP

September 8, 2021

We are happy to announce that the following papers have been accepted to this year's Conference on Empirical Methods in Natural Language Processing (EMNLP 2021):

  • “Multi-Sentence Resampling: A Simple Approach to Alleviate Dataset Length Bias and Beam-Search Degradation” by Ivan Provilkov and Andrey Malinin
  • “SPARQLing Database Queries from Intermediate Question Decompositions” by Irina Saparina and Anton Osokin
  • “Uncertainty Measures in Neural Belief Tracking: The Effects on Dialogue Policy Performance” by Carel van Niekerk, Andrey Malinin, Christian Geishauser, Michael Heck, Hsien-chin Lin, Nurul Lubis, Shutong Feng and Milica Gasic