Follow the knowledge: structural biases and artefacts in knowledge grounded dialog datasets

Source
Proceedings of the Third DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering / Muresan, Smaranda [edit.]; et al. [edit.]- () p. 109-121
Author(s)

Is It Smaller Than a Tennis Ball? Language Models Play the Game of Twenty Questions

Source
Proceedings of the Fifth BlackboxNLP Analyzing and Interpreting Neural Networks for NLP- () p. 80-90
Author(s)

Machine Translation for Multilingual Intent Detection and Slots Filling

Source
Proceedings of the Massively Multilingual Natural Language Understanding Workshop (MMNLU-22)- (2022) p. 69-82
Author(s)

20Q: Overlap-Free World Knowledge Benchmark for Language Models

Source
Proceedings of the 2nd Workshop on Natural Language Generation, Evaluation, and Metrics (GEM)- () p. 494-508
Author(s)