67 citations · 75 across the 8 of their papers we have counts for
16 papers
Compositional Generalization without Trees using Multiset Tagging and Latent Permutations
Matthias Lindemann, Alexander Koller, Ivan Titov
Seq2seq models have been shown to struggle with compositional generalization in semantic parsing, i.e. generalizing to unseen compositions of phenomena that the model handles corre…
What's the Meaning of Superhuman Performance in Today's NLU?
Simone Tedeschi, Johan Bos, Thierry Declerck +9
In the last five years, there has been a significant focus in Natural Language Processing (NLP) on developing larger Pretrained Language Models (PLMs) and introducing benchmarks su…
We're Afraid Language Models Aren't Modeling Ambiguity
Alisa Liu, Zhaofeng Wu, Julian Michael +6
Ambiguity is an intrinsic feature of natural language. Managing ambiguity is a key part of human language understanding, allowing us to anticipate misunderstanding as communicators…
Topic Modelling of Swedish Newspaper Articles about Coronavirus: a Case Study using Latent Dirichlet Allocation Method
Bernadeta Griciūtė, Lifeng Han, Goran Nenadic
Topic Modelling (TM) is from the research branches of natural language understanding (NLU) and natural language processing (NLP) that is to facilitate insightful analysis from larg…
Structural generalization is hard for sequence-to-sequence models
Yuekun Yao, Alexander Koller
Sequence-to-sequence (seq2seq) models have been successful across many NLP tasks, including ones that require predicting linguistic structure. However, recent work on compositional…
Compositional Generalisation with Structured Reordering and Fertility Layers
Matthias Lindemann, Alexander Koller, Ivan Titov
Seq2seq models have been shown to struggle with compositional generalisation, i.e. generalising to new and potentially more complex structures than seen during training. Taking ins…