Controllable Language Modelling

1 papers with code • 0 benchmarks • 0 datasets

Given unsupervised Language Modeling as pretraining task, the objective is to generate texts under particular control attributes (Topic, Sentiment)

Most implemented papers

NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist

inimah/metric-preference-checklist 15 May 2023

Our proposed framework provides access: (i) for verifying whether automatic metrics are faithful to human preference, regardless of their correlation level to human; and (ii) for inspecting the strengths and limitations of NLG systems via pairwise evaluation.