Split and Rephrase: Better Evaluation and Stronger Baselines

ACL 2018  ·  Roee Aharoni, Yoav Goldberg ·

Splitting and rephrasing a complex sentence into several shorter sentences that convey the same meaning is a challenging problem in NLP. We show that while vanilla seq2seq models can reach high scores on the proposed benchmark (Narayan et al., 2017), they suffer from memorization of the training set which contains more than 89{\%} of the unique simple sentences from the validation and test sets. To aid this, we present a new train-development-test data split and neural models augmented with a copy-mechanism, outperforming the best reported baseline by 8.68 BLEU and fostering further progress on the task.

PDF Abstract


  Add Datasets introduced or used in this paper

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.