Pith. sign in

REVIEW 1 cited by

Unsupervised Evaluation Metrics and Learning Criteria for Non-Parallel Textual Transfer

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1810.11878 v2 pith:BJ5TJF6J submitted 2018-10-28 cs.CL cs.AI

classification cs.CLcs.AI
keywords metricsevaluationlossshentextualtransferaddressdataset
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We consider the problem of automatically generating textual paraphrases with modified attributes or properties, focusing on the setting without parallel data (Hu et al., 2017; Shen et al., 2017). This setting poses challenges for evaluation. We show that the metric of post-transfer classification accuracy is insufficient on its own, and propose additional metrics based on semantic preservation and fluency as well as a way to combine them into a single overall score. We contribute new loss functions and training strategies to address the different metrics. Semantic preservation is addressed by adding a cyclic consistency loss and a loss based on paraphrase pairs, while fluency is improved by integrating losses based on style-specific language models. We experiment with a Yelp sentiment dataset and a new literature dataset that we propose, using multiple models that extend prior work (Shen et al., 2017). We demonstrate that our metrics correlate well with human judgments, at both the sentence-level and system-level. Automatic and manual evaluation also show large improvements over the baseline method of Shen et al. (2017). We hope that our proposed metrics can speed up system development for new textual transfer tasks while also encouraging the community to address our three complementary aspects of transfer quality.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Evaluating Style-Personalized Text Generation: Challenges and Directions

    cs.CL 2025-08 reject novelty 6.0 of 10

    A new style-discrimination benchmark for personalized text generation shows ensemble metrics give only a marginal, possibly test-fitted, edge over the best single judge.

Pith tools