Pith. sign in

REVIEW

Improving Adversarial Text Generation by Modeling the Distant Future

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 2005.01279 v1 pith:NJQBT7JN submitted 2020-05-04 cs.CL cs.LG

classification cs.CLcs.LG
keywords textgenerationfocusadversarialaforementionedalleviateapplyapproach
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Auto-regressive text generation models usually focus on local fluency, and may cause inconsistent semantic meaning in long text generation. Further, automatically generating words with similar semantics is challenging, and hand-crafted linguistic rules are difficult to apply. We consider a text planning scheme and present a model-based imitation-learning approach to alleviate the aforementioned issues. Specifically, we propose a novel guider network to focus on the generative process over a longer horizon, which can assist next-word prediction and provide intermediate rewards for generator optimization. Extensive experiments demonstrate that the proposed method leads to improved performance.

Discussion (0). Continue with ORCID to comment.

Pith tools