Papers › Adversarial Ranking for Language Generation

Adversarial Ranking for Language Generation

31 May 2017NeurIPS 2017 12arXiv:1705.11001archive 2025-07-28

Kevin Lin, Dianqi Li, Xiaodong He, Zhengyou Zhang, Ming-Ting Sun

Generative adversarial networks (GANs) have great successes on synthesizing data. However, the existing GANs restrict the discriminator to be a binary classifier, and thus limit their learning capacity for tasks that need to synthesize output with rich structures such as natural language descriptions. In this paper, we propose a novel generative adversarial network, RankGAN, for generating high-quality language descriptions. Rather than training the discriminator to learn and assign absolute binary predicate for individual data sample, the proposed RankGAN is able to analyze and rank a collection of human-written and machine-written sentences by giving a reference group. By viewing a set of data samples collectively and evaluating their quality through relative ranking scores, the discriminator is able to make better assessment which in turn helps to learn a better generator. The proposed RankGAN is optimized through the policy gradient technique. Experimental results on multiple public datasets clearly demonstrate the effectiveness of the proposed approach.

PaperPDFConference PDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

desire2020/RankGAN tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient (arXiv:1609.05473; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 7 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Text Generation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text Generation COCO Captions RankGAN BLEU-2 0.850 #3 of 5 Archive leaderboard report
Text Generation COCO Captions RankGAN BLEU-3 0.672 #3 of 5 Archive leaderboard report
Text Generation COCO Captions RankGAN BLEU-4 0.557 #3 of 5 Archive leaderboard report
Text Generation COCO Captions RankGAN BLEU-5 0.544 #3 of 5 Archive leaderboard report
Text Generation Chinese Poems RankGAN BLEU-2 0.812 #1 of 3 Archive leaderboard report
Text Generation EMNLP2017 WMT RankGAN BLEU-2 0.778 #5 of 5 Archive leaderboard report
Text Generation EMNLP2017 WMT RankGAN BLEU-3 0.478 #5 of 5 Archive leaderboard report
Text Generation EMNLP2017 WMT RankGAN BLEU-4 0.411 #5 of 5 Archive leaderboard report
Text Generation EMNLP2017 WMT RankGAN BLEU-5 0.463 #5 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections