Papers › MTTN: Multi-Pair Text to Text Narratives for Prompt Generation

MTTN: Multi-Pair Text to Text Narratives for Prompt Generation

21 Jan 2023arXiv:2301.10172archive 2025-07-28

Archan Ghosh, Debgandhar Ghosh, Madhurima Maji, Suchinta Chanda, Kalporup Goswami

The increased interest in diffusion models has opened up opportunities for advancements in generative text modeling. These models can produce impressive images when given a well-crafted prompt, but creating a powerful or meaningful prompt can be hit-or-miss. To address this, we have created a large-scale dataset that is derived and synthesized from real prompts and indexed with popular image-text datasets such as MS-COCO and Flickr. We have also implemented stages that gradually reduce context and increase complexity, which will further enhance the output due to the complex annotations created. The dataset, called MTTN, includes over 2.4 million sentences divided into 5 stages, resulting in a total of over 12 million pairs, and a vocabulary of over 300,000 unique words, providing ample variation. The original 2.4 million pairs are designed to reflect the way language is used on the internet globally, making the dataset more robust for any model trained on it.

PaperPDFCode

Code

mttn2023/mttn officialmentioned in papermentioned on GitHub 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.

Code Syntology ran Syntology

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

Tasks

Text GenerationText2text Generation

Datasets

Introduced by this paper, per the archive.

MTTN

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text2text Generation MTTN: Multi-Pair Text to Text Narratives for Prompt Generation MVP ROUGE-1 93.8372 #1 of 3 Archive leaderboard report
Text2text Generation MTTN: Multi-Pair Text to Text Narratives for Prompt Generation BART ROUGE-1 93.7086 #2 of 3 Archive leaderboard report
Text2text Generation MTTN: Multi-Pair Text to Text Narratives for Prompt Generation T5 ROUGE-1 93.3203 #3 of 3 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.

Methods

Diffusion

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