# SAPPHIRE: Approaches for Enhanced Concept-to-Text Generation

arXiv: https://arxiv.org/abs/2108.06643 · HTML: https://mlsanity.com/paper/2108.06643/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 42 references that are in the map.
- First posted on arXiv 15 Aug 2021.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [oLMpics -- On what Language Model Pre-training Captures](https://mlsanity.com/paper/1912.13283/) (2019)
- [COSMIC: COmmonSense knowledge for eMotion Identification in Conversations](https://mlsanity.com/paper/2010.02795/) (2020)
- [KG-BART: Knowledge Graph-Augmented BART for Generative Commonsense Reasoning](https://mlsanity.com/paper/2009.12677/) (2020)
- [CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling](https://mlsanity.com/paper/1811.10996/) (2018)
- [GenAug: Data Augmentation for Finetuning Text Generators](https://mlsanity.com/paper/2010.01794/) (2020)
- [Findings of the E2E NLG Challenge](https://mlsanity.com/paper/1810.01170/) (2018)
- [An Enhanced Knowledge Injection Model for Commonsense Generation](https://mlsanity.com/paper/2012.00366/) (2020)
- [Keep Calm and Switch On! Preserving Sentiment and Fluency in Semantic Text Exchange](https://mlsanity.com/paper/1909.00088/) (2019)
- [Retrieval Enhanced Model for Commonsense Generation](https://mlsanity.com/paper/2105.11174/) (2021)
- [ALOHA: Artificial Learning of Human Attributes for Dialogue Agents](https://mlsanity.com/paper/1910.08293/) (2019)
- [NAREOR: The Narrative Reordering Problem](https://mlsanity.com/paper/2104.06669/) (2021)
- [Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers](https://mlsanity.com/paper/2012.00571/) (2020)
- [Improving Automated Evaluation of Open Domain Dialog via Diverse Reference Augmentation](https://mlsanity.com/paper/2106.02833/) (2021)

## Built on by (most cited first, 8 of 8)

- [Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Models](https://mlsanity.com/paper/2109.03892/) (2021)
- [Contextualized Scene Imagination for Generative Commonsense Reasoning](https://mlsanity.com/paper/2112.06318/) (2021)
- [CHARD: Clinical Health-Aware Reasoning Across Dimensions for Text Generation Models](https://mlsanity.com/paper/2210.04191/) (2022)
- [PANCETTA: Phoneme Aware Neural Completion to Elicit Tongue Twisters Automatically](https://mlsanity.com/paper/2209.06275/) (2022)
- [A Unified Definition of Hallucination: It's The World Model, Stupid!](https://mlsanity.com/paper/2512.21577/) (2025)
- [HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models](https://mlsanity.com/paper/2605.19341/) (2026)
- [PINEAPPLE: Personifying INanimate Entities by Acquiring Parallel Personification data for Learning Enhanced generation](https://mlsanity.com/paper/2209.07752/) (2022)
- [To Memorize or to Retrieve: Scaling the Interaction Between Pretraining and Retrieval](https://mlsanity.com/paper/2604.00715/) (2026)

## Abstract (arXiv)

We motivate and propose a suite of simple but effective improvements for concept-to-text generation called SAPPHIRE: Set Augmentation and Post-hoc PHrase Infilling and REcombination. We demonstrate their effectiveness on generative commonsense reasoning, a.k.a. the CommonGen task, through experiments using both BART and T5 models. Through extensive automatic and human evaluation, we show that SAPPHIRE noticeably improves model performance. An in-depth qualitative analysis illustrates that SAPPHIRE effectively addresses many issues of the baseline model generations, including lack of commonsense, insufficient specificity, and poor fluency.