# Compositional Generalization for Data-to-Text Generation

arXiv: https://arxiv.org/abs/2312.02748 · HTML: https://mlsanity.com/paper/2312.02748/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 42 references that are in the map.
- First posted on arXiv 5 Dec 2023.

## Builds on (most cited first, 29 of 29)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Deep Reinforcement Learning for Dialogue Generation](https://mlsanity.com/paper/1606.01541/) (2016)
- [ToTTo: A Controlled Table-To-Text Generation Dataset](https://mlsanity.com/paper/2004.14373/) (2020)
- [The E2E Dataset: New Challenges For End-to-End Generation](https://mlsanity.com/paper/1706.09254/) (2017)
- [Challenges in Data-to-Document Generation](https://mlsanity.com/paper/1707.08052/) (2017)
- [Good-Enough Compositional Data Augmentation](https://mlsanity.com/paper/1904.09545/) (2019)
- [Revisiting Self-Training for Neural Sequence Generation](https://mlsanity.com/paper/1909.13788/) (2019)
- [Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems](https://mlsanity.com/paper/1508.01745/) (2015)
- [Handling Divergent Reference Texts when Evaluating Table-to-Text Generation](https://mlsanity.com/paper/1906.01081/) (2019)
- [Investigating Pretrained Language Models for Graph-to-Text Generation](https://mlsanity.com/paper/2007.08426/) (2020)
- [Text-to-Text Pre-Training for Data-to-Text Tasks](https://mlsanity.com/paper/2005.10433/) (2020)
- [Structured Attention Networks](https://mlsanity.com/paper/1702.00887/) (2017)
- [Few-shot Natural Language Generation for Task-Oriented Dialog](https://mlsanity.com/paper/2002.12328/) (2020)
- [Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge](https://mlsanity.com/paper/1901.07931/) (2019)
- [Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation](https://mlsanity.com/paper/1904.03396/) (2019)
- [Semantic Noise Matters for Neural Natural Language Generation](https://mlsanity.com/paper/1911.03905/) (2019)
- [Plan-then-Generate: Controlled Data-to-Text Generation via Planning](https://mlsanity.com/paper/2108.13740/) (2021)
- [Evaluating Semantic Accuracy of Data-to-Text Generation with Natural Language Inference](https://mlsanity.com/paper/2011.10819/) (2020)
- [Latent Alignment and Variational Attention](https://mlsanity.com/paper/1807.03756/) (2018)
- [Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge Graphs](https://mlsanity.com/paper/2307.07312/) (2023)
- [Improving Compositional Generalization with Self-Training for Data-to-Text Generation](https://mlsanity.com/paper/2110.08467/) (2021)
- [Multi-domain Neural Network Language Generation for Spoken Dialogue Systems](https://mlsanity.com/paper/1603.01232/) (2016)
- [AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation](https://mlsanity.com/paper/2106.05589/) (2021)
- [Evaluating Generative Models for Graph-to-Text Generation](https://mlsanity.com/paper/2307.14712/) (2023)
- [Can Neural Generators for Dialogue Learn Sentence Planning and Discourse Structuring?](https://mlsanity.com/paper/1809.03015/) (2018)
- [Reinforcement Learning Neural Turing Machines - Revised](https://mlsanity.com/paper/1505.00521/) (2015)
- [ChatGPT as Data Augmentation for Compositional Generalization: A Case Study in Open Intent Detection](https://mlsanity.com/paper/2308.13517/) (2023)
- [Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text Generation](https://mlsanity.com/paper/2206.02712/) (2022)

## Built on by (most cited first, 1 of 1)

- [Benchmarking Complex Instruction-Following with Multiple Constraints Composition](https://mlsanity.com/paper/2407.03978/) (2024)

## Abstract (arXiv)

Data-to-text generation involves transforming structured data, often represented as predicate-argument tuples, into coherent textual descriptions. Despite recent advances, systems still struggle when confronted with unseen combinations of predicates, producing unfaithful descriptions (e.g. hallucinations or omissions). We refer to this issue as compositional generalisation, and it encouraged us to create a benchmark for assessing the performance of different approaches on this specific problem. Furthermore, we propose a novel model that addresses compositional generalization by clustering predicates into groups. Our model generates text in a sentence-by-sentence manner, relying on one cluster of predicates at a time. This approach significantly outperforms T5~baselines across all evaluation metrics.Notably, it achieved a 31% improvement over T5 in terms of a metric focused on maintaining faithfulness to the input.