# Findings of the E2E NLG Challenge

arXiv: https://arxiv.org/abs/1810.01170 · HTML: https://mlsanity.com/paper/1810.01170/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2018.

## Built on by (most cited first, 28 of 28)

- [A Survey of Data Augmentation Approaches for NLP](https://mlsanity.com/paper/2105.03075/) (2021)
- [Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text](https://mlsanity.com/paper/2202.06935/) (2022)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding](https://mlsanity.com/paper/2104.08455/) (2021)
- [Understanding and Detecting Hallucinations in Neural Machine Translation via Model Introspection](https://mlsanity.com/paper/2301.07779/) (2023)
- [Structural Information Preserving for Graph-to-Text Generation](https://mlsanity.com/paper/2102.06749/) (2021)
- [The Authenticity Gap in Human Evaluation](https://mlsanity.com/paper/2205.11930/) (2022)
- [Underreporting of errors in NLG output, and what to do about it](https://mlsanity.com/paper/2108.01182/) (2021)
- [Improving Compositional Generalization with Self-Training for Data-to-Text Generation](https://mlsanity.com/paper/2110.08467/) (2021)
- [Learning to Reason for Text Generation from Scientific Tables](https://mlsanity.com/paper/2104.08296/) (2021)
- [Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG](https://mlsanity.com/paper/2109.07043/) (2021)
- [Style Control for Schema-Guided Natural Language Generation](https://mlsanity.com/paper/2109.12211/) (2021)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [Retrieve, Caption, Generate: Visual Grounding for Enhancing Commonsense in Text Generation Models](https://mlsanity.com/paper/2109.03892/) (2021)
- [MERGE: Fast Private Text Generation](https://mlsanity.com/paper/2305.15769/) (2023)
- [SAPPHIRE: Approaches for Enhanced Concept-to-Text Generation](https://mlsanity.com/paper/2108.06643/) (2021)
- [Non-neural Models Matter: A Re-evaluation of Neural Referring Expression Generation Systems](https://mlsanity.com/paper/2203.08274/) (2022)
- [Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation](https://mlsanity.com/paper/2410.09350/) (2024)
- [Better than Random: Reliable NLG Human Evaluation with Constrained Active Sampling](https://mlsanity.com/paper/2406.07967/) (2024)
- [Towards transparency in NLP shared tasks](https://mlsanity.com/paper/2105.05020/) (2021)
- [SLM-Bench: A Comprehensive Benchmark of Small Language Models on Environmental Impacts--Extended Version](https://mlsanity.com/paper/2508.15478/) (2025)
- [Generalising Multilingual Concept-to-Text NLG with Language Agnostic Delexicalisation](https://mlsanity.com/paper/2105.03432/) (2021)
- [Impact of Model Size on Fine-tuned LLM Performance in Data-to-Text Generation: A State-of-the-Art Investigation](https://mlsanity.com/paper/2407.14088/) (2024)
- [Comparing Computational Architectures for Automated Journalism](https://mlsanity.com/paper/2210.04107/) (2022)
- [Self-training from Self-memory in Data-to-text Generation](https://mlsanity.com/paper/2401.10567/) (2024)
- [Evaluating and Improving Graph to Text Generation with Large Language Models](https://mlsanity.com/paper/2501.14497/) (2025)
- [Factual Inconsistency in Data-to-Text Generation Scales Exponentially with LLM Size: A Statistical Validation](https://mlsanity.com/paper/2502.12372/) (2025)
- [Cross-Domain, Multi-Task Data-to-Text Generation without In-Domain Training Data](https://mlsanity.com/paper/2608.23391/) (2026)

## Abstract (arXiv)

This paper summarises the experimental setup and results of the first shared task on end-to-end (E2E) natural language generation (NLG) in spoken dialogue systems. Recent end-to-end generation systems are promising since they reduce the need for data annotation. However, they are currently limited to small, delexicalised datasets. The E2E NLG shared task aims to assess whether these novel approaches can generate better-quality output by learning from a dataset containing higher lexical richness, syntactic complexity and diverse discourse phenomena. We compare 62 systems submitted by 17 institutions, covering a wide range of approaches, including machine learning architectures -- with the majority implementing sequence-to-sequence models (seq2seq) -- as well as systems based on grammatical rules and templates.