# Neural data-to-text generation: A comparison between pipeline and end-to-end architectures

arXiv: https://arxiv.org/abs/1908.09022 · HTML: https://mlsanity.com/paper/1908.09022/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2019.

## Built on by (most cited first, 30 of 51)

- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [JointGT: Graph-Text Joint Representation Learning for Text Generation from Knowledge Graphs](https://mlsanity.com/paper/2106.10502/) (2021)
- [Plan-then-Generate: Controlled Data-to-Text Generation via Planning](https://mlsanity.com/paper/2108.13740/) (2021)
- [Structural Adapters in Pretrained Language Models for AMR-to-text Generation](https://mlsanity.com/paper/2103.09120/) (2021)
- [Controlling Hallucinations at Word Level in Data-to-Text Generation](https://mlsanity.com/paper/2102.02810/) (2021)
- [Data-to-text Generation with Macro Planning](https://mlsanity.com/paper/2102.02723/) (2021)
- [AI Hallucinations: A Misnomer Worth Clarifying](https://mlsanity.com/paper/2401.06796/) (2024)
- [PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation](https://mlsanity.com/paper/2203.09100/) (2022)
- [ByGPT5: End-to-End Style-conditioned Poetry Generation with Token-free Language Models](https://mlsanity.com/paper/2212.10474/) (2022)
- [Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View](https://mlsanity.com/paper/2102.08585/) (2021)
- [Improving Compositional Generalization with Self-Training for Data-to-Text Generation](https://mlsanity.com/paper/2110.08467/) (2021)
- [Neural Pipeline for Zero-Shot Data-to-Text Generation](https://mlsanity.com/paper/2203.16279/) (2022)
- [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022)
- [ASDOT: Any-Shot Data-to-Text Generation with Pretrained Language Models](https://mlsanity.com/paper/2210.04325/) (2022)
- [Stage-wise Fine-tuning for Graph-to-Text Generation](https://mlsanity.com/paper/2105.08021/) (2021)
- [DYPLOC: Dynamic Planning of Content Using Mixed Language Models for Text Generation](https://mlsanity.com/paper/2106.00791/) (2021)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [Soft Prompt Decoding for Multilingual Dense Retrieval](https://mlsanity.com/paper/2305.09025/) (2023)
- [AGGGEN: Ordering and Aggregating while Generating](https://mlsanity.com/paper/2106.05580/) (2021)
- [Non-neural Models Matter: A Re-evaluation of Neural Referring Expression Generation Systems](https://mlsanity.com/paper/2203.08274/) (2022)
- [A Comparative Analysis of Conversational Large Language Models in Knowledge-Based Text Generation](https://mlsanity.com/paper/2402.01495/) (2024)
- [What can Neural Referential Form Selectors Learn?](https://mlsanity.com/paper/2108.06806/) (2021)
- [MOCHA: A Multi-Task Training Approach for Coherent Text Generation from Cognitive Perspective](https://mlsanity.com/paper/2210.14650/) (2022)
- [A Systematic Review of Data-to-Text NLG](https://mlsanity.com/paper/2402.08496/) (2024)
- [Triples-to-isiXhosa (T2X): Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation](https://mlsanity.com/paper/2403.07567/) (2024)
- [Graph-Guided Textual Explanation Generation Framework](https://mlsanity.com/paper/2412.12318/) (2024)
- [AUGUST: an Automatic Generation Understudy for Synthesizing Conversational Recommendation Datasets](https://mlsanity.com/paper/2306.09631/) (2023)
- [Models of reference production: How do they withstand the test of time?](https://mlsanity.com/paper/2307.14817/) (2023)
- [Few-Shot Data-to-Text Generation via Unified Representation and Multi-Source Learning](https://mlsanity.com/paper/2308.05317/) (2023)

## Abstract (arXiv)

Traditionally, most data-to-text applications have been designed using a modular pipeline architecture, in which non-linguistic input data is converted into natural language through several intermediate transformations. In contrast, recent neural models for data-to-text generation have been proposed as end-to-end approaches, where the non-linguistic input is rendered in natural language with much less explicit intermediate representations in-between. This study introduces a systematic comparison between neural pipeline and end-to-end data-to-text approaches for the generation of text from RDF triples. Both architectures were implemented making use of state-of-the art deep learning methods as the encoder-decoder Gated-Recurrent Units (GRU) and Transformer. Automatic and human evaluations together with a qualitative analysis suggest that having explicit intermediate steps in the generation process results in better texts than the ones generated by end-to-end approaches. Moreover, the pipeline models generalize better to unseen inputs. Data and code are publicly available.