# Learning Neural Templates for Text Generation

arXiv: https://arxiv.org/abs/1808.10122 · HTML: https://mlsanity.com/paper/1808.10122/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Aug 2018.

## Built on by (most cited first, 30 of 61)

- [Large Language Models Can Be Strong Differentially Private Learners](https://mlsanity.com/paper/2110.05679/) (2021)
- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [Skill Induction and Planning with Latent Language](https://mlsanity.com/paper/2110.01517/) (2021)
- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Planning with Learned Entity Prompts for Abstractive Summarization](https://mlsanity.com/paper/2104.07606/) (2021)
- [Plan-then-Generate: Controlled Data-to-Text Generation via Planning](https://mlsanity.com/paper/2108.13740/) (2021)
- [Leveraging Language to Learn Program Abstractions and Search Heuristics](https://mlsanity.com/paper/2106.11053/) (2021)
- [Conditional Generation with a Question-Answering Blueprint](https://mlsanity.com/paper/2207.00397/) (2022)
- [Controlling Hallucinations at Word Level in Data-to-Text Generation](https://mlsanity.com/paper/2102.02810/) (2021)
- [What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization](https://mlsanity.com/paper/2105.00816/) (2021)
- [Benchmarking and Improving Text-to-SQL Generation under Ambiguity](https://mlsanity.com/paper/2310.13659/) (2023)
- [Sequence-to-Sequence Learning with Latent Neural Grammars](https://mlsanity.com/paper/2109.01135/) (2021)
- [Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View](https://mlsanity.com/paper/2102.08585/) (2021)
- [Few-Shot Table-to-Text Generation with Prototype Memory](https://mlsanity.com/paper/2108.12516/) (2021)
- [Neural Pipeline for Zero-Shot Data-to-Text Generation](https://mlsanity.com/paper/2203.16279/) (2022)
- [Translate & Fill: Improving Zero-Shot Multilingual Semantic Parsing with Synthetic Data](https://mlsanity.com/paper/2109.04319/) (2021)
- [BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition](https://mlsanity.com/paper/2105.12848/) (2021)
- [DiscoDVT: Generating Long Text with Discourse-Aware Discrete Variational Transformer](https://mlsanity.com/paper/2110.05999/) (2021)
- [Towards Verifiable Text Generation with Symbolic References](https://mlsanity.com/paper/2311.09188/) (2023)
- [Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization](https://mlsanity.com/paper/2205.14521/) (2022)
- [GenNI: Human-AI Collaboration for Data-Backed Text Generation](https://mlsanity.com/paper/2110.10185/) (2021)
- [Stylized Data-to-Text Generation: A Case Study in the E-Commerce Domain](https://mlsanity.com/paper/2305.03256/) (2023)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models](https://mlsanity.com/paper/2411.03250/) (2024)
- [Search and Learn: Improving Semantic Coverage for Data-to-Text Generation](https://mlsanity.com/paper/2112.02770/) (2021)
- [Regeneration Learning: A Learning Paradigm for Data Generation](https://mlsanity.com/paper/2301.08846/) (2023)
- [AGGGEN: Ordering and Aggregating while Generating](https://mlsanity.com/paper/2106.05580/) (2021)
- [Automatically Summarizing Evidence from Clinical Trials: A Prototype Highlighting Current Challenges](https://mlsanity.com/paper/2303.05392/) (2023)
- [LLM Based Multi-Document Summarization Exploiting Main-Event Biased Monotone Submodular Content Extraction](https://mlsanity.com/paper/2310.03414/) (2023)
- [AutoTemplate: A Simple Recipe for Lexically Constrained Text Generation](https://mlsanity.com/paper/2211.08387/) (2022)

## Abstract (arXiv)

While neural, encoder-decoder models have had significant empirical success in text generation, there remain several unaddressed problems with this style of generation. Encoder-decoder models are largely (a) uninterpretable, and (b) difficult to control in terms of their phrasing or content. This work proposes a neural generation system using a hidden semi-markov model (HSMM) decoder, which learns latent, discrete templates jointly with learning to generate. We show that this model learns useful templates, and that these templates make generation both more interpretable and controllable. Furthermore, we show that this approach scales to real data sets and achieves strong performance nearing that of encoder-decoder text generation models.