# Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue

arXiv: https://arxiv.org/abs/1906.07220 · HTML: https://mlsanity.com/paper/1906.07220/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2019.

## Built on by (most cited first, 30 of 35)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation](https://mlsanity.com/paper/2104.08704/) (2021)
- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding](https://mlsanity.com/paper/2104.08455/) (2021)
- [Representation Noising: A Defence Mechanism Against Harmful Finetuning](https://mlsanity.com/paper/2405.14577/) (2024)
- [Rethinking Explainability as a Dialogue: A Practitioner's Perspective](https://mlsanity.com/paper/2202.01875/) (2022)
- [GEMv2: Multilingual NLG Benchmarking in a Single Line of Code](https://mlsanity.com/paper/2206.11249/) (2022)
- [MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models](https://mlsanity.com/paper/2502.14302/) (2025)
- [ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples](https://mlsanity.com/paper/2210.12374/) (2022)
- [Faithfulness in Natural Language Generation: A Systematic Survey of Analysis, Evaluation and Optimization Methods](https://mlsanity.com/paper/2203.05227/) (2022)
- [KnowHalu: Hallucination Detection via Multi-Form Knowledge Based Factual Checking](https://mlsanity.com/paper/2404.02935/) (2024)
- [Structural Information Preserving for Graph-to-Text Generation](https://mlsanity.com/paper/2102.06749/) (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)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation](https://mlsanity.com/paper/2401.10186/) (2024)
- [Learning to Reason for Text Generation from Scientific Tables](https://mlsanity.com/paper/2104.08296/) (2021)
- [Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labeling](https://mlsanity.com/paper/2102.03551/) (2021)
- [Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio](https://mlsanity.com/paper/2306.15926/) (2023)
- [The Whole Truth and Nothing But the Truth: Faithful and Controllable Dialogue Response Generation with Dataflow Transduction and Constrained Decoding](https://mlsanity.com/paper/2209.07800/) (2022)
- [TabGenie: A Toolkit for Table-to-Text Generation](https://mlsanity.com/paper/2302.14169/) (2023)
- [Generative Subgraph Retrieval for Knowledge Graph-Grounded Dialog Generation](https://mlsanity.com/paper/2410.09350/) (2024)
- [Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation](https://mlsanity.com/paper/2310.18794/) (2023)
- [LUNA: A Model-Based Universal Analysis Framework for Large Language Models](https://mlsanity.com/paper/2310.14211/) (2023)
- [clem:todd: A Framework for the Systematic Benchmarking of LLM-Based Task-Oriented Dialogue System Realisations](https://mlsanity.com/paper/2505.05445/) (2025)
- [RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText Generators](https://mlsanity.com/paper/2205.12590/) (2022)
- [Toward An Optimal Selection of Dialogue Strategies: A Target-Driven Approach for Intelligent Outbound Robots](https://mlsanity.com/paper/2206.10953/) (2022)
- [Are Current Task-oriented Dialogue Systems Able to Satisfy Impolite Users?](https://mlsanity.com/paper/2210.12942/) (2022)
- [Dependency Dialogue Acts -- Annotation Scheme and Case Study](https://mlsanity.com/paper/2302.12944/) (2023)
- [Teaching with Lies: Curriculum DPO on Synthetic Negatives for Hallucination Detection](https://mlsanity.com/paper/2505.17558/) (2025)

## Abstract (arXiv)

Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Avenues like the E2E NLG Challenge have encouraged the development of neural approaches, particularly sequence-to-sequence (Seq2Seq) models for this problem. The semantic representations used, however, are often underspecified, which places a higher burden on the generation model for sentence planning, and also limits the extent to which generated responses can be controlled in a live system. In this paper, we (1) propose using tree-structured semantic representations, like those used in traditional rule-based NLG systems, for better discourse-level structuring and sentence-level planning; (2) introduce a challenging dataset using this representation for the weather domain; (3) introduce a constrained decoding approach for Seq2Seq models that leverages this representation to improve semantic correctness; and (4) demonstrate promising results on our dataset and the E2E dataset.