# Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings

arXiv: https://arxiv.org/abs/1606.05491 · HTML: https://mlsanity.com/paper/1606.05491/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2016.

## Built on by (most cited first, 27 of 27)

- [Survey of Hallucination in Natural Language Generation](https://mlsanity.com/paper/2202.03629/) (2022)
- [The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics](https://mlsanity.com/paper/2102.01672/) (2021)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey](https://mlsanity.com/paper/2105.04387/) (2021)
- [When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities](https://mlsanity.com/paper/2307.16376/) (2023)
- [CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning](https://mlsanity.com/paper/2204.08426/) (2022)
- [Context-Aware Language Modeling for Goal-Oriented Dialogue Systems](https://mlsanity.com/paper/2204.10198/) (2022)
- [AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentation](https://mlsanity.com/paper/2106.05589/) (2021)
- [Controllable and Diverse Text Generation in E-commerce](https://mlsanity.com/paper/2102.11497/) (2021)
- [Unifying Structured Data as Graph for Data-to-Text Pre-Training](https://mlsanity.com/paper/2401.01183/) (2024)
- [Jointly Improving Language Understanding and Generation with Quality-Weighted Weak Supervision of Automatic Labeling](https://mlsanity.com/paper/2102.03551/) (2021)
- [Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG](https://mlsanity.com/paper/2109.07043/) (2021)
- [GenNI: Human-AI Collaboration for Data-Backed Text Generation](https://mlsanity.com/paper/2110.10185/) (2021)
- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [HyperSDFusion: Bridging Hierarchical Structures in Language and Geometry for Enhanced 3D Text2Shape Generation](https://mlsanity.com/paper/2403.00372/) (2024)
- [AGGGEN: Ordering and Aggregating while Generating](https://mlsanity.com/paper/2106.05580/) (2021)
- [Incremental Beam Manipulation for Natural Language Generation](https://mlsanity.com/paper/2102.02574/) (2021)
- [Multi-View Feature Representation for Dialogue Generation with Bidirectional Distillation](https://mlsanity.com/paper/2102.10780/) (2021)
- [Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy](https://mlsanity.com/paper/2109.05312/) (2021)
- [Document Automation Architectures and Technologies: A Survey](https://mlsanity.com/paper/2109.11603/) (2021)
- [RSTGen: Imbuing Fine-Grained Interpretable Control into Long-FormText Generators](https://mlsanity.com/paper/2205.12590/) (2022)
- [Transforming Multi-Conditioned Generation from Meaning Representation](https://mlsanity.com/paper/2101.04257/) (2021)
- [Document Automation Architectures: Updated Survey in Light of Large Language Models](https://mlsanity.com/paper/2308.09341/) (2023)
- [E2E Refined Dataset](https://mlsanity.com/paper/2211.00513/) (2022)
- [Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2211.03648/) (2022)
- [Exposing the Functionalities of Neurons for Gated Recurrent Unit Based Sequence-to-Sequence Model](https://mlsanity.com/paper/2303.15072/) (2023)
- [VERITYGATE: A Four-Gate Schema-Level Faithfulness Framework and Paired Benchmark for Grounded LLM Narrations over Structured Evidence](https://mlsanity.com/paper/2610.00833/) (2026)

## Abstract (arXiv)

We present a natural language generator based on the sequence-to-sequence approach that can be trained to produce natural language strings as well as deep syntax dependency trees from input dialogue acts, and we use it to directly compare two-step generation with separate sentence planning and surface realization stages to a joint, one-step approach. We were able to train both setups successfully using very little training data. The joint setup offers better performance, surpassing state-of-the-art with regards to n-gram-based scores while providing more relevant outputs.