# Low-Resource Response Generation with Template Prior

arXiv: https://arxiv.org/abs/1909.11968 · HTML: https://mlsanity.com/paper/1909.11968/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [UniCoder: Scaling Code Large Language Model via Universal Code](https://mlsanity.com/paper/2406.16441/) (2024)
- [Modulating Language Models with Emotions](https://mlsanity.com/paper/2108.07886/) (2021)
- [Towards Standard Criteria for human evaluation of Chatbots: A Survey](https://mlsanity.com/paper/2105.11197/) (2021)
- [Leveraging Large Language Models for Enhanced NLP Task Performance through Knowledge Distillation and Optimized Training Strategies](https://mlsanity.com/paper/2402.09282/) (2024)
- [New Intent Discovery with Attracting and Dispersing Prototype](https://mlsanity.com/paper/2403.16913/) (2024)
- [ECLIPSE: Semantic Entropy-LCS for Cross-Lingual Industrial Log Parsing](https://mlsanity.com/paper/2405.13548/) (2024)
- [XFormParser: A Simple and Effective Multimodal Multilingual Semi-structured Form Parser](https://mlsanity.com/paper/2405.17336/) (2024)
- [Automatic Document Sketching: Generating Drafts from Analogous Texts](https://mlsanity.com/paper/2106.07192/) (2021)
- [QURG: Question Rewriting Guided Context-Dependent Text-to-SQL Semantic Parsing](https://mlsanity.com/paper/2305.06655/) (2023)

## Abstract (arXiv)

We study open domain response generation with limited message-response pairs. The problem exists in real-world applications but is less explored by the existing work. Since the paired data now is no longer enough to train a neural generation model, we consider leveraging the large scale of unpaired data that are much easier to obtain, and propose response generation with both paired and unpaired data. The generation model is defined by an encoder-decoder architecture with templates as prior, where the templates are estimated from the unpaired data as a neural hidden semi-markov model. By this means, response generation learned from the small paired data can be aided by the semantic and syntactic knowledge in the large unpaired data. To balance the effect of the prior and the input message to response generation, we propose learning the whole generation model with an adversarial approach. Empirical studies on question response generation and sentiment response generation indicate that when only a few pairs are available, our model can significantly outperform several state-of-the-art response generation models in terms of both automatic and human evaluation.