# Response Enhanced Semi-supervised Dialogue Query Generation

arXiv: https://arxiv.org/abs/2312.12713 · HTML: https://mlsanity.com/paper/2312.12713/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 20 Dec 2023.

## Builds on (most cited first, 12 of 12)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [Revisiting Self-Training for Neural Sequence Generation](https://mlsanity.com/paper/1909.13788/) (2019)
- [Answering Complex Open-domain Questions Through Iterative Query Generation](https://mlsanity.com/paper/1910.07000/) (2019)
- [KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation](https://mlsanity.com/paper/2004.04100/) (2020)
- [From Statistical Methods to Deep Learning, Automatic Keyphrase Prediction: A Survey](https://mlsanity.com/paper/2305.02579/) (2023)
- [Link the World: Improving Open-domain Conversation with Dynamic Spatiotemporal-aware Knowledge](https://mlsanity.com/paper/2206.14000/) (2022)
- [Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production](https://mlsanity.com/paper/2302.09300/) (2023)

## Built on by (most cited first, 2 of 2)

- [Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal](https://mlsanity.com/paper/2403.01244/) (2024)
- [Mitigating the Negative Impact of Over-association for Conversational Query Production](https://mlsanity.com/paper/2409.19572/) (2024)

## Abstract (arXiv)

Leveraging vast and continually updated knowledge from the Internet has been considered an important ability for a dialogue system. Therefore, the dialogue query generation task is proposed for generating search queries from dialogue histories, which will be submitted to a search engine for retrieving relevant websites on the Internet. In this regard, previous efforts were devoted to collecting conversations with annotated queries and training a query producer (QP) via standard supervised learning. However, these studies still face the challenges of data scarcity and domain adaptation. To address these issues, in this paper, we propose a semi-supervised learning framework -- SemiDQG, to improve model performance with unlabeled conversations. Based on the observation that the search query is typically related to the topic of dialogue response, we train a response-augmented query producer (RA) to provide rich and effective training signals for QP. We first apply a similarity-based query selection strategy to select high-quality RA-generated pseudo queries, which are used to construct pseudo instances for training QP and RA. Then, we adopt the REINFORCE algorithm to further enhance QP, with RA-provided rewards as fine-grained training signals. Experimental results and in-depth analysis of three benchmarks show the effectiveness of our framework in cross-domain and low-resource scenarios. Particularly, SemiDQG significantly surpasses ChatGPT and competitive baselines. Our code is available at urlhttps://github.com/DeepLearnXMU/SemiDQG.