# Dialogue Response Selection with Hierarchical Curriculum Learning

arXiv: https://arxiv.org/abs/2012.14756 · HTML: https://mlsanity.com/paper/2012.14756/

## Key facts

- Cited by 27 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 29 Dec 2020.

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

- [A Contrastive Framework for Neural Text Generation](https://mlsanity.com/paper/2202.06417/) (2022)
- [Contrastive Search Is What You Need For Neural Text Generation](https://mlsanity.com/paper/2210.14140/) (2022)
- [CLINE: Contrastive Learning with Semantic Negative Examples for Natural Language Understanding](https://mlsanity.com/paper/2107.00440/) (2021)
- [Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking](https://mlsanity.com/paper/2106.00291/) (2021)
- [TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning](https://mlsanity.com/paper/2111.04198/) (2021)
- [Hybrid Curriculum Learning for Emotion Recognition in Conversation](https://mlsanity.com/paper/2112.11718/) (2021)
- [PCC: Paraphrasing with Bottom-k Sampling and Cyclic Learning for Curriculum Data Augmentation](https://mlsanity.com/paper/2208.08110/) (2022)
- [ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation](https://mlsanity.com/paper/2311.13258/) (2023)
- [Advances in Multi-turn Dialogue Comprehension: A Survey](https://mlsanity.com/paper/2103.03125/) (2021)
- [Exploring Dense Retrieval for Dialogue Response Selection](https://mlsanity.com/paper/2110.06612/) (2021)
- [Hierarchical Curriculum Learning for AMR Parsing](https://mlsanity.com/paper/2110.07855/) (2021)
- [HiCuLR: Hierarchical Curriculum Learning for Rhetorical Role Labeling of Legal Documents](https://mlsanity.com/paper/2409.18647/) (2024)
- [From Easy to Hard: A Dual Curriculum Learning Framework for Context-Aware Document Ranking](https://mlsanity.com/paper/2208.10226/) (2022)
- [Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning](https://mlsanity.com/paper/2111.10154/) (2021)
- [Momentum Decoding: Open-ended Text Generation As Graph Exploration](https://mlsanity.com/paper/2212.02175/) (2022)
- [Pre-training Multi-party Dialogue Models with Latent Discourse Inference](https://mlsanity.com/paper/2305.15175/) (2023)
- [CellMix: A General Instance Relationship based Method for Data Augmentation Towards Pathology Image Classification](https://mlsanity.com/paper/2301.11513/) (2023)
- [Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue Systems](https://mlsanity.com/paper/2106.01263/) (2021)
- [A Dual-Contrastive Framework for Low-Resource Cross-Lingual Named Entity Recognition](https://mlsanity.com/paper/2204.00796/) (2022)
- [Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection](https://mlsanity.com/paper/2208.09601/) (2022)
- [Contrastive Learning Subspace for Text Clustering](https://mlsanity.com/paper/2408.14119/) (2024)
- [Advances in Multi-turn Dialogue Comprehension: A Survey](https://mlsanity.com/paper/2110.04984/) (2021)
- [Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings](https://mlsanity.com/paper/2204.02710/) (2022)
- [Sparse and Dense Approaches for the Full-rank Retrieval of Responses for Dialogues](https://mlsanity.com/paper/2204.10558/) (2022)
- [On Task-Adaptive Pretraining for Dialogue Response Selection](https://mlsanity.com/paper/2210.04073/) (2022)
- [Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2211.03648/) (2022)
- [Disentangling Curriculum Learning in NLP: Towards a Unifying Taxonomy](https://mlsanity.com/paper/2607.18984/) (2026)

## Abstract (arXiv)

We study the learning of a matching model for dialogue response selection. Motivated by the recent finding that models trained with random negative samples are not ideal in real-world scenarios, we propose a hierarchical curriculum learning framework that trains the matching model in an "easy-to-difficult" scheme. Our learning framework consists of two complementary curricula: (1) corpus-level curriculum (CC); and (2) instance-level curriculum (IC). In CC, the model gradually increases its ability in finding the matching clues between the dialogue context and a response candidate. As for IC, it progressively strengthens the model's ability in identifying the mismatching information between the dialogue context and a response candidate. Empirical studies on three benchmark datasets with three state-of-the-art matching models demonstrate that the proposed learning framework significantly improves the model performance across various evaluation metrics.