| Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems | ✓ Link | 0.918 | 0.964 | 0.993 | | Dial-MAE | 2023-06-07 |
| Efficient Dynamic Hard Negative Sampling for Dialogue Selection | ✓ Link | 0.917 | 0.965 | 0.994 | | BERT-FP+EDHNS | 2024-08-16 |
| Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue Systems | ✓ Link | 0.916 | 0.965 | 0.994 | | Uni-Enc+BERT-FP | 2021-06-02 |
| Fine-grained Post-training for Improving Retrieval-based Dialogue Systems | ✓ Link | 0.911 | 0.962 | 0.994 | | BERT-FP | 2021-05-24 |
| Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning | | 0.886 | 0.948 | 0.990 | | BERT-UMS+FGC | 2021-11-19 |
| Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue Systems | ✓ Link | 0.886 | 0.946 | 0.989 | | Uni-Encoder | 2021-06-02 |
| Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues | | 0.884 | 0.946 | 0.990 | 0.975 | BERT-SL | 2020-09-14 |
| Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring | ✓ Link | 0.882 | 0.949 | 0.990 | | Poly-encoder | 2019-04-22 |
| Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response Selection | ✓ Link | 0.875 | 0.942 | 0.988 | | UMS_BERT+ | 2020-09-10 |
| An Effective Domain Adaptive Post-Training Method for BERT in Response Selection | ✓ Link | 0.855 | 0.928 | 0.985 | | BERT-VFT | 2019-08-13 |
| Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots | ✓ Link | 0.855 | 0.928 | 0.983 | 0.965 | SA-BERT | 2020-04-07 |
| Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues | ✓ Link | 0.821 | 0.911 | 0.981 | 0.957 | WDMN | 2021-08-17 |
| Multi-hop Selector Network for Multi-turn Response Selection in Retrieval-based Chatbots | ✓ Link | 0.800 | 0.899 | 0.978 | | MSN | 2019-11-01 |
| Sequential Attention-based Network for Noetic End-to-End Response Selection | ✓ Link | 0.796 | 0.894 | 0.975 | | ESIM | 2019-01-09 |
| One Time of Interaction May Not Be Enough: Go Deep with an Interaction-over-Interaction Network for Response Selection in Dialogues | ✓ Link | 0.796 | 0.894 | 0.974 | 0.947 | IoI-local | 2019-07-01 |
| Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots | ✓ Link | 0.794 | 0.889 | 0.974 | 0.946 | IMN | 2019-01-07 |
| TripleNet: Triple Attention Network for Multi-Turn Response Selection in Retrieval-based Chatbots | | 0.790 | 0.885 | 0.970 | 0.943 | TripleNet | 2019-09-24 |
| Sampling Matters! An Empirical Study of Negative Sampling Strategies for Learning of Matching Models in Retrieval-based Dialogue Systems | | 0.785 | 0.883 | 0.974 | 0.944 | DAM-Semi | 2019-11-01 |
| Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network | ✓ Link | 0.767 | 0.874 | 0.969 | 0.938 | DAM | 2018-07-01 |
| Multi-Granularity Representations of Dialog | | 0.753 | | | 0.935 | DAM-MG | 2019-08-26 |
| Modeling Multi-turn Conversation with Deep Utterance Aggregation | ✓ Link | 0.752 | 0.868 | 0.962 | | DUA | 2018-06-24 |
| Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-based Chatbots | ✓ Link | 0.726 | 0.822 | 0.960 | 0.926 | SMN | 2016-12-06 |
| Multi-view Response Selection for Human-Computer Conversation | | 0.662 | 0.801 | 0.951 | 0.908 | Multi-View | 2016-11-01 |
| Improved Deep Learning Baselines for Ubuntu Corpus Dialogs | | 0.630 | 0.780 | 0.944 | 0.895 | Dual-BiLSTM | 2015-10-13 |
| The Ubuntu Dialogue Corpus: A Large Dataset for Research in Unstructured Multi-Turn Dialogue Systems | ✓ Link | 0.604 | 0.745 | 0.926 | 0.878 | Dual-LSTM | 2015-06-30 |