.png){kind=icon}
返回
Exploring Dense Retrieval for Dialogue Response Selection
.png){kind=icon}
OA
AI
DOI：10.1145/3632750.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. However, in real-world scenarios, the high computation cost forces existing dialogue response selection models to rank only a small number of candidates, recalled by a coarse-grained model, precluding many high-quality candidates. To overcome this problem, we present a novel and efficient response selection model and a set of tailor-designed learning strategies to train it effectively. The proposed model consists of a dense retrieval module and an interaction layer, which could directly select the proper response from a large corpus. We conduct re-rank and full-rank evaluations on widely used benchmarks to evaluate our proposed model. Extensive experimental results demonstrate that our proposed model notably outperforms the state-of-the-art baselines on both re-rank and full-rank evaluations. Moreover, human evaluation results show that the response quality could be improved further by enlarging the candidate pool with nonparallel corpora. In addition, we also release high-quality benchmarks that are carefully annotated for more accurate dialogue response selection evaluation. All source codes, datasets, model parameters, and other related resources have been publicly available.
Keyword:
Retrieval-based dialogue system
deep semantic hashing
dense retrieval
dialogue evaluation
期刊
IF:
9.1
论文数:
1.2K
被引数:
4.7K
机构
引用论文
分享收藏Recalcitrant Seeds: Short-term Storage Effects in Avicennia marina (Forsk.) Vierh. may be Germination-associated抗性种子：对白骨壤(Avicennia marina (Forsk.) Vierh.)短期储存的影响可能与发芽相关
OAAI
OAAI分享收藏Matrix Effects in the Detection of Pb and Ba in Soils Using Laser-Induced Breakdown Spectroscopy使用激光诱导击穿光谱检测土壤中Pb和Ba的基质效应
PREAI
分享收藏Plasma enhanced deposition of ‘silicon nitride’ for use as an encapsulant for silicon ion-implanted gallium arsenide等离子体增强沉积‘silicon nitride’用于作为硅离子注入砷化镓的封装材料.png)
Vacuum
VacuumIF0
PREAI
分享收藏Stochastic fatigue damage in viscoelastic materials using probabilistic pseudo J-integral Paris' lawOAAI
OAAI分享收藏
查看更多内容