NettetFew-Shot-Intent-Detection includes popular challenging intent detection datasets with ... DNNC and CPFT, and the 10-shot learning results of all the models are reported by the paper authors. Citation. ... {zhang2024few, title = {Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning}, author = {Zhang, Jianguo and Bui ... NettetYongjun Chen, Zhiwei Liu, Jia Li, Julian McAuley, and Caiming Xiong. 2024. Intent Contrastive Learning for Sequential Recommendation. In WWW. 2172--2182. Google Scholar; Guanyi Chu, Xiao Wang, Chuan Shi, and Xunqiang Jiang. 2024. CuCo: Graph representation with curriculum contrastive learning. In IJCAI. 2300--2306. Google …
Intent Contrastive Learning for Sequential Recommendation
NettetarXiv:2109.06349v1 [cs.CL] 13 Sep 2024 Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning Jian-Guo Zhang1∗, Trung Bui 2, Seunghyun Yoon2, Xiang Chen2, Zhiwei Liu1 Congying Xia1, Quan Hung Tran2, Walter Chang2, Philip Yu1 1 Universityof Illinois at Chicago, Chicago, USA 2Adobe Research, San Jose, USA … NettetarXiv.org e-Print archive bothwell regional health
Co-Modality Graph Contrastive Learning for Imbalanced Node …
NettetIntent Discovery. 9 papers with code • 3 benchmarks • 3 datasets. Given a set of labelled and unlabelled utterances, the idea is to identify existing (known) intents and potential … Nettet9. mar. 2024 · Intent recognition is critical for task-oriented dialogue systems. However, for emerging domains and new services, it is difficult to accurately identify the … NettetThen the acoustic and linguistic embeddings are simul- taneously aligned through cross-modal contrastive learning and fed into an intent classier to predict the intent labels. The model is optimized with two losses: contrastive learn- ing loss from multi-modal embeddings and intent classication loss from the predictions and ground truths. hayabusa feather