activity
20162023
most citedAttention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling

68 citations · 249 across the 16 of their papers we have counts for

collaborators
Showing cs.CLShow all

10 papers · 1 filter

cs.CL20231 cited

Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks

Zixuan Ke, Bing Liu, Wenhan Xiong +2

Continual learning (CL) has two main objectives: preventing catastrophic forgetting (CF) and encouraging knowledge transfer (KT). The existing literature mainly focused on overcomi…

cs.CL202316 cited

Continual Pre-training of Language Models

Zixuan Ke, Yijia Shao, Haowei Lin +3

Language models (LMs) have been instrumental for the rapid advance of natural language processing. This paper studies continual pre-training of LMs, in particular, continual domain…

cs.CL20223 cited

Reinforcement Learning of Multi-Domain Dialog Policies Via Action Embeddings

Jorge A. Mendez, Alborz Geramifard, Mohammad Ghavamzadeh +1

Learning task-oriented dialog policies via reinforcement learning typically requires large amounts of interaction with users, which in practice renders such methods unusable for re…

cs.CL20219 cited

Continual Learning with Knowledge Transfer for Sentiment Classification

Zixuan Ke, Bing Liu, Hao Wang +1

This paper studies continual learning (CL) for sentiment classification (SC). In this setting, the CL system learns a sequence of SC tasks incrementally in a neural network, where…

cs.CL2021

Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks

Zixuan Ke, Hu Xu, Bing Liu

This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks. Although some CL techniques have been proposed for document sentiment class…

cs.CL2021

CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks

Zixuan Ke, Bing Liu, Hu Xu +1

This paper studies continual learning (CL) of a sequence of aspect sentiment classification(ASC) tasks in a particular CL setting called domain incremental learning (DIL). Each tas…