1.2k citations · 2.8k across the 60 of their papers we have counts for
11 papers · 1 filter
Enhancing Question Answering for Enterprise Knowledge Bases using Large Language Models
Feihu Jiang, Chuan Qin, Kaichun Yao +4
Efficient knowledge management plays a pivotal role in augmenting both the operational efficiency and the innovative capacity of businesses and organizations. By indexing knowledge…
Scaling Sentence Embeddings with Large Language Models
Ting Jiang, Shaohan Huang, Zhongzhi Luan +2
Large language models (LLMs) have recently garnered significant interest. With in-context learning, LLMs achieve impressive results in various natural language tasks. However, the…
Pruning Pre-trained Language Models Without Fine-Tuning
Ting Jiang, Deqing Wang, Fuzhen Zhuang +2
To overcome the overparameterized problem in Pre-trained Language Models (PLMs), pruning is widely used as a simple and straightforward compression method by directly removing unim…
A Hierarchical Interactive Network for Joint Span-based Aspect-Sentiment Analysis
Wei Chen, Jinglong Du, Zhao Zhang +2
Recently, some span-based methods have achieved encouraging performances for joint aspect-sentiment analysis, which first extract aspects (aspect extraction) by detecting aspect bo…
Exploiting Global and Local Hierarchies for Hierarchical Text Classification
Ting Jiang, Deqing Wang, Leilei Sun +3
Hierarchical text classification aims to leverage label hierarchy in multi-label text classification. Existing methods encode label hierarchy in a global view, where label hierarch…
PromptBERT: Improving BERT Sentence Embeddings with Prompts
Ting Jiang, Jian Jiao, Shaohan Huang +7
We propose PromptBERT, a novel contrastive learning method for learning better sentence representation. We firstly analyze the drawback of current sentence embedding from original…
Domain Adaptation with Category Attention Network for Deep Sentiment Analysis
Dongbo Xi, Fuzhen Zhuang, Ganbin Zhou +3
Domain adaptation tasks such as cross-domain sentiment classification aim to utilize existing labeled data in the source domain and unlabeled or few labeled data in the target doma…
Improving Non-autoregressive Generation with Mixup Training
Ting Jiang, Shaohan Huang, Zihan Zhang +6
While pre-trained language models have achieved great success on various natural language understanding tasks, how to effectively leverage them into non-autoregressive generation t…
LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification
Ting Jiang, Deqing Wang, Leilei Sun +3
Extreme Multi-label text Classification (XMC) is a task of finding the most relevant labels from a large label set. Nowadays deep learning-based methods have shown significant succ…
E-BERT: A Phrase and Product Knowledge Enhanced Language Model for E-commerce
Denghui Zhang, Zixuan Yuan, Yanchi Liu +3
Pre-trained language models such as BERT have achieved great success in a broad range of natural language processing tasks. However, BERT cannot well support E-commerce related tas…
Cross-Domain Labeled LDA for Cross-Domain Text Classification
Baoyu Jing, Chenwei Lu, Deqing Wang +2
Cross-domain text classification aims at building a classifier for a target domain which leverages data from both source and target domain. One promising idea is to minimize the fe…