86 citations · 388 across the 32 of their papers we have counts for
7 papers · 1 filter
From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader
Weiwen Xu, Xin Li, Wenxuan Zhang +4
We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models wit…
ConNER: Consistency Training for Cross-lingual Named Entity Recognition
Ran Zhou, Xin Li, Lidong Bing +3
Cross-lingual named entity recognition (NER) suffers from data scarcity in the target languages, especially under zero-shot settings. Existing translate-train or knowledge distilla…
Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations
Linlin Liu, Xingxuan Li, Megh Thakkar +4
Due to the huge amount of parameters, fine-tuning of pretrained language models (PLMs) is prone to overfitting in the low resource scenarios. In this work, we present a novel metho…
Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation
Deng Cai, Xin Li, Jackie Chun-Sing Ho +2
We introduce a new method to improve existing multilingual sentence embeddings with Abstract Meaning Representation (AMR). Compared with the original textual input, AMR is a struct…
PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Tasks
Weiwen Xu, Xin Li, Yang Deng +2
Span identification aims at identifying specific text spans from text input and classifying them into pre-defined categories. Different from previous works that merely leverage the…
A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges
Wenxuan Zhang, Xin Li, Yang Deng +2
As an important fine-grained sentiment analysis problem, aspect-based sentiment analysis (ABSA), aiming to analyze and understand people's opinions at the aspect level, has been at…
Enhancing Cross-lingual Prompting with Dual Prompt Augmentation
Meng Zhou, Xin Li, Yue Jiang +1
Prompting shows promising results in few-shot scenarios. However, its strength for multilingual/cross-lingual problems has not been fully exploited. Zhao and Schütze (2021) made in…