activity
20202023
most citedGPT-RE: In-context Learning for Relation Extraction using Large Language Models

13 citations · 40 across the 13 of their papers we have counts for

collaborators

14 papers

cs.CL2023

Variable-length Neural Interlingua Representations for Zero-shot Neural Machine Translation

Zhuoyuan Mao, Haiyue Song, Raj Dabre +2

The language-independency of encoded representations within multilingual neural machine translation (MNMT) models is crucial for their generalization ability on zero-shot translati…

cs.CL2023

Exploring the Impact of Layer Normalization for Zero-shot Neural Machine Translation

Zhuoyuan Mao, Raj Dabre, Qianying Liu +3

This paper studies the impact of layer normalization (LayerNorm) on zero-shot translation (ZST). Recent efforts for ZST often utilize the Transformer architecture as the backbone,…

cs.CL2023★ 13 cited

GPT-RE: In-context Learning for Relation Extraction using Large Language Models

Zhen Wan, Fei Cheng, Zhuoyuan Mao +4

In spite of the potential for ground-breaking achievements offered by large language models (LLMs) (e.g., GPT-3), they still lag significantly behind fully-supervised baselines (e.…

cs.CL2023

LEALLA: Learning Lightweight Language-agnostic Sentence Embeddings with Knowledge Distillation

Zhuoyuan Mao, Tetsuji Nakagawa

Large-scale language-agnostic sentence embedding models such as LaBSE (Feng et al., 2022) obtain state-of-the-art performance for parallel sentence alignment. However, these large-…

cs.CL2022

Textual Enhanced Contrastive Learning for Solving Math Word Problems

Yibin Shen, Qianying Liu, Zhuoyuan Mao +2

Solving math word problems is the task that analyses the relation of quantities and requires an accurate understanding of contextual natural language information. Recent studies sh…

cs.CL2022★ 2 cited

Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extraction

Zhen Wan, Qianying Liu, Zhuoyuan Mao +3

Relation extraction (RE) has achieved remarkable progress with the help of pre-trained language models. However, existing RE models are usually incapable of handling two situations…