55 citations · 70 across the 11 of their papers we have counts for
12 papers
Beyond Generic: Enhancing Image Captioning with Real-World Knowledge using Vision-Language Pre-Training Model
Kanzhi Cheng, Wenpo Song, Zheng Ma +3
Current captioning approaches tend to generate correct but "generic" descriptions that lack real-world knowledge, e.g., named entities and contextual information. Considering that…
Extrapolating Large Language Models to Non-English by Aligning Languages
Wenhao Zhu, Yunzhe Lv, Qingxiu Dong +6
Existing large language models show disparate capability across different languages, due to the imbalance in the training data. Their performances on English tasks are often strong…
SIFTER: A Task-specific Alignment Strategy for Enhancing Sentence Embeddings
Chao Yu, Wenhao Zhu, Chaoming Liu +2
The paradigm of pre-training followed by fine-tuning on downstream tasks has become the mainstream method in natural language processing tasks. Although pre-trained models have the…
INK: Injecting kNN Knowledge in Nearest Neighbor Machine Translation
Wenhao Zhu, Jingjing Xu, Shujian Huang +2
Neural machine translation has achieved promising results on many translation tasks. However, previous studies have shown that neural models induce a non-smooth representation spac…
On Structural Expressive Power of Graph Transformers
Wenhao Zhu, Tianyu Wen, Guojie Song +2
Graph Transformer has recently received wide attention in the research community with its outstanding performance, yet its structural expressive power has not been well analyzed. I…
Hierarchical Transformer for Scalable Graph Learning
Wenhao Zhu, Tianyu Wen, Guojie Song +2
Graph Transformer is gaining increasing attention in the field of machine learning and has demonstrated state-of-the-art performance on benchmarks for graph representation learning…
Multilingual Machine Translation with Large Language Models: Empirical Results and Analysis
Wenhao Zhu, Hongyi Liu, Qingxiu Dong +5
Large language models (LLMs) have demonstrated remarkable potential in handling multilingual machine translation (MMT). In this paper, we systematically investigate the advantages…
kNN-BOX: A Unified Framework for Nearest Neighbor Generation
Wenhao Zhu, Qianfeng Zhao, Yunzhe Lv +4
Augmenting the base neural model with a token-level symbolic datastore is a novel generation paradigm and has achieved promising results in machine translation (MT). In this paper,…
What Knowledge Is Needed? Towards Explainable Memory for kNN-MT Domain Adaptation
Wenhao Zhu, Shujian Huang, Yunzhe Lv +2
kNN-MT presents a new paradigm for domain adaptation by building an external datastore, which usually saves all target language token occurrences in the parallel corpus. As a resul…
Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation
Fei Yuan, Yinquan Lu, WenHao Zhu +4
Multilingual neural machine translation (MNMT) aims to build a unified model for many language directions. Existing monolithic models for MNMT encounter two challenges: parameter i…
Stepping Back to SMILES Transformers for Fast Molecular Representation Inference
Wenhao Zhu, Ziyao Li, Lingsheng Cai +1
In the intersection of molecular science and deep learning, tasks like virtual screening have driven the need for a high-throughput molecular representation generator on large chem…
FGraDA: A Dataset and Benchmark for Fine-Grained Domain Adaptation in Machine Translation
Wenhao Zhu, Shujian Huang, Tong Pu +6
Previous research for adapting a general neural machine translation (NMT) model into a specific domain usually neglects the diversity in translation within the same domain, which i…