LogogramNLP: Comparing Visual and Textual Representations of Ancient Logographic Writing Systems for NLP

no code implementations • 8 Aug 2024 • Danlu Chen, Freda Shi, Aditi Agarwal, Jacobo Myerston, Taylor Berg-Kirkpatrick

Standard natural language processing (NLP) pipelines operate on symbolic representations of language, which typically consist of sequences of discrete tokens.

Pixel Sentence Representation Learning

2 code implementations • 13 Feb 2024 • Chenghao Xiao, Zhuoxu Huang, Danlu Chen, G Thomas Hudson, Yizhi Li, Haoran Duan, Chenghua Lin, Jie Fu, Jungong Han, Noura Al Moubayed

To our knowledge, this is the first representation learning method devoid of traditional language models for understanding sentence and document semantics, marking a stride closer to human-like textual comprehension.

Natural Language Inference Representation Learning +3

VizSeq: A Visual Analysis Toolkit for Text Generation Tasks

1 code implementation • IJCNLP 2019 • Changhan Wang, Anirudh Jain, Danlu Chen, Jiatao Gu

Automatic evaluation of text generation tasks (e. g. machine translation, text summarization, image captioning and video description) usually relies heavily on task-specific metrics, such as BLEU and ROUGE.

Benchmarking Image Captioning +5

Predictive Ensemble Learning with Application to Scene Text Detection

no code implementations • 12 May 2019 • Danlu Chen, Xu-Yao Zhang, Wei zhang, Yao Lu, Xiuli Li, Tao Mei

Taking scene text detection as the application, where no suitable ensemble learning strategy exists, PEL can significantly improve the performance, compared to either individual state-of-the-art models, or the fusion of multiple models by non-maximum suppression.

Classification Ensemble Learning +5

A Simple yet Effective Joint Training Method for Cross-Lingual Universal Dependency Parsing

no code implementations • CONLL 2018 • Danlu Chen, Mengxiao Lin, Zhifeng Hu, Xipeng Qiu

This paper describes Fudan{'}s submission to CoNLL 2018{'}s shared task Universal Dependency Parsing.

Dependency Parsing Transfer Learning

Memory-Efficient Implementation of DenseNets

6 code implementations • 21 Jul 2017 • Geoff Pleiss, Danlu Chen, Gao Huang, Tongcheng Li, Laurens van der Maaten, Kilian Q. Weinberger

A 264-layer DenseNet (73M parameters), which previously would have been infeasible to train, can now be trained on a single workstation with 8 NVIDIA Tesla M40 GPUs.

Multi-Scale Dense Networks for Resource Efficient Image Classification

7 code implementations • ICLR 2018 • Gao Huang, Danlu Chen, Tianhong Li, Felix Wu, Laurens van der Maaten, Kilian Q. Weinberger

In this paper we investigate image classification with computational resource limits at test time.

General Classification Handwritten Mathmatical Expression Recognition +1

Cached Long Short-Term Memory Neural Networks for Document-Level Sentiment Classification

no code implementations • EMNLP 2016 • Jiacheng Xu, Danlu Chen, Xipeng Qiu, Xuangjing Huang

Recently, neural networks have achieved great success on sentiment classification due to their ability to alleviate feature engineering.

Classification Feature Engineering +3