Author name cluster

Yang Fan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

AAAI Conference 2024 Conference Paper

TDeLTA: A Light-Weight and Robust Table Detection Method Based on Learning Text Arrangement

Yang Fan
Xiangping Wu
Qingcai Chen
Heng Li
Yan Huang
Zhixiang Cai
Qitian Wu

The diversity of tables makes table detection a great challenge, leading to existing models becoming more tedious and complex. Despite achieving high performance, they often overfit to the table style in training set, and suffer from significant performance degradation when encountering out-of-distribution tables in other domains. To tackle this problem, we start from the essence of the table, which is a set of text arranged in rows and columns. Based on this, we propose a novel, light-weighted and robust Table Detection method based on Learning Text Arrangement, namely TDeLTA. TDeLTA takes the text blocks as input, and then models the arrangement of them with a sequential encoder and an attention module. To locate the tables precisely, we design a text-classification task, classifying the text blocks into 4 categories according to their semantic roles in the tables. Experiments are conducted on both the text blocks parsed from PDF and extracted by open-source OCR tools, respectively. Compared to several state-of-the-art methods, TDeLTA achieves competitive results with only 3.1M model parameters on the large-scale public datasets. Moreover, when faced with the cross-domain data under the 0-shot setting, TDeLTA outperforms baselines by a large margin of nearly 7%, which shows the strong robustness and transferability of the proposed model.

PDF Details DOI

AAAI Conference 2021 Conference Paper

Learning to Reweight with Deep Interactions

Yang Fan
Yingce Xia
Lijun Wu
Shufang Xie
Weiqing Liu
Jiang Bian
Tao Qin
Xiang-Yang Li

Recently, the concept of teaching has been introduced into machine learning, in which a teacher model is used to guide the training of a student model (which will be used in real tasks) through data selection, loss function design, etc. Learning to reweight, which is a specific kind of teaching that reweights training data using a teacher model, receives much attention due to its simplicity and effectiveness. In existing learning to reweight works, the teacher model only utilizes shallow/surface information such as training iteration number and loss/accuracy of the student model from training/validation sets, but ignores the internal states of the student model, which limits the potential of learning to reweight. In this work, we propose an improved data reweighting algorithm, in which the student model provides its internal states to the teacher model, and the teacher model returns adaptive weights of training samples to enhance the training of the student model. The teacher model is jointly trained with the student model using meta gradients propagated from a validation set. Experiments on image classification with clean/noisy labels and neural machine translation empirically demonstrate that our algorithm makes significant improvement over previous methods.

PDF Details

ICML Conference 2020 Conference Paper

Sequence Generation with Mixed Representations

Lijun Wu 0003
Shufang Xie 0003
Yingce Xia
Yang Fan
Jian-Huang Lai
Tao Qin 0001
Tie-Yan Liu

Tokenization is the first step of many natural language processing (NLP) tasks and plays an important role for neural NLP models. Tokenizaton method such as byte-pair encoding (BPE), which can greatly reduce the large vocabulary and deal with out-of-vocabulary words, has shown to be effective and is widely adopted for sequence generation tasks. While various tokenization methods exist, there is no common acknowledgement which is the best. In this work, we propose to leverage the mixed representations from different tokenization methods for sequence generation tasks, in order to boost the model performance with unique characteristics and advantages of individual tokenization methods. Specifically, we introduce a new model architecture to incorporate mixed representations and a co-teaching algorithm to better utilize the diversity of different tokenization methods. Our approach achieves significant improvements on neural machine translation (NMT) tasks with six language pairs (e. g. , English$\leftrightarrow$German, English$\leftrightarrow$Romanian), as well as an abstractive summarization task.

Details

NeurIPS Conference 2018 Conference Paper

Learning to Teach with Dynamic Loss Functions

Lijun Wu
Fei Tian
Yingce Xia
Yang Fan
Tao Qin
Lai Jian-Huang
Tie-Yan Liu

Teaching is critical to human society: it is with teaching that prospective students are educated and human civilization can be inherited and advanced. A good teacher not only provides his/her students with qualified teaching materials (e. g. , textbooks), but also sets up appropriate learning objectives (e. g. , course projects and exams) considering different situations of a student. When it comes to artificial intelligence, treating machine learning models as students, the loss functions that are optimized act as perfect counterparts of the learning objective set by the teacher. In this work, we explore the possibility of imitating human teaching behaviors by dynamically and automatically outputting appropriate loss functions to train machine learning models. Different from typical learning settings in which the loss function of a machine learning model is predefined and fixed, in our framework, the loss function of a machine learning model (we call it student) is defined by another machine learning model (we call it teacher). The ultimate goal of teacher model is cultivating the student to have better performance measured on development dataset. Towards that end, similar to human teaching, the teacher, a parametric model, dynamically outputs different loss functions that will be used and optimized by its student model at different training stages. We develop an efficient learning method for the teacher model that makes gradient based optimization possible, exempt of the ineffective solutions such as policy optimization. We name our method as ``learning to teach with dynamic loss functions'' (L2T-DLF for short). Extensive experiments on real world tasks including image classification and neural machine translation demonstrate that our method significantly improves the quality of various student models.

PDF Details

YNIMG Journal 2014 Journal Article

A high performance 3D cluster-based test of unsmoothed fMRI data

Huanjie Li
Lisa D. Nickerson
Jinhu Xiong
Qihong Zou
Yang Fan
Yajun Ma
Tingqi Shi
Jianqiao Ge

Cluster-size tests (CST) based on random field theory have been widely adopted in fMRI data analysis to detect brain activation. However, most existing approaches can be used appropriately only when the image is highly smoothed in the spatial domain. Unfortunately, spatial smoothing degrades spatial specificity. Recently, a threshold-free cluster enhancement technique was proposed which does not require spatial smoothing, but this method can be used only for group level analysis. Advances in imaging technology now yield high quality high spatial resolution imaging data in single subjects and an inference approach that retains the benefits of greater spatial resolution is called for. In this work, we present a new CST with a correction for voxelation to address this problem. The theoretical formulation of the new approach based on Gaussian random fields is developed to estimate statistical significance using 3D statistical parametric maps without assuming spatial smoothness. Simulated phantom and resting-state fMRI experimental data are then used to compare the voxelation-corrected procedure to the widely used standard random field theory. Unlike standard random field theory approaches, which require heavy spatial smoothing, the new approach has a higher sensitivity for localizing activation regions without the requirement of spatial smoothness.

Details DOI