Di Jin

verfied profile

∙ 0 followers
MIT

I am a PhD student from MIT, working on NLP.

BERT2DNN: BERT Distillation with Massive Unlabeled Data for Online E-Commerce Search

Relevance has significant impact on user experience and business profit ...
10/20/2020 ∙ by Yunjiang Jiang, et al. ∙ 0 ∙ share

read it
What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams

Open domain question answering (OpenQA) tasks have been recently attract...
09/28/2020 ∙ by Di Jin, et al. ∙ 5 ∙ share

read it
From Static to Dynamic Node Embeddings

We introduce a general framework for leveraging graph stream data for te...
09/21/2020 ∙ by Di Jin, et al. ∙ 8 ∙ share

read it
Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) aims to predict the sentiment tow...
09/16/2020 ∙ by Xiaoyu Xing, et al. ∙ 0 ∙ share

read it
Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards

Generating accurate descriptions for online fashion items is important n...
08/06/2020 ∙ by Xuewen Yang, et al. ∙ 2 ∙ share

read it
Calling Out Bluff: Attacking the Robustness of Automatic Scoring Systems with Simple Adversarial Testing

A significant progress has been made in deep-learning based Automatic Es...
07/14/2020 ∙ by Yaman Kumar, et al. ∙ 0 ∙ share

read it
GCN for HIN via Implicit Utilization of Attention and Meta-paths

Heterogeneous information network (HIN) embedding, aiming to map the str...
07/06/2020 ∙ by Di Jin, et al. ∙ 0 ∙ share

read it
Learning Continuous-Time Dynamics by Stochastic Differential Networks

Learning continuous-time stochastic dynamics from sparse or irregular ob...
06/11/2020 ∙ by Yingru Liu, et al. ∙ 7 ∙ share

read it
From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap

Dialogue state tracking (DST) is at the heart of task-oriented dialogue ...
04/13/2020 ∙ by Shuyang Gao, et al. ∙ 16 ∙ share

read it
Hooks in the Headline: Learning to Generate Headlines with Controlled Styles

Current summarization systems only produce plain, factual headlines, but...
04/04/2020 ∙ by Di Jin, et al. ∙ 9 ∙ share

read it
Unsupervised Domain Adaptation for Neural Machine Translation with Iterative Back Translation

State-of-the-art neural machine translation (NMT) systems are data-hungr...
01/22/2020 ∙ by Di Jin, et al. ∙ 0 ∙ share

read it
MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension

Machine Reading Comprehension (MRC) for question answering (QA), which a...
10/01/2019 ∙ by Di Jin, et al. ∙ 0 ∙ share

read it
From Community to Role-based Graph Embeddings

Roles are sets of structurally similar nodes that are more similar to no...
08/22/2019 ∙ by Ryan A. Rossi, et al. ∙ 0 ∙ share

read it
Is BERT Really Robust? Natural Language Attack on Text Classification and Entailment

Machine learning algorithms are often vulnerable to adversarial examples...
07/27/2019 ∙ by Di Jin, et al. ∙ 0 ∙ share

read it
node2bits: Compact Time- and Attribute-aware Node Representations for User Stitching

Identity stitching, the task of identifying and matching various online ...
04/18/2019 ∙ by Di Jin, et al. ∙ 0 ∙ share

read it
Publicly Available Clinical BERT Embeddings

Contextual word embedding models such as ELMo (Peters et al., 2018) and ...
04/06/2019 ∙ by Emily Alsentzer, et al. ∙ 0 ∙ share

read it
Unsupervised Text Style Transfer via Iterative Matching and Translation

Text style transfer seeks to learn how to automatically rewrite sentence...
01/31/2019 ∙ by Zhijing Jin, et al. ∙ 28 ∙ share

read it
Advancing PICO Element Detection in Medical Text via Deep Neural Networks

In evidence-based medicine (EBM), structured medical questions are alway...
10/30/2018 ∙ by Di Jin, et al. ∙ 0 ∙ share

read it
Hierarchical Neural Networks for Sequential Sentence Classification in Medical Scientific Abstracts

Prevalent models based on artificial neural network (ANN) for sentence c...
08/19/2018 ∙ by Di Jin, et al. ∙ 0 ∙ share

read it
High-throughput, high-resolution Generated Adversarial Network Microscopy

We for the first time combine generated adversarial network (GAN) with w...
01/07/2018 ∙ by Hao Zhang, et al. ∙ 0 ∙ share

read it

Di Jin

Featured Co-authors

Xin Wang

Philip S. Yu

Jiawei Han

Xuanjing Huang

Qi Zhang

Hao Zhang

Jue Wang

Rajiv Ratn Shah

Dilek Hakkani-Tur

Ryan A. Rossi

Peter Szolovits

BERT2DNN: BERT Distillation with Massive Unlabeled Data for Online E-Commerce Search

What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams

From Static to Dynamic Node Embeddings

Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis

Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards

Calling Out Bluff: Attacking the Robustness of Automatic Scoring Systems with Simple Adversarial Testing

GCN for HIN via Implicit Utilization of Attention and Meta-paths

Learning Continuous-Time Dynamics by Stochastic Differential Networks

From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap

Hooks in the Headline: Learning to Generate Headlines with Controlled Styles

Unsupervised Domain Adaptation for Neural Machine Translation with Iterative Back Translation

MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension

From Community to Role-based Graph Embeddings

Is BERT Really Robust? Natural Language Attack on Text Classification and Entailment

node2bits: Compact Time- and Attribute-aware Node Representations for User Stitching

Publicly Available Clinical BERT Embeddings

Unsupervised Text Style Transfer via Iterative Matching and Translation

Advancing PICO Element Detection in Medical Text via Deep Neural Networks

Hierarchical Neural Networks for Sequential Sentence Classification in Medical Scientific Abstracts

High-throughput, high-resolution Generated Adversarial Network Microscopy