Search Results for author: Junwen Duan

Found 8 papers, 2 papers with code

Event Representation Learning Enhanced with External Commonsense Knowledge

1 code implementation IJCNLP 2019 Xiao Ding, Kuo Liao, Ting Liu, Zhongyang Li, Junwen Duan

Prior work has proposed effective methods to learn event representations that can capture syntactic and semantic information over text corpus, demonstrating their effectiveness for downstream tasks such as script event prediction.

Representation Learning Stock Market Prediction

Learning Target-Specific Representations of Financial News Documents For Cumulative Abnormal Return Prediction

1 code implementation COLING 2018 Junwen Duan, Yue Zhang, Xiao Ding, Ching-Yun Chang, Ting Liu

The model uses a target-sensitive representation of the news abstract to weigh sentences in the news content, so as to select and combine the most informative sentences for market modeling.

Information Retrieval Sentence +1

Learning Sentence Representations over Tree Structures for Target-Dependent Classification

no code implementations NAACL 2018 Junwen Duan, Xiao Ding, Ting Liu

To address above issues, we propose a reinforcement learning based approach, which automatically induces target-specific sentence representations over tree structures.

Classification General Classification +4

Knowledge-Driven Event Embedding for Stock Prediction

no code implementations COLING 2016 Xiao Ding, Yue Zhang, Ting Liu, Junwen Duan

Representing structured events as vectors in continuous space offers a new way for defining dense features for natural language processing (NLP) applications.

Information Retrieval Open Information Extraction +4

Faster Stochastic Variance Reduction Methods for Compositional MiniMax Optimization

no code implementations18 Aug 2023 Jin Liu, Xiaokang Pan, Junwen Duan, Hongdong Li, Youqi Li, Zhe Qu

All the proposed complexities indicate that our proposed methods can match lower bounds to existing minimax optimizations, without requiring a large batch size in each iteration.

Stochastic Optimization

MHLAT: Multi-hop Label-wise Attention Model for Automatic ICD Coding

no code implementations16 Sep 2023 Junwen Duan, Han Jiang, Ying Yu

International Classification of Diseases (ICD) coding is the task of assigning ICD diagnosis codes to clinical notes.

You Only Forward Once: Prediction and Rationalization in A Single Forward Pass

no code implementations4 Nov 2023 Han Jiang, Junwen Duan, Zhe Qu, Jianxin Wang

In our framework, A pre-trained language model like BERT is deployed to simultaneously perform prediction and rationalization with less impact from interlocking or spurious correlations.

Language Modelling

Cannot find the paper you are looking for? You can Submit a new open access paper.