Share This Author
BlocHIE: A BLOCkchain-Based Platform for Healthcare Information Exchange
- Shan Jiang, Jiannong Cao, Hanqing Wu, Yanni Yang, Mingyu Derek Ma, Jianfei He
- Computer Science, MedicineInternational Conference on Smart Computing
- 1 June 2018
A Blockchain-based platform for healthcare information exchange that combines off-chain storage and on-chain verification to satisfy the requirements of both privacy and authenticability, and proposes two fairness-based packing algorithms to improve the system throughput and the fairness among users jointly.
Dual Memory Network Model for Biased Product Review Classification
- Yunfei Long, Mingyu Derek Ma, Q. Lu, Rong Xiang, Chu-Ren Huang
- Computer ScienceWASSA@EMNLP
- 1 September 2018
A dual user and product memory network (DUPMN) model is proposed to learn user profiles and product reviews using separate memory networks and the two representations are used jointly for sentiment prediction.
Implicit Discourse Relation Identification for Open-domain Dialogues
A method to automatically extract the implicit discourse relation argument pairs and labels from a dataset of dialogic turns is proposed, resulting in a novel corpus of discourse relation pairs, the first of its kind to attempt to identify the discourse relations connecting the dialogicturns in open-domain discourse.
EventPlus: A Temporal Event Understanding Pipeline
- Mingyu Derek Ma, Jiao Sun, Nanyun Peng
- Computer ScienceNorth American Chapter of the Association for…
- 13 January 2021
EventPlus as the first comprehensive temporal event understanding pipeline provides a convenient tool for users to quickly obtain annotations about events and their temporal information for any user-provided document.
HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning
A taxonomy expansion algorithm that seeks to preserve the structure of a taxonomy in a more expressive hyperbolic embedding space and learn to represent concepts and their relations with a Hyperbolic Graph Neural Network (HGNN).
Summarization as Indirect Supervision for Relation Extraction
S U RE is presented, which converts RE into a summarization formulation and develops sentence and relation conversion techniques that essentially bridge the formulation of summarization and RE tasks, showing that summarization is a promising source of indirect supervision to improve RE models.
Dual memory network model for sentiment analysis of review text
DICE: Data-Efficient Clinical Event Extraction with Generative Models
DICE is introduced, a robust and data-efﬁcient generative model for clinical event extraction that frames event extraction as a conditional generation problem and uti- lizes descriptions provided by domain experts to boost the performance under low-resource settings.
Bending the Future: Autoregressive Modeling of Temporal Knowledge Graphs in Curvature-Variable Hyperbolic Spaces
This work proposes HyperVC, which utilizes hyperbolic space that better encodes the hierarchies within knowledge graphs at diﬀerent timestamps than Euclidean space, and reports two evaluation metrics for extrapolated link prediction, including Mean Reciprocal Rank (MRR) and H@1/3/10.