Search Results for author: Zhongyang Li

Found 14 papers, 4 papers with code

ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks

1 code implementation16 Dec 2022 Kai Xiong, Xiao Ding, Zhongyang Li, Li Du, Bing Qin, Yi Zheng, Baoxing Huai

Causal chain reasoning (CCR) is an essential ability for many decision-making AI systems, which requires the model to build reliable causal chains by connecting causal pairs.

Decision Making

Exact Recovery of Community Detection in dependent Gaussian Mixture Models

no code implementations23 Sep 2022 Zhongyang Li, Sichen Yang

We study the community detection problem on a Gaussian mixture model, in which (1) vertices are divided into $k\geq 2$ distinct communities that are not necessarily equally-sized; (2) the Gaussian perturbations for different entries in the observation matrix are not necessarily independent or identically distributed.

Community Detection

Guided Generation of Cause and Effect

no code implementations21 Jul 2021 Zhongyang Li, Xiao Ding, Ting Liu, J. Edward Hu, Benjamin Van Durme

We present a conditional text generation framework that posits sentential expressions of possible causes and effects.

Conditional Text Generation Knowledge Graphs

CausalBERT: Injecting Causal Knowledge Into Pre-trained Models with Minimal Supervision

no code implementations21 Jul 2021 Zhongyang Li, Xiao Ding, Kuo Liao, Bing Qin, Ting Liu

Recent work has shown success in incorporating pre-trained models like BERT to improve NLP systems.

Causal Inference

On the coercivity condition in the learning of interacting particle systems

no code implementations20 Nov 2020 Zhongyang Li, Fei Lu

In the learning of systems of interacting particles or agents, coercivity condition ensures identifiability of the interaction functions, providing the foundation of learning by nonparametric regression.


Exact Recovery of Community Detection in k-Community Gaussian Mixture Model

no code implementations29 Aug 2020 Zhongyang Li

We study the community detection problem on a Gaussian mixture model, in which vertices are divided into $k\geq 2$ distinct communities.

Community Detection

Modeling Event Background for If-Then Commonsense Reasoning Using Context-aware Variational Autoencoder

no code implementations IJCNLP 2019 Li Du, Xiao Ding, Ting Liu, Zhongyang Li

Understanding event and event-centered commonsense reasoning are crucial for natural language processing (NLP).

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

ELG: An Event Logic Graph

no code implementations18 Jul 2019 Xiao Ding, Zhongyang Li, Ting Liu, Kuo Liao

The evolution and development of events have their own basic principles, which make events happen sequentially.

Decision Making

Learning to Rank for Plausible Plausibility

no code implementations ACL 2019 Zhongyang Li, Tongfei Chen, Benjamin Van Durme

Researchers illustrate improvements in contextual encoding strategies via resultant performance on a battery of shared Natural Language Understanding (NLU) tasks.

Learning-To-Rank Natural Language Understanding

Story Ending Prediction by Transferable BERT

1 code implementation17 May 2019 Zhongyang Li, Xiao Ding, Ting Liu

In this study, we investigate a transferable BERT (TransBERT) training framework, which can transfer not only general language knowledge from large-scale unlabeled data but also specific kinds of knowledge from various semantically related supervised tasks, for a target task.

Language Modelling Natural Language Inference +2

Generating Reasonable and Diversified Story Ending Using Sequence to Sequence Model with Adversarial Training

no code implementations COLING 2018 Zhongyang Li, Xiao Ding, Ting Liu

In this paper, we propose using adversarial training augmented Seq2Seq model to generate reasonable and diversified story endings given a story context.

Cloze Test Information Retrieval +1

Constructing Narrative Event Evolutionary Graph for Script Event Prediction

1 code implementation14 May 2018 Zhongyang Li, Xiao Ding, Ting Liu

Script event prediction requires a model to predict the subsequent event given an existing event context.


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