C
Chang Li
Publications - 7
Citations - 167
Chang Li is an academic researcher. The author has contributed to research in topics: Perspective (graphical) & News media. The author has an hindex of 4, co-authored 7 publications receiving 93 citations.
Papers
More filters
Proceedings ArticleDOI
Encoding Social Information with Graph Convolutional Networks forPolitical Perspective Detection in News Media
Chang Li,Dan Goldwasser +1 more
TL;DR: Graph Convolutional Networks, a recently proposed neural architecture for representing relational information, is used to capture the documents’ social context, showing that social information can be used effectively as a source of distant supervision, and when direct supervision is available, even littlesocial information can significantly improve performance.
Proceedings Article
Structured Representation Learning for Online Debate Stance Prediction
TL;DR: This work suggests to view this task of understanding the stances expressed in debates as a representation learning problem, and embed the text and authors jointly based on their interactions, and evaluates the model over the Internet Argumentation Corpus, and compares different approaches for structural information embedding.
Proceedings ArticleDOI
MEAN: Multi-head Entity Aware Attention Networkfor Political Perspective Detection in News Media
Chang Li,Dan Goldwasser +1 more
TL;DR: A novel framework is proposed that considers entities mentioned in news articles and external knowledge about them, capturing the bias with respect to those entities, and is capable of identifying the difference in news narratives with different perspectives.
Proceedings ArticleDOI
Introducing DRAIL – a Step Towards Declarative Deep Relational Learning
TL;DR: DRAIL, a new declarative framework for specifying Deep Relational Models, is introduced and the DRAIL formulation of two NLP tasks, Twitter Part-of-Speech tagging and Entity-Relation extraction is shown.
Proceedings ArticleDOI
PurdueNLP at SemEval-2017 Task 1: Predicting Semantic Textual Similarity with Paraphrase and Event Embeddings
I-Ta Lee,Mahak Goindani,Chang Li,Di Jin,Kristen Johnson,Xiao Zhang,Maria Leonor Pacheco,Dan Goldwasser +7 more
TL;DR: The proposed system consists of two subsystems and one regression model for predicting STS scores, designed to learn Paraphrase and Event Embeddings that can take the consideration of paraphrasing characteristics and sentence structures into the system.