• Publications
  • Influence
Driving Semantic Parsing from the World's Response
TLDR
We develop two novel learning algorithms capable of predicting complex structures which only rely on a binary feedback signal based on the context of an external world. Expand
  • 231
  • 30
  • PDF
Modeling Learner Engagement in MOOCs using Probabilistic Soft Logic
TLDR
We use probabilistic soft logic (PSL) to model student engagement by capturing domain knowledge about student interactions and performance and demonstrate that modeling engagement is helpful in predicting student performance. Expand
  • 96
  • 11
  • PDF
Learning Latent Engagement Patterns of Students in Online Courses
TLDR
We study the different aspects of online student behavior in MOOCs, develop a large-scale, data-driven approach for modeling student engagement in online courses based on latent representations. Expand
  • 100
  • 10
  • PDF
Discriminative Learning over Constrained Latent Representations
TLDR
This paper proposes a general learning framework for a class of problems that require learning over latent intermediate representations. Expand
  • 80
  • 9
  • PDF
TATHYA: A Multi-Classifier System for Detecting Check-Worthy Statements in Political Debates
TLDR
We design a multi-classifier system TATHYA, that models latent groupings in data and improves state-of-art systems in detecting check-worthy statements by 19.5% in F1-score on a held-out test set. Expand
  • 41
  • 5
  • PDF
Identifying Stance by Analyzing Political Discourse on Twitter
TLDR
We present a weakly supervised method for understanding the stances held by politicians, on a wide array of issues, by analyzing how issues are framed in their tweets and their temporal activity patterns. Expand
  • 22
  • 5
  • PDF
Learning from natural instructions
TLDR
In this paper we suggest to view the process of learning a decision function as a natural language lesson interpretation problem, as opposed to learning from labeled examples. Expand
  • 83
  • 4
  • PDF
Predicting Instructor's Intervention in MOOC forums
TLDR
This paper introduces the problem of predicting instructor interventions in MOOC forums by abstracting contents of individual posts of threads using latent categories, learned jointly with the binary intervention prediction problem. Expand
  • 66
  • 3
  • PDF
Structured Output Learning with Indirect Supervision
TLDR
In this paper, we formalize the observation that many structured output prediction problems have a companion binary decision problem of predicting whether an input can produce a good structure. Expand
  • 60
  • 3
  • PDF
Uncovering hidden engagement patterns for predicting learner performance in MOOCs
TLDR
Maintaining and cultivating student engagement is a prerequisite for MOOCs to have broad educational impact. Expand
  • 38
  • 3
  • PDF
...
1
2
3
4
5
...