Share This Author
Hierarchical Attention Networks for Document Classification
- Zichao Yang, Diyi Yang, Chris Dyer, Xiaodong He, Alex Smola, E. Hovy
- Computer ScienceNAACL
- 13 June 2016
Experiments conducted on six large scale text classification tasks demonstrate that the proposed architecture outperform previous methods by a substantial margin.
Humor Recognition and Humor Anchor Extraction
This work identifies several semantic structures behind humor and design sets of features for each structure, and employs a computational approach to recognize humor, and develops a simple and effective method to extract anchors that enable humor in a sentence.
ToTTo: A Controlled Table-To-Text Generation Dataset
We present ToTTo, an open-domain English table-to-text dataset with over 120,000 training examples that proposes a controlled generation task: given a Wikipedia table and a set of highlighted table…
MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification
By mixing labeled, unlabeled and augmented data, MixText significantly outperformed current pre-trained and fined-tuned models and other state-of-the-art semi-supervised learning methods on several text classification benchmarks.
“ Turn on , Tune in , Drop out ” : Anticipating student dropouts in Massive Open Online Courses
In this paper, we explore student dropout behavior in Massive Open Online Courses(MOOC). We use as a case study a recent Coursera class from which we develop a survival model that allows us to…
Sentiment Analysis in MOOC Discussion Forums: What does it tell us?
This paper explores mining collective sentiment from forum posts in a Massive Open Online Course (MOOC) in order to monitor students’ trending opinions towards the course and major course tools, such as lecture and peer-assessment.
Automatically Neutralizing Subjective Bias in Text
- Reid Pryzant, Richard Diehl Martinez, Nathan Dass, S. Kurohashi, Dan Jurafsky, Diyi Yang
- Computer ScienceAAAI
- 21 November 2019
Large-scale human evaluation across four domains (encyclopedias, news headlines, books, and political speeches) suggests that these algorithms are a first step towards the automatic identification and reduction of bias.
That’s So Annoying!!!: A Lexical and Frame-Semantic Embedding Based Data Augmentation Approach to Automatic Categorization of Annoying Behaviors using #petpeeve Tweets
In quantitative analysis, it is shown that lexical and syntactic features are useful for automatic categorization of annoying behaviors, and frame-semantic features further boost the performance; that leveraging large lexical embeddings to create additional training instances significantly improves the lexical model; and incorporating frame- semantic embedding achieves the best overall performance.
Exploring the Effect of Confusion in Discussion Forums of Massive Open Online Courses
The results demonstrate that the more confusion students express or are exposed to, the lower the probability of their retention in MOOCs and implications for design of interventions towards improving the retention of students in MOocs are demonstrated.
Linguistic Reflections of Student Engagement in Massive Open Online Courses
Using computational linguistic models to measure learner motivation and cognitive engagement from the text of forum posts is investigated, and techniques using survival models that evaluate the predictive validity of these variables in connection with attrition over time are validated.