Data Mining Practical Machine Learning Tools and Techniques

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

Social Psychology of Organizations

Matrix Factorization Techniques for Recommender Systems

Discourse in the Novel

We propose a hierarchical attention network for document classification. Our model has two distinctive characteristics: (i) it has a hierarchical structure that mirrors the hierarchical structure of documents; (ii) it has two levels of attention mechanisms applied at the wordand sentence-level, enabling it to attend differentially to more and less important content when constructing the document representation. Experiments conducted on six large scale text classification tasks demonstrate that the proposed architecture outperform previous methods by a substantial margin. Visualization of the attention layers illustrates that the model selects qualitatively informative words and sentences.

/pdf/hierarchical-attention-networks-for-document-classification-2f4ul5pyx3.pdf

Hierarchical Attention Networks for Document Classification

Sentiment analysis is one of the great accomplishments of the last decade in the field of Language Technologies. In this paper, we explore 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. We observe a correlation between sentiment ratio measured based on daily forum posts and number of students who drop out each day. On a user-level, we evaluate the impact of sentiment on attrition over time. A qualitative analysis clarifies the subtle differences in how these language behaviors are used in practice across three MOOCs. Implications for research and practice are discussed.

https://educationaldatamining.org/EDM2014/uploads/procs2014/long%20papers/130_EDM-2014-Full.pdf

Sentiment Analysis in MOOC Discussion Forums: What does it tell us?

We propose a novel data augmentation approach to enhance computational behavioral analysis using social media text. In particular, we collect a Twitter corpus of the descriptions of annoying behaviors using the #petpeeve hashtags. In the qualitative analysis, we study the language use in these tweets, with a special focus on the fine-grained categories and the geographic variation of the language. In quantitative analysis, we show 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.

/pdf/that-s-so-annoying-a-lexical-and-frame-semantic-embedding-2jadgte867.pdf

That's So Annoying!!!: A Lexical and Frame-Semantic Embedding Based Data Augmentation Approach to Automatic Categorization of Annoying Behaviors using #petpeeve Tweets

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 cells, produce a one-sentence description. To obtain generated targets that are natural but also faithful to the source table, we introduce a dataset construction process where annotators directly revise existing candidate sentences from Wikipedia. We present systematic analyses of our dataset and annotation process as well as results achieved by several state-of-the-art baselines. While usually fluent, existing methods often hallucinate phrases that are not supported by the table, suggesting that this dataset can serve as a useful research benchmark for high-precision conditional text generation.

ToTTo: A Controlled Table-To-Text Generation Dataset

Humor is an essential component in personal communication. How to create computational models to discover the structures behind humor, recognize humor and even extract humor anchors remains a challenge. In this work, we first identify several semantic structures behind humor and design sets of features for each structure, and next employ a computational approach to recognize humor. Furthermore, we develop a simple and effective method to extract anchors that enable humor in a sentence. Experiments conducted on two datasets demonstrate that our humor recognizer is effective in automatically distinguishing between humorous and non-humorous texts and our extracted humor anchors correlate quite well with human annotations.

/pdf/humor-recognition-and-humor-anchor-extraction-2o41gkb6k3.pdf

Diyi Yang

Papers

Hierarchical Attention Networks for Document Classification

Sentiment Analysis in MOOC Discussion Forums: What does it tell us?

That's So Annoying!!!: A Lexical and Frame-Semantic Embedding Based Data Augmentation Approach to Automatic Categorization of Annoying Behaviors using #petpeeve Tweets

ToTTo: A Controlled Table-To-Text Generation Dataset

Humor Recognition and Humor Anchor Extraction