Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

Identifying Editor Roles in Argumentative Writing from Student Revision Histories

Sep 03, 2019
Tazin Afrin, Diane Litman

We present a method for identifying editor roles from students' revision behaviors during argumentative writing. We first develop a method for applying a topic modeling algorithm to identify a set of editor roles from a vocabulary capturing three aspects of student revision behaviors: operation, purpose, and position. We validate the identified roles by showing that modeling the editor roles that students take when revising a paper not only accounts for the variance in revision purposes in our data, but also relates to writing improvement.

* In: Artificial Intelligence in Education. AIED 2019. Lecture Notes in Computer Science, vol 11626. Springer, Cham 

  Access Paper or Ask Questions

Representation Learning for Spatial Graphs

Dec 22, 2018
Zheng Wang, Ce Ju, Gao Cong, Cheng Long

Recently, the topic of graph representation learning has received plenty of attention. Existing approaches usually focus on structural properties only and thus they are not sufficient for those spatial graphs where the nodes are associated with some spatial information. In this paper, we present the first deep learning approach called s2vec for learning spatial graph representations, which is based on denoising autoencoders framework (DAF). We evaluate the learned representations on real datasets and the results verified the effectiveness of s2vec when used for spatial clustering.

* 4 pages, 1 figure, conference 

  Access Paper or Ask Questions

Face Recognition: From Traditional to Deep Learning Methods

Oct 31, 2018
Daniel Sáez Trigueros, Li Meng, Margaret Hartnett

Starting in the seventies, face recognition has become one of the most researched topics in computer vision and biometrics. Traditional methods based on hand-crafted features and traditional machine learning techniques have recently been superseded by deep neural networks trained with very large datasets. In this paper we provide a comprehensive and up-to-date literature review of popular face recognition methods including both traditional (geometry-based, holistic, feature-based and hybrid methods) and deep learning methods.

  Access Paper or Ask Questions

Multi-task Learning of Pairwise Sequence Classification Tasks Over Disparate Label Spaces

Apr 09, 2018
Isabelle Augenstein, Sebastian Ruder, Anders Søgaard

We combine multi-task learning and semi-supervised learning by inducing a joint embedding space between disparate label spaces and learning transfer functions between label embeddings, enabling us to jointly leverage unlabelled data and auxiliary, annotated datasets. We evaluate our approach on a variety of sequence classification tasks with disparate label spaces. We outperform strong single and multi-task baselines and achieve a new state-of-the-art for topic-based sentiment analysis.

* To appear at NAACL 2018 (long) 

  Access Paper or Ask Questions

Sentiment analysis of twitter data

Dec 16, 2017
Hamid Bagheri, Md Johirul Islam

Social networks are the main resources to gather information about people's opinion and sentiments towards different topics as they spend hours daily on social media and share their opinion. In this technical paper, we show the application of sentimental analysis and how to connect to Twitter and run sentimental analysis queries. We run experiments on different queries from politics to humanity and show the interesting results. We realized that the neutral sentiments for tweets are significantly high which clearly shows the limitations of the current works.

* 5 pages 

  Access Paper or Ask Questions

Probabilistic Latent Semantic Analysis (PLSA) untuk Klasifikasi Dokumen Teks Berbahasa Indonesia

Dec 02, 2015
Derwin Suhartono

One task that is included in managing documents is how to find substantial information inside. Topic modeling is a technique that has been developed to produce document representation in form of keywords. The keywords will be used in the indexing process and document retrieval as needed by users. In this research, we will discuss specifically about Probabilistic Latent Semantic Analysis (PLSA). It will cover PLSA mechanism which involves Expectation Maximization (EM) as the training algorithm, how to conduct testing, and obtain the accuracy result.

* 17 pages, 6 figures, 3 tables, Technical Report Program Studi Doktor Ilmu Komputer Universitas Indonesia 

  Access Paper or Ask Questions

A Tutorial on Independent Component Analysis

Apr 11, 2014
Jonathon Shlens

Independent component analysis (ICA) has become a standard data analysis technique applied to an array of problems in signal processing and machine learning. This tutorial provides an introduction to ICA based on linear algebra formulating an intuition for ICA from first principles. The goal of this tutorial is to provide a solid foundation on this advanced topic so that one might learn the motivation behind ICA, learn why and when to apply this technique and in the process gain an introduction to this exciting field of active research.

  Access Paper or Ask Questions

Coordinate Descent for MCP/SCAD Penalized Least Squares Converges Linearly

Sep 18, 2021
Yuling Jiao, Dingwei Li, Min Liu, Xiliang Lu

Recovering sparse signals from observed data is an important topic in signal/imaging processing, statistics and machine learning. Nonconvex penalized least squares have been attracted a lot of attentions since they enjoy nice statistical properties. Computationally, coordinate descent (CD) is a workhorse for minimizing the nonconvex penalized least squares criterion due to its simplicity and scalability. In this work, we prove the linear convergence rate to CD for solving MCP/SCAD penalized least squares problems.

  Access Paper or Ask Questions

Explainable Autonomous Robots: A Survey and Perspective

May 06, 2021
Tatsuya Sakai, Takayuki Nagai

Advanced communication protocols are critical to enable the coexistence of autonomous robots with humans. Thus, the development of explanatory capabilities is an urgent first step toward autonomous robots. This survey provides an overview of the various types of "explainability" discussed in machine learning research. Then, we discuss the definition of "explainability" in the context of autonomous robots (i.e., explainable autonomous robots) by exploring the question "what is an explanation?" We further conduct a research survey based on this definition and present some relevant topics for future research.

  Access Paper or Ask Questions

Multi-modal Ensemble Models for Predicting Video Memorability

Feb 01, 2021
Tony Zhao, Irving Fang, Jeffrey Kim, Gerald Friedland

Modeling media memorability has been a consistent challenge in the field of machine learning. The Predicting Media Memorability task in MediaEval2020 is the latest benchmark among similar challenges addressing this topic. Building upon techniques developed in previous iterations of the challenge, we developed ensemble methods with the use of extracted video, image, text, and audio features. Critically, in this work we introduce and demonstrate the efficacy and high generalizability of extracted audio embeddings as a feature for the task of predicting media memorability.

  Access Paper or Ask Questions