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

Time Series Imputation

Mar 22, 2019
Samuel Arcadinho, Paulo Mateus

Multivariate time series is a very active topic in the research community and many machine learning tasks are being used in order to extract information from this type of data. However, in real-world problems data has missing values, which may difficult the application of machine learning techniques to extract information. In this paper we focus on the task of imputation of time series. Many imputation methods for time series are based on regression methods. Unfortunately, these methods perform poorly when the variables are categorical. To address this case, we propose a new imputation method based on Expectation Maximization over dynamic Bayesian networks. The approach is assessed with synthetic and real data, and it outperforms several state-of-the art methods.

* Master paper, draft to be submitted 

  Access Paper or Ask Questions

A simple and efficient architecture for trainable activation functions

Feb 12, 2019
Andrea Apicella, Francesco Isgrò, Roberto Prevete

Learning automatically the best activation function for the task is an active topic in neural network research. At the moment, despite promising results, it is still difficult to determine a method for learning an activation function that is at the same time theoretically simple and easy to implement. Moreover, most of the methods proposed so far introduce new parameters or adopt different learning techniques. In this work we propose a simple method to obtain trained activation function which adds to the neural network local subnetworks with a small amount of neurons. Experiments show that this approach could lead to better result with respect to using a pre-defined activation function, without introducing a large amount of extra parameters that need to be learned.

  Access Paper or Ask Questions

A Tutorial on Distance Metric Learning: Mathematical Foundations, Algorithms and Software

Dec 14, 2018
Juan Luis Suárez, Salvador García, Francisco Herrera

This paper describes the discipline of distance metric learning, a branch of machine learning that aims to learn distances from the data. Distance metric learning can be useful to improve similarity learning algorithms, and also has applications in dimensionality reduction. We describe the distance metric learning problem and analyze its main mathematical foundations. We discuss some of the most popular distance metric learning techniques used in classification, showing their goals and the required information to understand and use them. Furthermore, we present a Python package that collects a set of 17 distance metric learning techniques explained in this paper, with some experiments to evaluate the performance of the different algorithms. Finally, we discuss several possibilities of future work in this topic.

  Access Paper or Ask Questions

An English-Hindi Code-Mixed Corpus: Stance Annotation and Baseline System

May 30, 2018
Sahil Swami, Ankush Khandelwal, Vinay Singh, Syed Sarfaraz Akhtar, Manish Shrivastava

Social media has become one of the main channels for peo- ple to communicate and share their views with the society. We can often detect from these views whether the person is in favor, against or neu- tral towards a given topic. These opinions from social media are very useful for various companies. We present a new dataset that consists of 3545 English-Hindi code-mixed tweets with opinion towards Demoneti- sation that was implemented in India in 2016 which was followed by a large countrywide debate. We present a baseline supervised classification system for stance detection developed using the same dataset that uses various machine learning techniques to achieve an accuracy of 58.7% on 10-fold cross validation.

* 9 pages, CICling 2018 

  Access Paper or Ask Questions

Fact Checking in Community Forums

Mar 08, 2018
Tsvetomila Mihaylova, Preslav Nakov, Lluis Marquez, Alberto Barron-Cedeno, Mitra Mohtarami, Georgi Karadzhov, James Glass

Community Question Answering (cQA) forums are very popular nowadays, as they represent effective means for communities around particular topics to share information. Unfortunately, this information is not always factual. Thus, here we explore a new dimension in the context of cQA, which has been ignored so far: checking the veracity of answers to particular questions in cQA forums. As this is a new problem, we create a specialized dataset for it. We further propose a novel multi-faceted model, which captures information from the answer content (what is said and how), from the author profile (who says it), from the rest of the community forum (where it is said), and from external authoritative sources of information (external support). Evaluation results show a MAP value of 86.54, which is 21 points absolute above the baseline.

* AAAI-2018; Fact-Checking; Veracity; Community-Question Answering; Neural Networks; Distributed Representations 

  Access Paper or Ask Questions

An Ensemble Model with Ranking for Social Dialogue

Dec 20, 2017
Ioannis Papaioannou, Amanda Cercas Curry, Jose L. Part, Igor Shalyminov, Xinnuo Xu, Yanchao Yu, Ondřej Dušek, Verena Rieser, Oliver Lemon

Open-domain social dialogue is one of the long-standing goals of Artificial Intelligence. This year, the Amazon Alexa Prize challenge was announced for the first time, where real customers get to rate systems developed by leading universities worldwide. The aim of the challenge is to converse "coherently and engagingly with humans on popular topics for 20 minutes". We describe our Alexa Prize system (called 'Alana') consisting of an ensemble of bots, combining rule-based and machine learning systems, and using a contextual ranking mechanism to choose a system response. The ranker was trained on real user feedback received during the competition, where we address the problem of how to train on the noisy and sparse feedback obtained during the competition.

* NIPS 2017 Workshop on Conversational AI 

  Access Paper or Ask Questions

Inverse Reinforcement Learning for Marketing

Dec 13, 2017
Igor Halperin

Learning customer preferences from an observed behaviour is an important topic in the marketing literature. Structural models typically model forward-looking customers or firms as utility-maximizing agents whose utility is estimated using methods of Stochastic Optimal Control. We suggest an alternative approach to study dynamic consumer demand, based on Inverse Reinforcement Learning (IRL). We develop a version of the Maximum Entropy IRL that leads to a highly tractable model formulation that amounts to low-dimensional convex optimization in the search for optimal model parameters. Using simulations of consumer demand, we show that observational noise for identical customers can be easily confused with an apparent consumer heterogeneity.

* 18 pages, 5 figures 

  Access Paper or Ask Questions

SelQA: A New Benchmark for Selection-based Question Answering

Oct 28, 2016
Tomasz Jurczyk, Michael Zhai, Jinho D. Choi

This paper presents a new selection-based question answering dataset, SelQA. The dataset consists of questions generated through crowdsourcing and sentence length answers that are drawn from the ten most prevalent topics in the English Wikipedia. We introduce a corpus annotation scheme that enhances the generation of large, diverse, and challenging datasets by explicitly aiming to reduce word co-occurrences between the question and answers. Our annotation scheme is composed of a series of crowdsourcing tasks with a view to more effectively utilize crowdsourcing in the creation of question answering datasets in various domains. Several systems are compared on the tasks of answer sentence selection and answer triggering, providing strong baseline results for future work to improve upon.

  Access Paper or Ask Questions

Distilling Word Embeddings: An Encoding Approach

Jul 24, 2016
Lili Mou, Ran Jia, Yan Xu, Ge Li, Lu Zhang, Zhi Jin

Distilling knowledge from a well-trained cumbersome network to a small one has recently become a new research topic, as lightweight neural networks with high performance are particularly in need in various resource-restricted systems. This paper addresses the problem of distilling word embeddings for NLP tasks. We propose an encoding approach to distill task-specific knowledge from a set of high-dimensional embeddings, which can reduce model complexity by a large margin as well as retain high accuracy, showing a good compromise between efficiency and performance. Experiments in two tasks reveal the phenomenon that distilling knowledge from cumbersome embeddings is better than directly training neural networks with small embeddings.

* Accepted by CIKM-16 as a short paper, and by the Representation Learning for Natural Language Processing (RL4NLP) Workshop @ACL-16 for presentation 

  Access Paper or Ask Questions

Query-Focused Opinion Summarization for User-Generated Content

Jun 17, 2016
Lu Wang, Hema Raghavan, Claire Cardie, Vittorio Castelli

We present a submodular function-based framework for query-focused opinion summarization. Within our framework, relevance ordering produced by a statistical ranker, and information coverage with respect to topic distribution and diverse viewpoints are both encoded as submodular functions. Dispersion functions are utilized to minimize the redundancy. We are the first to evaluate different metrics of text similarity for submodularity-based summarization methods. By experimenting on community QA and blog summarization, we show that our system outperforms state-of-the-art approaches in both automatic evaluation and human evaluation. A human evaluation task is conducted on Amazon Mechanical Turk with scale, and shows that our systems are able to generate summaries of high overall quality and information diversity.

* COLING 2014 

  Access Paper or Ask Questions