Related papers: Semi-supervised and Unsupervised Methods for Categ…
In this paper, we propose a variational approach to unsupervised sentiment analysis. Instead of using ground truth provided by domain experts, we use target-opinion word pairs as a supervision signal. For example, in a document snippet "the…
Unlabelled data appear in many domains and are particularly relevant to streaming applications, where even though data is abundant, labelled data is rare. To address the learning problems associated with such data, one can ignore the…
Underground forums play a crucial role in the criminal ecosystem, facilitating the exchange of knowledge and the trade of illegal tools and services. By analyzing the skills, motivations, focus, and operations of cyber-criminals active in…
Leveraging the power of increasing amounts of data to analyze customer base for attracting and retaining the most valuable customers is a major problem facing companies in this information age. Data mining technologies extract hidden…
Part of speech tagging is a fundamental NLP task often regarded as solved for high-resource languages such as English. Current state-of-the-art models have achieved high accuracy, especially on the news domain. However, when these models…
A growing specter in the rise of machine learning is whether the decisions made by machine learning models are fair. While research is already underway to formalize a machine-learning concept of fairness and to design frameworks for…
Offensive language is pervasive in social media. Individuals frequently take advantage of the perceived anonymity of computer-mediated communication, using this to engage in behavior that many of them would not consider in real life. The…
Speech summarisation techniques take human speech as input and then output an abridged version as text or speech. Speech summarisation has applications in many domains from information technology to health care, for example improving speech…
In several domains obtaining class annotations is expensive while at the same time unlabelled data are abundant. While most semi-supervised approaches enforce restrictive assumptions on the data distribution, recent work has managed to…
We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models. Constructing a large-scale labeled image captioning dataset is an expensive task in terms of labor, time, and cost. In…
Existing weakly-supervised semantic segmentation methods using image-level annotations typically rely on initial responses to locate object regions. However, such response maps generated by the classification network usually focus on…
With large volumes of health care data comes the research area of computational phenotyping, making use of techniques such as machine learning to describe illnesses and other clinical concepts from the data itself. The "traditional"…
Is all of machine learning supervised to some degree? The field of machine learning has traditionally been categorized pedagogically into $supervised~vs~unsupervised~learning$; where supervised learning has typically referred to learning…
Answering questions is a primary goal of many conversational systems or search products. While most current systems have focused on answering questions against structured databases or curated knowledge graphs, on-line community forums or…
We demonstrate the effectiveness of multilingual learning for unsupervised part-of-speech tagging. The central assumption of our work is that by combining cues from multiple languages, the structure of each becomes more apparent. We…
In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach…
Semi-supervised learning is an important and active topic of research in pattern recognition. For classification using linear discriminant analysis specifically, several semi-supervised variants have been proposed. Using any one of these…
Due to abundance of data from multiple modalities, cross-modal retrieval tasks with image-text, audio-image, etc. are gaining increasing importance. Of the different approaches proposed, supervised methods usually give significant…
Segmentation remains an important preprocessing step both in languages where "words" or other important syntactic/semantic units (like morphemes) are not clearly delineated by white space, as well as when dealing with continuous speech…
The irreplaceable key to the triumph of Question & Answer (Q&A) platforms is their users providing high-quality answers to the challenging questions posted across various topics of interest. From more than a decade, the expert finding…