Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining - Concepts and Techniques.

Sentiment analysis and opinion mining is the field of study that analyzes people's opinions, sentiments, evaluations, attitudes, and emotions from written language. It is one of the most active research areas in natural language processing and is also widely studied in data mining, Web mining, and text mining. In fact, this research has spread outside of computer science to the management sciences and social sciences due to its importance to business and society as a whole. The growing importance of sentiment analysis coincides with the growth of social media such as reviews, forum discussions, blogs, micro-blogs, Twitter, and social networks. For the first time in human history, we now have a huge volume of opinionated data recorded in digital form for analysis. Sentiment analysis systems are being applied in almost every business and social domain because opinions are central to almost all human activities and are key influencers of our behaviors. Our beliefs and perceptions of reality, and the choices we make, are largely conditioned on how others see and evaluate the world. For this reason, when we need to make a decision we often seek out the opinions of others. This is true not only for individuals but also for organizations. This book is a comprehensive introductory and survey text. It covers all important topics and the latest developments in the field with over 400 references. It is suitable for students, researchers and practitioners who are interested in social media analysis in general and sentiment analysis in particular. Lecturers can readily use it in class for courses on natural language processing, social media analysis, text mining, and data mining. Lecture slides are also available online.

/pdf/sentiment-analysis-and-opinion-mining-8314pykwrf.pdf

Sentiment Analysis and Opinion Mining

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

Public, professional and academic interest in automated fact-checking has drastically increased over the past decade, with many aiming to automate one of the first steps in a fact-check procedure: the selection of so-called checkworthy claims. However, there is little agreement on the definition and characteristics of checkworthiness among fact-checkers, which is consequently reflected in the datasets used for training and testing checkworthy claim detection models. After elaborate analysis of checkworthy claim selection procedures in fact-check organisations and analysis of state-of-the-art claim detection datasets, checkworthiness is defined as the concept of having a spatiotemporal and context-dependent worth and need to have the correctness of the objectivity it conveys verified. This is irrespective of the claim’s perceived veracity judgement by an individual based on prior knowledge and beliefs. Concerning the characteristics of current datasets, it is argued that the data is not only highly imbalanced and noisy, but also too limited in scope and language. Furthermore, we believe that the subjective concept of checkworthiness might not be a suitable filter for claim detection.

Checkworthiness in Automatic Claim Detection Models: Definitions and Analysis of Datasets.

While already having at their disposal an array of advanced and task-specific tools for the gathering, dispersal and exploitation of highly structured information, the Belgian Federal Police (BFP) are now shifting attention to novel technologies for exploiting vast amounts of unstructured information sources, from which further knowledge could be obtained for analysis purposes. The aim of the INFO-NS research project is to provide an objective study of the applicability of mining and decision support tools for the BFP. More specifically, it is studied whether information retrieval, extraction and classification tools might leverage intelligence and decision support while exploiting the information that is contained in vast amounts of free text material and linking it with any coexisting, structured data sets that are currently in use. This article provides an insight into the requirements of the BFP with regard to a like decision support system, and presents one aspect of evaluation criteria aimed at testing the functional conformity of such tools against a set of functional requirements.

Evaluation of Intelligent Exploitation Tools for Non-structured Police Information

We built a system for the automatic creation of a text- based topic hierarchy, meant to be used in a geographically defined community. This poses two main problems. First, the appearance of both standard language and a community-related dialect, demanding that dialect words should be as much as possible corrected to standard words, and second, the automatic hierarchic clustering of texts by their topic. The problem of correcting dialect words is dealt with by performing a nearest neighbor search over a dynamic set of known words, using a set of transition rules from dialect to standard words, which are learned from a parallel corpus. We solve the clustering problem by implementing a hierarchical co-clustering algorithm that automatically generates a topic hierarchy of the collection and simultaneously groups documents and words into clusters.

http://liir.cs.kuleuven.be/publication_files/tir07_wim_de_smet.pdf

Generating a Topic Hierarchy from Dialect Texts

This paper presents a novel unsupervised method for identifying the semantic structure in long semi-structured video streams. We identify chains, i.e., local clusters of repeated features from both the video stream and audio transcripts. Each chain serves as an indicator that the temporal interval it demarcates is part of the same semantic event. By layering all the chains over each other, dense regions emerge from the overlapping chains, from which we can identify the semantic structure of the video. We present two clustering strategies that accomplish this task, and compare them against a baseline Scene Transition Graph approach. We then develop a commentator that provides a semantic labeling of the resultant video segmentation.

/pdf/unsupervised-scene-detection-and-commentator-building-using-1fdybrwsn1.pdf

Unsupervised scene detection and commentator building using multi-modal chains

We introduce a novel approach to correcting context-dependent dt-mistakes, one of the most frequent spelling errors in the Dutch language. We show that by using a neural network to estimate the probability distribution of a verb’s suffix conditioned jointly on its stem and context, we obtain large improvements over state-of-the-art spell checkers on three different benchmarking datasets, achieving a perfect score on a verb spelling test from de Standaard, a Flemish newspaper. The method is unsupervised and only relies on basic preprocessing tools to tokenize the text and identify verbs, which enables training on millions of sentences. Furthermore, we propose a method to determine which words in a sentence cause the system to make corrections, which is valuable for providing feedback to the user.

Marie-Francine Moens

Papers

Checkworthiness in Automatic Claim Detection Models: Definitions and Analysis of Datasets.

Evaluation of Intelligent Exploitation Tools for Non-structured Police Information

Generating a Topic Hierarchy from Dialect Texts

Unsupervised scene detection and commentator building using multi-modal chains

Automatic detection and correction of context-dependent dt-mistakes using neural networks