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

We query the pictures of Yahoo! News for persons and objects by using the accompanying news captions as an indexing annotation. Our aim is to find these pictures on top of the answer list in which the sought persons or objects are most prominently present. We demonstrate that an appearance or content model based on syntactic, semantic and discourse analysis of the short news text is only useful for finding the best picture of a person of object if the database contains photos each picturing many entities. In other circumstances a simpler bag-of-nouns representation has a good performance. The appearance models are tested in a probabilistic ranking function.

/pdf/finding-the-best-picture-cross-media-retrieval-of-content-4zasyvfo8e.pdf

Finding the best picture: cross-media retrieval of content

The neural encoder-decoder framework is widely adopted for image captioning of natural images. However, few works have contributed to generating captions for cultural images using this scheme. In this paper, we propose an artwork type enriched image captioning model where the encoder represents an input artwork image as a 512-dimensional vector and the decoder generates a corresponding caption based on the input image vector. The artwork type is first predicted by a convolutional neural network classifier and then merged into the decoder. We investigate multiple approaches to integrate the artwork type into the captioning model among which is one that applies a step-wise weighted sum of the artwork type vector and the hidden representation vector of the decoder. This model outperforms three baseline image captioning models for a Chinese art image captioning dataset on all evaluation metrics. One of the baselines is a state-of-the-art approach fusing textual image attributes into the captioning model for natural images. The proposed model also obtains promising results for another Egyptian art image captioning dataset.

https://dl.acm.org/doi/pdf/10.1145/3343031.3350972

Generating Captions for Images of Ancient Artworks

Feed-forward networks are widely used in cross-modal applications to bridge modalities by mapping distributed vectors of one modality to the other, or to a shared space. The predicted vectors are then used to perform e.g., retrieval or labeling. Thus, the success of the whole system relies on the ability of the mapping to make the neighborhood structure (i.e., the pairwise similarities) of the predicted vectors akin to that of the target vectors. However, whether this is achieved has not been investigated yet. Here, we propose a new similarity measure and two ad hoc experiments to shed light on this issue. In three cross-modal benchmarks we learn a large number of language-to-vision and vision-to-language neural network mappings (up to five layers) using a rich diversity of image and text features and loss functions. Our results reveal that, surprisingly, the neighborhood structure of the predicted vectors consistently resembles more that of the input vectors than that of the target vectors. In a second experiment, we further show that untrained nets do not significantly disrupt the neighborhood (i.e., semantic) structure of the input vectors.

/pdf/do-neural-network-cross-modal-mappings-really-bridge-2dfjrrzmrk.pdf

Do Neural Network Cross-Modal Mappings Really Bridge Modalities?

Spam and phishing emails are not only annoying to users, but are a real threat to internet communication and web economy. The fight against unwanted emails has become a cat-and-mouse game between criminals and people trying to develop techniques for detecting such unwanted emails. Criminals are constantly developing new tricks and adopt the ones that make emails pass spam filters. We have developed a systems that enables the detection of certain common salting tricks that are employed by criminals. Salting is the intentional addition or distortion of content. In this paper we describe a framework to identify email messages that might contain new, previously unseen tricks. To this end, we compare the simulated perceived email message text generated by our hidden salting simulation system to the OCRed text we obtain from the rendered email message. We present robust text comparison techniques and train a classifier based on the differences of these two texts. In simulations we show that we can detect suspicious emails with a high level of accuracy.

/pdf/detecting-known-and-new-salting-tricks-in-unwanted-emails-3zpdv96zfy.pdf

Detecting Known and New Salting Tricks in Unwanted Emails.

Presently, we are confronted with an enormous amount of legal documents, which are increasingly recorded in electronic format. There is a need to make the information in legal texts easily and automatically accessible. In this paper we argue that in the legal field, where we are confronted with specific text types, knowledge about discourse structures and the linguistic cues that signal them is very valuable to incorporate in information extraction systems and in text processing systems in general. We also demonstrate the need for adequate formalisms for representing discourse patterns. However, intertextual analysis of texts that describes and explains the properties of text types and genres is underdeveloped in the legal field.

Marie-Francine Moens

Papers

Finding the best picture: cross-media retrieval of content

Generating Captions for Images of Ancient Artworks

Do Neural Network Cross-Modal Mappings Really Bridge Modalities?

Detecting Known and New Salting Tricks in Unwanted Emails.

Intelligent Information Extraction from Legal Texts