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

This paper proposes an iterative inference algorithm for multi-hop explanation regeneration, that retrieves relevant factual evidence in the form of text snippets, given a natural language question and its answer. Combining multiple sources of evidence or facts for multi-hop reasoning becomes increasingly hard when the number of sources needed to make an inference grows. Our algorithm copes with this by decomposing the selection of facts from a corpus autoregressively, conditioning the next iteration on previously selected facts. This allows us to use a pairwise learning-to-rank loss. We validate our method on datasets of the TextGraphs 2019 and 2020 Shared Tasks for explanation regeneration. Existing work on this task either evaluates facts in isolation or artificially limits the possible chains of facts, thus limiting multi-hop inference. We demonstrate that our algorithm, when used with a pre-trained transformer model, outperforms the previous state-of-the-art in terms of precision, training time and inference efficiency.

Autoregressive Reasoning over Chains of Facts with Transformers.

Implicit semantic role labeling (iSRL) is the task of predicting the semantic roles of a predicate that do not appear as explicit arguments, but rather regard common sense knowledge or are mentioned earlier in the discourse. We introduce an approach to iSRL based on a predictive recurrent neural semantic frame model (PRNSFM) that uses a large unannotated corpus to learn the probability of a sequence of semantic arguments given a predicate. We leverage the sequence probabilities predicted by the PRNSFM to estimate selectional preferences for predicates and their arguments. On the NomBank iSRL test set, our approach improves state-of-the-art performance on implicit semantic role labeling with less reliance than prior work on manually constructed language resources.

Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments

Discrete and continuous representations of content (e.g., of language or images) have interesting properties to be explored for the understanding of or reasoning with this content by machines. This position paper puts forward our opinion on the role of discrete and continuous representations and their processing in the deep learning field. Current neural network models compute continuous-valued data. Information is compressed into dense, distributed embeddings. By stark contrast, humans use discrete symbols in their communication with language. Such symbols represent a compressed version of the world that derives its meaning from shared contextual information. Additionally, human reasoning involves symbol manipulation at a cognitive level, which facilitates abstract reasoning, the composition of knowledge and understanding, generalization and efficient learning. Motivated by these insights, in this paper we argue that combining discrete and continuous representations and their processing will be essential to build systems that exhibit a general form of intelligence. We suggest and discuss several avenues that could improve current neural networks with the inclusion of discrete elements to combine the advantages of both types of representations.

Discrete and continuous representations and processing in deep learning: Looking forward

The study of the formal attributes of legal systems such as consistency, completeness, independence and generality is of special interest in legal philosophy and legal theory. Apart from concern with the content of the law, these formal attributes constitute desiderata without which a legal system is considered deficient. Legisprudence is a relatively new discipline within legal theory that studies these formal (and other) attributes of law at the level of law making (i.e. legislation). This trend in legal theory is also paralleled by research in the so-called field of legimatics, which focuses generally on the use of informatics in the process of drafting legislation. One approach within legimatics studies the limits and constraints of applying AI techniques and methods to the law making process (e.g. JURIX 1993) as well as application of these techniques to certain tasks within this process (JURIX 1993; Valente 1995; Den Haan 1996). This paper discusses normative conflicts, their explication and typology, and relates these to the conceptualization of legal knowledge and methods for representing it. In particular, we discuss some common approaches in legal theory for the explication of normative conflicts and show their limitations. In particular, we argue that these common approaches do not pay sufficient attention to the role ‘world knowledge’ plays in the analysis of normative conflicts. Finally, we suggest alternative ways for dealing with the problems that arise from inconsistency in law. The observations we make are relevant for the development of computer programs designed to assist in the law-making process. 1 The problem of normative conflicts Normative conflict or inconsistency in law1 is broadly defined as the provision by the legal system of incompatible solutions to the same individual 1 There is a plethora of terms used to refer to the phenomenon of inconsistency in law notwithstanding the conceptual differences underlying these terms. Normative inconsistencies, normative conflicts, antinomies, discordance etc. are among these terms. In this paper we do not attempt to offer a full account of the conceptual differences underlying these terms but will make reference to them when

/pdf/on-the-formal-analysis-of-normative-conflicts-eaqa9ts9mo.pdf

On the formal analysis of normative conflicts

In this paper, we present four clustering algorithms for noun phrase coreference resolution. We developed two novel algorithms for this task, a fuzzy algorithm and its hard variant and evaluated their performance on two dierent sets of texts in comparison with an existing fuzzy and a hard clustering algorithm that are described in the literature. Our algorithms perform slightly better and do not rely on a predefined threshold distance value for cluster membership. In addition, our fuzzy clustering algorithm seems to perform better than a hard clustering on a pronoun resolution task.

/pdf/clustering-algorithms-for-noun-phrase-coreference-resolution-3mo3yb4x4z.pdf

Marie-Francine Moens

Papers

Autoregressive Reasoning over Chains of Facts with Transformers.

Improving Implicit Semantic Role Labeling by Predicting Semantic Frame Arguments

Discrete and continuous representations and processing in deep learning: Looking forward

On the formal analysis of normative conflicts

Clustering Algorithms for Noun Phrase Coreference Resolution