The key idea behind active learning is that a machine learning algorithm can perform better with less training if it is allowed to choose the data from which it learns. An active learner may pose "queries," usually in the form of unlabeled data instances to be labeled by an "oracle" (e.g., a human annotator) that already understands the nature of the problem. This sort of approach is well-motivated in many modern machine learning and data mining applications, where unlabeled data may be abundant or easy to come by, but training labels are difficult, time-consuming, or expensive to obtain. This book is a general introduction to active learning. It outlines several scenarios in which queries might be formulated, and details many query selection algorithms which have been organized into four broad categories, or "query selection frameworks." We also touch on some of the theoretical foundations of active learning, and conclude with an overview of the strengths and weaknesses of these approaches in practice, including a summary of ongoing work to address these open challenges and opportunities.

Active Learning

Learning multilingual named entity recognition from Wikipedia

Most current dependency parsers presuppose that input words have been morphologically disambiguated using a part-of-speech tagger before parsing begins. We present a transition-based system for joint part-of-speech tagging and labeled dependency parsing with non-projective trees. Experimental evaluation on Chinese, Czech, English and German shows consistent improvements in both tagging and parsing accuracy when compared to a pipeline system, which lead to improved state-of-the-art results for all languages.

A Transition-Based System for Joint Part-of-Speech Tagging and Labeled Non-Projective Dependency Parsing

https://link.springer.com/content/pdf/10.1057%2Fjors.1990.171.pdf

Computer Intensive Methods for Testing Hypotheses: An Introduction

Active learning is a supervised machine learning technique in which the learner is in control of the data used for learning. That control is utilized by the learner to ask an oracle, typically a human with extensive knowledge of the domain at hand, about the classes of the instances for which the model learned so far makes unreliable predictions. The active learning process takes as input a set of labeled examples, as well as a larger set of unlabeled examples, and produces a classifier and a relatively small set of newly labeled data. The overall goal is to create as good a classifier as possible, without having to mark-up and supply the learner with more data than necessary. The learning process aims at keeping the human annotation effort to a minimum, only asking for advice where the training utility of the result of such a query is high. Active learning has been successfully applied to a number of natural language processing tasks, such as, information extraction, named entity recognition, text categorization, part-of-speech tagging, parsing, and word sense disambiguation. This report is a literature survey of active learning from the perspective of natural language processing.

/pdf/a-literature-survey-of-active-machine-learning-in-the-13naa5r7xl.pdf

A literature survey of active machine learning in the context of natural language processing

We present a HMM part-of-speech tagging method which is particularly suited for POS tagsets with a large number of fine-grained tags. It is based on three ideas: (1) splitting of the POS tags into attribute vectors and decomposition of the contextual POS probabilities of the HMM into a product of attribute probabilities, (2) estimation of the contextual probabilities with decision trees, and (3) use of high-order HMMs. In experiments on German and Czech data, our tagger outperformed state-of-the-art POS taggers.

/pdf/estimation-of-conditional-probabilities-with-decision-trees-5dhyfrz4k4.pdf

Estimation of Conditional Probabilities With Decision Trees and an Application to Fine-Grained POS Tagging

Active learning is a proven method for reducing the cost of creating the training sets that are necessary for statistical NLP. However, there has been little work on stopping criteria for active learning. An operational stopping criterion is necessary to be able to use active learning in NLP applications. We investigate three different stopping criteria for active learning of named entity recognition (NER) and show that one of them, gradient-based stopping, (i) reliably stops active learning, (ii) achieves nearoptimal NER performance, (iii) and needs only about 20% as much training data as exhaustive labeling.

Stopping Criteria for Active Learning of Named Entity Recognition

Supervised classification needs large amounts of annotated training data that is expensive to create. Two approaches that reduce the cost of annotation are active learning and crowdsourcing. However, these two approaches have not been combined successfully to date. We evaluate the utility of active learning in crowdsourcing on two tasks, named entity recognition and sentiment detection, and show that active learning outperforms random selection of annotation examples in a noisy crowdsourcing scenario.

/pdf/active-learning-with-amazon-mechanical-turk-4u6vik2snl.pdf

Active Learning with Amazon Mechanical Turk

We present CloudScan; an invoice analysis system that requires zero configuration or upfront annotation. In contrast to previous work, CloudScan does not rely on templates of invoice layout, instead it learns a single global model of invoices that naturally generalizes to unseen invoice layouts. The model is trained using data automatically extracted from end-user provided feedback. This automatic training data extraction removes the requirement for users to annotate the data precisely. We describe a recurrent neural network model that can capture long range context and compare it to a baseline logistic regression model corresponding to the current CloudScan production system. We train and evaluate the system on 8 important fields using a dataset of 326,471 invoices. The recurrent neural network and baseline model achieve 0.891 and 0.887 average F1 scores respectively on seen invoice layouts. For the harder task of unseen invoice layouts, the recurrent neural network model outperforms the baseline with 0.840 average F1 compared to 0.788.

/pdf/cloudscan-a-configuration-free-invoice-analysis-system-using-2t7tt4bxzm.pdf

CloudScan - A Configuration-Free Invoice Analysis System Using Recurrent Neural Networks

Document information extraction tasks performed by humans create data consisting of a PDF or document image input, and extracted string outputs. This end-to-end data is naturally consumed and produced when performing the task because it is valuable in and of itself. It is naturally available, at no additional cost. Unfortunately, state-of-the-art word classification methods for information extraction cannot use this data, instead requiring word-level labels which are expensive to create and consequently not available for many real life tasks. In this paper we propose the Attend, Copy, Parse architecture, a deep neural network model that can be trained directly on end-to-end data, bypassing the need for word-level labels. We evaluate the proposed architecture on a large diverse set of invoices, and outperform a state-of-the-art production system based on word classification. We believe our proposed architecture can be used on many real life information extraction tasks where word classification cannot be used due to a lack of the required word-level labels.

Florian Laws

Papers

Estimation of Conditional Probabilities With Decision Trees and an Application to Fine-Grained POS Tagging

Stopping Criteria for Active Learning of Named Entity Recognition

Active Learning with Amazon Mechanical Turk

CloudScan - A Configuration-Free Invoice Analysis System Using Recurrent Neural Networks

Attend, Copy, Parse End-to-end Information Extraction from Documents