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

Neural machine translation (NMT) models typically operate with a fixed vocabulary, but translation is an open-vocabulary problem. Previous work addresses the translation of out-of-vocabulary words by backing off to a dictionary. In this paper, we introduce a simpler and more effective approach, making the NMT model capable of open-vocabulary translation by encoding rare and unknown words as sequences of subword units. This is based on the intuition that various word classes are translatable via smaller units than words, for instance names (via character copying or transliteration), compounds (via compositional translation), and cognates and loanwords (via phonological and morphological transformations). We discuss the suitability of different word segmentation techniques, including simple character ngram models and a segmentation based on the byte pair encoding compression algorithm, and empirically show that subword models improve over a back-off dictionary baseline for the WMT 15 translation tasks English!German and English!Russian by up to 1.1 and 1.3 BLEU, respectively.

/pdf/neural-machine-translation-of-rare-words-with-subword-units-3w3a5ojqnb.pdf

Neural Machine Translation of Rare Words with Subword Units

We describe an open-source toolkit for statistical machine translation whose novel contributions are (a) support for linguistically motivated factors, (b) confusion network decoding, and (c) efficient data formats for translation models and language models. In addition to the SMT decoder, the toolkit also includes a wide variety of tools for training, tuning and applying the system to many translation tasks.

/pdf/moses-open-source-toolkit-for-statistical-machine-3pmfuwk8uc.pdf

Moses: Open Source Toolkit for Statistical Machine Translation

This introductory text to statistical machine translation (SMT) provides all of the theories and methods needed to build a statistical machine translator, such as Google Language Tools and Babelfish. In general, statistical techniques allow automatic translation systems to be built quickly for any language-pair using only translated texts and generic software. With increasing globalization, statistical machine translation will be central to communication and commerce. Based on courses and tutorials, and classroom-tested globally, it is ideal for instruction or self-study, for advanced undergraduates and graduate students in computer science and/or computational linguistics, and researchers in natural language processing. The companion website provides open-source corpora and tool-kits.

/pdf/statistical-machine-translation-1yr1jtzcjp.pdf

Statistical Machine Translation

We present a statistical phrase-based translation model that uses hierarchical phrases---phrases that contain subphrases. The model is formally a synchronous context-free grammar but is learned from a bitext without any syntactic information. Thus it can be seen as a shift to the formal machinery of syntax-based translation systems without any linguistic commitment. In our experiments using BLEU as a metric, the hierarchical phrase-based model achieves a relative improvement of 7.5% over Pharaoh, a state-of-the-art phrase-based system.

/pdf/a-hierarchical-phrase-based-model-for-statistical-machine-1xejmbxuk5.pdf

A Hierarchical Phrase-Based Model for Statistical Machine Translation

We achieved a state of the art performance in statistical machine translation by using a large number of features with an online large-margin training algorithm. The millions of parameters were tuned only on a small development set consisting of less than 1K sentences. Experiments on Arabic-toEnglish translation indicated that a model trained with sparse binary features outperformed a conventional SMT system with a small number of features.

Online Large-Margin Training for Statistical Machine Translation

In statistical machine translation, the generation of a translation hypothesis is computationally expensive. If arbitrary reorderings are permitted, the search problem is NP-hard. On the other hand, if we restrict the possible reorderings in an appropriate way, we obtain a polynomial-time search algorithm. We investigate different reordering constraints for phrase-based statistical machine translation, namely the IBM constraints and the ITG constraints. We present efficient dynamic programming algorithms for both constraints. We evaluate the constraints with respect to translation quality on two Japanese-English tasks. We show that the reordering constraints improve translation quality compared to an unconstrained search that permits arbitrary phrase reorderings. The ITG constraints preform best on both tasks and yield statistically significant improvements compared to the unconstrained search.

/pdf/reordering-constraints-for-phrase-based-statistical-machine-13q0cexb64.pdf

Reordering constraints for phrase-based statistical machine translation

We present an unsupervised model for joint phrase alignment and extraction using non-parametric Bayesian methods and inversion transduction grammars (ITGs). The key contribution is that phrases of many granularities are included directly in the model through the use of a novel formulation that memorizes phrases generated not only by terminal, but also non-terminal symbols. This allows for a completely probabilistic model that is able to create a phrase table that achieves competitive accuracy on phrase-based machine translation tasks directly from unaligned sentence pairs. Experiments on several language pairs demonstrate that the proposed model matches the accuracy of traditional two-step word alignment/phrase extraction approach while reducing the phrase table to a fraction of the original size.

/pdf/an-unsupervised-model-for-joint-phrase-alignment-and-3u430qcg2m.pdf

An Unsupervised Model for Joint Phrase Alignment and Extraction

This study proposes a word alignment model based on a recurrent neural network (RNN), in which an unlimited alignment history is represented by recurrently connected hidden layers. We perform unsupervised learning using noise-contrastive estimation (Gutmann and Hyvarinen, 2010; Mnih and Teh, 2012), which utilizes artificially generated negative samples. Our alignment model is directional, similar to the generative IBM models (Brown et al., 1993). To overcome this limitation, we encourage agreement between the two directional models by introducing a penalty function that ensures word embedding consistency across two directional models during training. The RNN-based model outperforms the feed-forward neural network-based model (Yang et al., 2013) as well as the IBM Model 4 under Japanese-English and French-English word alignment tasks, and achieves comparable translation performance to those baselines for Japanese-English and Chinese-English translation tasks.

/pdf/recurrent-neural-networks-for-word-alignment-model-3scpv78sdd.pdf

Recurrent Neural Networks for Word Alignment Model

This paper proposes a novel method for lexicon extraction that extracts translation pairs from comparable corpora by using graph-based label propagation. In previous work, it was established that performance drastically decreases when the coverage of a seed lexicon is small. We resolve this problem by utilizing indirect relations with the bilingual seeds together with direct relations, in which each word is represented by a distribution of translated seeds. The seed distributions are propagated over a graph representing relations among words, and translation pairs are extracted by identifying word pairs with a high similarity in the seed distributions. We propose two types of the graphs: a co-occurrence graph, representing co-occurrence relations between words, and a similarity graph, representing context similarities between words. Evaluations using English and Japanese patent comparable corpora show that our proposed graph propagation method outperforms conventional methods. Further, the similarity graph achieved improved performance by clustering synonyms into the same translation.

Taro Watanabe

Papers

Online Large-Margin Training for Statistical Machine Translation

Reordering constraints for phrase-based statistical machine translation

An Unsupervised Model for Joint Phrase Alignment and Extraction

Recurrent Neural Networks for Word Alignment Model

Bilingual Lexicon Extraction from Comparable Corpora Using Label Propagation