Data Mining Practical Machine Learning Tools and Techniques

Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts all text-based language problems into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new ``Colossal Clean Crawled Corpus'', we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our data set, pre-trained models, and code.

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

Neural Machine Translation (NMT) has obtained state-of-the art performance for several language pairs, while only using parallel data for training. Target-side monolingual data plays an important role in boosting fluency for phrase-based statistical machine translation, and we investigate the use of monolingual data for NMT. In contrast to previous work, which combines NMT models with separately trained language models, we note that encoder-decoder NMT architectures already have the capacity to learn the same information as a language model, and we explore strategies to train with monolingual data without changing the neural network architecture. By pairing monolingual training data with an automatic back-translation, we can treat it as additional parallel training data, and we obtain substantial improvements on the WMT 15 task English German (+2.8-3.7 BLEU), and for the low-resourced IWSLT 14 task Turkish->English (+2.1-3.4 BLEU), obtaining new state-of-the-art results. We also show that fine-tuning on in-domain monolingual and parallel data gives substantial improvements for the IWSLT 15 task English->German.

/pdf/improving-neural-machine-translation-models-with-monolingual-5duca8kmlm.pdf

Improving Neural Machine Translation Models with Monolingual Data

Knowledge graph (KG) embedding is to embed components of a KG including entities and relations into continuous vector spaces, so as to simplify the manipulation while preserving the inherent structure of the KG. It can benefit a variety of downstream tasks such as KG completion and relation extraction, and hence has quickly gained massive attention. In this article, we provide a systematic review of existing techniques, including not only the state-of-the-arts but also those with latest trends. Particularly, we make the review based on the type of information used in the embedding task. Techniques that conduct embedding using only facts observed in the KG are first introduced. We describe the overall framework, specific model design, typical training procedures, as well as pros and cons of such techniques. After that, we discuss techniques that further incorporate additional information besides facts. We focus specifically on the use of entity types, relation paths, textual descriptions, and logical rules. Finally, we briefly introduce how KG embedding can be applied to and benefit a wide variety of downstream tasks such as KG completion, relation extraction, question answering, and so forth.

Knowledge Graph Embedding: A Survey of Approaches and Applications

A catalogue record for this book is available from the British Library ISBN 0 521 82347 1 hardback ISBN 0 521 53032 6 paperback Contents List of tables page vii Preface to the second edition ix Preface to the first edition xii 1 Why a global language? 1 What is a global language? 3 What makes a global language? 7 Why do we need a global language? 11 What are the dangers of a global language? 14 Could anything stop a global language? 25 A critical era 27 2 Why English? The historical context 29 Origins 30 America 31 Canada 36 The Caribbean 39 Australia and New Zealand 40 South Africa 43 South Asia 46 Former colonial Africa 49 Southeast Asia and the South Pacific 54 A world view 59 v Contents

English as a global language

There has recently been an increased interest in named entity recognition and disambiguation systems at major conferences such as WWW, SIGIR, ACL, KDD, etc. However, most work has focused on algorithms and evaluations, leaving little space for implementation details. In this paper, we discuss some implementation and data processing challenges we encountered while developing a new multilingual version of DBpedia Spotlight that is faster, more accurate and easier to configure. We compare our solution to the previous system, considering time performance, space requirements and accuracy in the context of the Dutch and English languages. Additionally, we report results for 9 additional languages among the largest Wikipedias. Finally, we present challenges and experiences to foment the discussion with other developers interested in recognition and disambiguation of entities in natural language text.

Improving efficiency and accuracy in multilingual entity extraction

This paper presents the results of the WMT15 shared tasks, which included a standard news translation task, a metrics task, a tuning task, a task for run-time estimation of machine translation quality, and an automatic post-editing task. This year, 68 machine translation systems from 24 institutions were submitted to the ten translation directions in the standard translation task. An additional 7 anonymized systems were included, and were then evaluated both automatically and manually. The quality estimation task had three subtasks, with a total of 10 teams, submitting 34 entries. The pilot automatic postediting task had a total of 4 teams, submitting 7 entries.

/pdf/findings-of-the-2015-workshop-on-statistical-machine-2w6uujmxuh.pdf

Findings of the 2015 Workshop on Statistical Machine Translation

We present Grid Beam Search (GBS), an algorithm which extends beam search to allow the inclusion of pre-specified lexical constraints. The algorithm can be used with any model that generates a sequence $ \mathbf{\hat{y}} = \{y_{0}\ldots y_{T}\} $, by maximizing $ p(\mathbf{y} | \mathbf{x}) = \prod\limits_{t}p(y_{t} | \mathbf{x}; \{y_{0} \ldots y_{t-1}\}) $. Lexical constraints take the form of phrases or words that must be present in the output sequence. This is a very general way to incorporate additional knowledge into a model's output without requiring any modification of the model parameters or training data. We demonstrate the feasibility and flexibility of Lexically Constrained Decoding by conducting experiments on Neural Interactive-Predictive Translation, as well as Domain Adaptation for Neural Machine Translation. Experiments show that GBS can provide large improvements in translation quality in interactive scenarios, and that, even without any user input, GBS can be used to achieve significant gains in performance in domain adaptation scenarios.

Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search

We present Grid Beam Search (GBS), an algorithm which extends beam search to allow the inclusion of pre-specified lexical constraints. The algorithm can be used with any model which generates sequences token by token. Lexical constraints take the form of phrases or words that must be present in the output sequence. This is a very general way to incorporate auxillary knowledge into a model’s output without requiring any modification of the parameters or training data. We demonstrate the feasibility and flexibility of Lexically Constrained Decoding by conducting experiments on Neural Interactive-Predictive Translation, as well as Domain Adaptation for Neural Machine Translation. Experiments show that GBS can provide large improvements in translation quality in interactive scenarios, and that, even without any user input, GBS can be used to achieve significant gains in performance in domain adaptation scenarios.

/pdf/lexically-constrained-decoding-for-sequence-generation-using-5d5y7siwts.pdf

Translation quality estimation is a task of growing importance in NLP, due to its potential to reduce post-editing human effort in disruptive ways. However, this potential is currently limited by the relatively low accuracy of existing systems. In this paper, we achieve remarkable improvements by exploiting synergies between the related tasks of word-level quality estimation and automatic post-editing. First, we stack a new, carefully engineered, neural model into a rich feature-based word-level quality estimation system. Then, we use the output of an automatic post-editing system as an extra feature, obtaining striking results on WMT16: a word-level F 1 MULT score of 57.47% (an absolute gain of +7.95% over the current state of the art), and a Pearson correlation score of 65.56% for sentence-level HTER prediction (an absolute gain of +13.36%).

/pdf/pushing-the-limits-of-translation-quality-estimation-l4tv7u6kha.pdf

Chris Hokamp

Papers

Improving efficiency and accuracy in multilingual entity extraction

Findings of the 2015 Workshop on Statistical Machine Translation

Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search

Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search

Pushing the Limits of Translation Quality Estimation