Data Mining Practical Machine Learning Tools and Techniques

tical perspective. For instance, there are only three passing references to kuru in a book of 650 pages. This edition reflects the renewed interest in the immunological theories of multiple sclerosis. More than half the text is devoted to Professor Lumsden's analysis of the pathoIogy and, in particular, the chemical pathology of the immune response. There is a great deal of original work devoted to the chemistry and behaviour of the immunoglobulins. Much of this appears in specialist journals and one must be grateful for the critical summary provided here. Professor Lumsden unequivocally sees the key to the problem of multiple sclerosis in the study of its immunochemistry, relegating infection by a virus or a slow virus to a quite subsidiary role. The clinical studies drawing on wide practical experience help to get one's prejudices about the illness onto a more reasoned footing. The section on treatment is still sadly limited. Dr. McAlpine found little to add to the regime which he described in 1955. McAlpine, Lumsden, and Acheson's reappraisal is an essential reference for the practising neurologist and the new edition makes important modification of and changes in emphasis from the edition of 1965.

https://jnnp.bmj.com/content/jnnp/36/5/894.3.full.pdf

The assessment of aphasia and related disorders

Distributed word representations, or word vectors, have recently been applied to many tasks in natural language processing, leading to state-of-the-art performance. A key ingredient to the successful application of these representations is to train them on very large corpora, and use these pre-trained models in downstream tasks. In this paper, we describe how we trained such high quality word representations for 157 languages. We used two sources of data to train these models: the free online encyclopedia Wikipedia and data from the common crawl project. We also introduce three new word analogy datasets to evaluate these word vectors, for French, Hindi and Polish. Finally, we evaluate our pre-trained word vectors on 10 languages for which evaluation datasets exists, showing very strong performance compared to previous models.

Learning Word Vectors for 157 Languages

Distributed word representations have recently been proven to be an invaluable resource for NLP. These representations are normally learned using neural networks and capture syntactic and semantic information about words. Information about word morphology and shape is normally ignored when learning word representations. However, for tasks like part-of-speech tagging, intra-word information is extremely useful, specially when dealing with morphologically rich languages. In this paper, we propose a deep neural network that learns character-level representation of words and associate them with usual word representations to perform POS tagging. Using the proposed approach, while avoiding the use of any handcrafted feature, we produce state-of-the-art POS taggers for two languages: English, with 97.32% accuracy on the Penn Treebank WSJ corpus; and Portuguese, with 97.47% accuracy on the Mac-Morpho corpus, where the latter represents an error reduction of 12.2% on the best previous known result.

/pdf/learning-character-level-representations-for-part-of-speech-i2dwfr91wo.pdf

Learning Character-level Representations for Part-of-Speech Tagging

Most recent sentence simplification systems use basic machine translation models to learn lexical and syntactic paraphrases from a manually simplified parallel corpus. These methods are limited by the quality and quantity of manually simplified corpora, which are expensive to build. In this paper, we conduct an in-depth adaptation of statistical machine translation to perform text simplification, taking advantage of large-scale paraphrases learned from bilingual texts and a small amount of manual simplifications with multiple references. Our work is the first to design automatic metrics that are effective for tuning and evaluating simplification systems, which will facilitate iterative development for this task.

/pdf/optimizing-statistical-machine-translation-for-text-2uqxl8rf9e.pdf

Optimizing Statistical Machine Translation for Text Simplification

Discriminating between Similar Languages (DSL) is a challenging task addressed at the VarDial Workshop series. We report on our participation in the DSL shared task with a two-stage system. In the first stage, character n-grams are used to separate language groups, then specialized classifiers distinguish similar language varieties. We have conducted experiments with three system configurations and submitted one run for each. Our main approach is a word-level convolutional neural network (CNN) that learns task-specific vectors with minimal text preprocessing. We also experiment with multi-layer perceptron (MLP) networks and another hybrid configuration. Our best run achieved an accuracy of 90.76%, ranking 8th among 11 participants and getting very close to the system that ranked first (less than 2 points). Even though the CNN model could not achieve the best results, it still makes a viable approach to discriminating between similar languages.

/pdf/discriminating-between-similar-languages-with-word-level-11n6g5anpu.pdf

Discriminating between Similar Languages with Word-level Convolutional Neural Networks

Effective textual communication depends on readers being proficient enough to comprehend texts, and texts being clear enough to be understood by the intended audience, in a reading task. When the meaning of textual information and instructions is not well conveyed, many losses and damages may occur. Among the solutions to alleviate this problem is the automatic evaluation of sentence readability, task which has been receiving a lot of attention due to its large applicability. However, a shortage of resources, such as corpora for training and evaluation, hinders the full development of this task. In this paper, we generate a nontrivial sentence corpus in Portuguese. We evaluate three scenarios for building it, taking advantage of a parallel corpus of simplification, in which each sentence triplet is aligned and has simplification operations annotated, being ideal for justifying possible mistakes of future methods. The best scenario of our corpus PorSimplesSent is composed of 4,888 pairs, which is bigger than a similar corpus for English; all the three versions of it are publicly available. We created four baselines for PorSimplesSent and made available a pairwise ranking method, using 17 linguistic and psycholinguistic features, which correctly identifies the ranking of sentence pairs with an accuracy of 74.2%.

A Nontrivial Sentence Corpus for the Task of Sentence Readability Assessment in Portuguese

Corpus nilc: descrição e análise crítica com vistas ao projeto Lacio-Web

The Web content accessibility guidelines (WCAG) 2.0 include in its principle of comprehensibility an accessibility requirement related to the level of writing. This requirement states that websites with texts demanding higher reading skills than individuals with lower secondary education possess (fifth to ninth grades in Brazil) should offer them an alternative version of the same content. Natural Language Processing technology and research in Psycholinguistics can help automate the task of classifying a text according to its reading difficulty. In this paper, we present experiments to build a readability checker to classify texts in Portuguese, considering different text genres, domains and reader ages, using naturally occurring texts. More precisely, we classify texts in simple (for 7 to 14-year-olds) and complex (for adults), and address three key research questions: (1) Which machine-learning algorithm produces the best results? (2) Which features are relevant? (3) Do different text genres have an impact on readability assessment?.

Revisiting the readability assessment of texts in portuguese

In low-resource scenarios, for example, small datasets or a lack in computational resources available, state-of-the-art deep learning methods for speech recognition have been known to fail. It is possible to achieve more robust models if care is taken to ensure the learning guarantees provided by the statistical learning theory. This work presents a shallow and hybrid approach using a convolutional neural network feature extractor fed into a hierarchical tree of support vector machines for classification. Here, we show that gross errors present even in state-of-the-art systems can be avoided and that an accurate acoustic model can be built in a hierarchical fashion. Furthermore, we present proof that our algorithm does adhere to the learning guarantees provided by the statistical learning theory. The acoustic model produced in this work outperforms traditional hidden Markov models, and the hierarchical support vector machine tree outperforms a multi-class multilayer perceptron classifier using the same features. More importantly, we isolate the performance of the acoustic model and provide results on both the frame and phoneme level, considering the true robustness of the model. We show that even with a small amount of data, accurate and robust recognition rates can be obtained.

/pdf/theoretical-learning-guarantees-applied-to-acoustic-modeling-2p5tuzf1m4.pdf

Sandra Maria Aluísio

Papers

Discriminating between Similar Languages with Word-level Convolutional Neural Networks

A Nontrivial Sentence Corpus for the Task of Sentence Readability Assessment in Portuguese

Corpus nilc: descrição e análise crítica com vistas ao projeto Lacio-Web

Revisiting the readability assessment of texts in portuguese

Theoretical learning guarantees applied to acoustic modeling