Multi-task learning (MTL) has led to successes in many applications of machine learning, from natural language processing and speech recognition to computer vision and drug discovery. This article aims to give a general overview of MTL, particularly in deep neural networks. It introduces the two most common methods for MTL in Deep Learning, gives an overview of the literature, and discusses recent advances. In particular, it seeks to help ML practitioners apply MTL by shedding light on how MTL works and providing guidelines for choosing appropriate auxiliary tasks.

An Overview of Multi-Task Learning in Deep Neural Networks

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

Child psychiatrists, pediatricians, and other child clinicians need to have a solid understanding of child language development. There are at least four important reasons that make this necessary. First, slowing, arrest, and deviation of language development are highly associated with, and complicate the course of, child psychopathology. Second, language competence plays a crucial role in emotional and mood regulation, evaluation, and therapy. Third, language deficits are the most frequent underpinning of the learning disorders, ubiquitous in our clinical populations. Fourth, clinicians should not confuse the rich linguistic and dialectal diversity of our clinical populations with abnormalities in child language development. The challenge for the clinician becomes, then, how to get immersed in the captivating field of child language acquisition without getting overwhelmed by its conceptual and empirical complexity. In the past 50 years and since the seminal works of Roger Brown, Jerome Bruner, and Catherine Snow, child language researchers (often known as developmental psycholinguists) have produced a remarkable body of knowledge. Linguists such as Chomsky and philosophers such as Grice have strongly influenced the science of child language. One of the major tenets of Chomskian linguistics (known as generative grammar) is that children’s capacity to acquire language is “hardwired” with “universal grammar”—an innate language acquisition device (LAD), a language “instinct”—at its core. This view is in part supported by the assertion that the linguistic input that children receive is relatively dismal and of poor quality relative to the high quantity and quality of output that they manage to produce after age 2 and that only an advanced, innate capacity to decode and organize linguistic input can enable them to “get from here (prelinguistic infant) to there (linguistic child).” In “Constructing a Language,” Tomasello presents a contrasting theory of how the child acquires language: It is not a universal grammar that allows for language development. Rather, human cognition universals of communicative needs and vocal-auditory processing result in some language universals, such as nouns and verbs as expressions of reference and predication (p. 19). The author proposes that two sets of cognitive skills resulting from biological/phylogenetic adaptations are fundamental to the ontogenetic origins of language. These sets of inherited cognitive skills are intentionreading on the one hand and pattern-finding, on the other. Intention-reading skills encompass the prelinguistic infant’s capacities to share attention to outside events with other persons, establishing joint attentional frames, to understand other people’s communicative intentions, and to imitate the adult’s communicative intentions (an intersubjective form of imitation that requires symbolic understanding and perspective-taking). Pattern-finding skills include the ability of infants as young as 7 months old to analyze concepts and percepts (most relevant here, auditory or speech percepts) and create concrete or abstract categories that contain analogous items. Tomasello, a most prominent developmental scientist with research foci on child language acquisition and on social cognition and social learning in children and primates, succinctly and clearly introduces the major points of his theory and his views on the origins of language in the initial chapters. In subsequent chapters, he delves into the details by covering most language acquisition domains, namely, word (lexical) learning, syntax, and morphology and conversation, narrative, and extended discourse. Although one of the remaining domains (pragmatics) is at the core of his theory and permeates the text throughout, the relative paucity of passages explicitly devoted to discussing acquisition and proBOOK REVIEWS

Constructing a language: A usage-based theory of language acquisition

Language and the Internet

The Stanford typed dependencies representation was designed to provide a simple description of the grammatical relationships in a sentence that can easily be understood and effectively used by people without linguistic expertise who want to extract textual relations. In particular, rather than the phrase structure representations that have long dominated in the computational linguistic community, it represents all sentence relationships uniformly as typed dependency relations. That is, as triples of a relation between pairs of words, such as “the subject of distributes is Bell.” Our experience is that this simple, uniform representation is quite accessible to non-linguists thinking about tasks involving information extraction from text and is quite effective in relation extraction applications. Here is an example sentence:

/pdf/stanford-typed-dependencies-manual-2lwrx08xq4.pdf

Stanford typed dependencies manual

Geolocation prediction is vital to geospatial applications like localised search and local event detection. Predominately, social media geolocation models are based on full text data, including common words with no geospatial dimension (e.g. today) and noisy strings (tmrw), potentially hampering prediction and leading to slower/more memory-intensive models. In this paper, we focus on finding location indicative words (LIWs) via feature selection, and establishing whether the reduced feature set boosts geolocation accuracy. Our results show that an information gain ratiobased approach surpasses other methods at LIW selection, outperforming state-of-the-art geolocation prediction methods by 10.6% in accuracy and reducing the mean and median of prediction error distance by 45km and 209km, respectively, on a public dataset. We further formulate notions of prediction confidence, and demonstrate that performance is even higher in cases where our model is more confident, striking a trade-off between accuracy and coverage. Finally, the identified LIWs reveal regional language differences, which could be potentially useful for lexicographers.

/pdf/geolocation-prediction-in-social-media-data-by-finding-2h77ndhwii.pdf

Geolocation Prediction in Social Media Data by Finding Location Indicative Words

Twitter provides access to large volumes of data in real time, but is notoriously noisy, hampering its utility for NLP. In this article, we target out-of-vocabulary words in short text messages and propose a method for identifying and normalizing lexical variants. Our method uses a classifier to detect lexical variants, and generates correction candidates based on morphophonemic similarity. Both word similarity and context are then exploited to select the most probable correction candidate for the word. The proposed method doesn't require any annotations, and achieves state-of-the-art performance over an SMS corpus and a novel dataset based on Twitter.

Lexical normalization for social media text

We apply topic modelling to automatically induce word senses of a target word, and demonstrate that our word sense induction method can be used to automatically detect words with emergent novel senses, as well as token occurrences of those senses. We start by exploring the utility of standard topic models for word sense induction (WSI), with a pre-determined number of topics (=senses). We next demonstrate that a non-parametric formulation that learns an appropriate number of senses per word actually performs better at the WSI task. We go on to establish state-of-the-art results over two WSI datasets, and apply the proposed model to a novel sense detection task.

/pdf/word-sense-induction-for-novel-sense-detection-jfmbjbmuqn.pdf

Word Sense Induction for Novel Sense Detection

Cell phone text messaging users express themselves briefly and colloquially using a variety of creative forms. We analyze a sample of creative, non-standard text message word forms to determine frequent word formation processes in texting language. Drawing on these observations, we construct an unsupervised noisy-channel model for text message normalization. On a test set of 303 text message forms that differ from their standard form, our model achieves 59% accuracy, which is on par with the best supervised results reported on this dataset.

/pdf/an-unsupervised-model-for-text-message-normalization-18upvq63zx.pdf

An Unsupervised Model for Text Message Normalization

This paper presents the first attempt to use word embeddings to predict the compositionality of multiword expressions. We consider both single- and multi-prototype word embeddings. Experimental results show that, in combination with a back-off method based on string similarity, word embeddings outperform a method using count-based distributional similarity. Our best results are competitive with, or superior to, state-of-the-art methods over three standard compositionality datasets, which include two types of multiword expressions and two languages.

/pdf/a-word-embedding-approach-to-predicting-the-compositionality-2e2rolcm7i.pdf

Paul Cook

Papers

Geolocation Prediction in Social Media Data by Finding Location Indicative Words

Lexical normalization for social media text

Word Sense Induction for Novel Sense Detection

An Unsupervised Model for Text Message Normalization

A Word Embedding Approach to Predicting the Compositionality of Multiword Expressions