Related papers: Unlabeled Data for Morphological Generation With C…

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…

Based on recent advances in natural language modeling and those in text generation capabilities, we propose a novel data augmentation method for text classification tasks. We use a powerful pre-trained neural network model to artificially…

We explore the task of multi-source morphological reinflection, which generalizes the standard, single-source version. The input consists of (i) a target tag and (ii) multiple pairs of source form and source tag for a lemma. The motivation…

Transformer neural networks require a large amount of labeled data to train effectively. Such data is often scarce in electroencephalography, as annotations made by medical experts are costly. This is why self-supervised training, using…

Speaker identification in the household scenario (e.g., for smart speakers) is typically based on only a few enrollment utterances but a much larger set of unlabeled data, suggesting semisupervised learning to improve speaker profiles. We…

Machine transliteration is the process of automatically transforming the script of a word from a source language to a target language, while preserving pronunciation. Sequence to sequence learning has recently emerged as a new paradigm in…

Publicly available, large pretrained LanguageModels (LMs) generate text with remarkable quality, but only sequentially from left to right. As a result, they are not immediately applicable to generation tasks that break the unidirectional…

Morpho-syntactic lexicons provide information about the morphological and syntactic roles of words in a language. Such lexicons are not available for all languages and even when available, their coverage can be limited. We present a…

We demonstrate that error correcting codes (ECCs) can be used to construct a labeled data set for finetuning of "trainable" communication systems without sacrificing resources for the transmission of known symbols. This enables adaptive…

Deep learning methods have advanced quickly in brain imaging analysis over the past few years, but they are usually restricted by the limited labeled data. Pre-trained model on unlabeled data has presented promising improvement in feature…

We experiment graph-based Semi-Supervised Learning (SSL) of Conditional Random Fields (CRF) for the application of Spoken Language Understanding (SLU) on unaligned data. The aligned labels for examples are obtained using IBM Model. We adapt…

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

We study the problem of automatically building hypernym taxonomies from textual and visual data. Previous works in taxonomy induction generally ignore the increasingly prominent visual data, which encode important perceptual semantics.…

Generative adversarial networks (GANs) have been remarkably successful in learning complex high dimensional real word distributions and generating realistic samples. However, they provide limited control over the generation process.…

Extreme classification tasks are multi-label tasks with an extremely large number of labels (tags). These tasks are hard because the label space is usually (i) very large, e.g. thousands or millions of labels, (ii) very sparse, i.e. very…

The predominant approach for language modeling is to process sequences from left to right, but this eliminates a source of information: the order by which the sequence was generated. One strategy to recover this information is to decode…

Current text classification methods typically require a good number of human-labeled documents as training data, which can be costly and difficult to obtain in real applications. Humans can perform classification without seeing any labeled…

We incorporate morphological supervision into character language models (CLMs) via multitasking and show that this addition improves bits-per-character (BPC) performance across 24 languages, even when the morphology data and language…

We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including: part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This…

We consider the problem of anomaly detection with a small set of partially labeled anomaly examples and a large-scale unlabeled dataset. This is a common scenario in many important applications. Existing related methods either exclusively…