Related papers: Weakly Supervised POS Taggers Perform Poorly on Tr…

This paper addresses the challenge of integrating low-resource languages into multilingual automatic speech recognition (ASR) systems. We introduce a novel application of weighted cross-entropy, typically used for unbalanced datasets, to…

We introduce an adaptive scheduling for adaptive sampling as a novel way of machine learning in the construction of part-of-speech taggers. The goal is to speed up the training on large data sets, without significant loss of performance…

Exploiting cognates for transfer learning in under-resourced languages is an exciting opportunity for language understanding tasks, including unsupervised machine translation, named entity recognition and information retrieval. Previous…

Data availability and quality are major challenges in natural language processing for low-resourced languages. In particular, there is significantly less data available than for higher-resourced languages. This data is also often of low…

In this work, we focus on low-resource dependency parsing for multiple languages. Several strategies are tailored to enhance performance in low-resource scenarios. While these are well-known to the community, it is not trivial to select the…

Cross-lingual speech adaptation aims to solve the problem of leveraging multiple rich-resource languages to build models for a low-resource target language. Since the low-resource language has limited training data, speech recognition…

Recent years have seen rapid development in Information Extraction, as well as its subtask, Relation Extraction. Relation Extraction is able to detect semantic relations between entities in sentences. Currently, many efficient approaches…

This paper discusses the problem of weakly supervised classification, in which instances are given weak labels that are produced by some label-corruption process. The goal is to derive conditions under which loss functions for weak-label…

Text-to-Speech (TTS) synthesis using deep learning relies on voice quality. Modern TTS models are advanced, but they need large amount of data. Given the growing computational complexity of these models and the scarcity of large,…

Transformer based architectures have shown notable results on many down streaming tasks including question answering. The availability of data, on the other hand, impedes obtaining legitimate performance for low-resource languages. In this…

Increasing attention is being diverted to data-efficient problem settings like Open Vocabulary Semantic Segmentation (OVSS) which deals with segmenting an arbitrary object that may or may not be seen during training. The closest standard…

PoS tags, once taken for granted as a useful resource for syntactic parsing, have become more situational with the popularization of deep learning. Recent work on the impact of PoS tags on graph- and transition-based parsers suggests that…

Translation into severely low-resource languages has both the cultural goal of saving and reviving those languages and the humanitarian goal of assisting the everyday needs of local communities that are accelerated by the recent COVID-19…

Despite advances in dependency parsing, languages with small treebanks still present challenges. We assess recent approaches to multilingual contextual word representations (CWRs), and compare them for crosslingual transfer from a language…

Weakly supervised learning is a popular approach for training machine learning models in low-resource settings. Instead of requesting high-quality yet costly human annotations, it allows training models with noisy annotations obtained from…

Natural language processing is heavily Anglo-centric, while the demand for models that work in languages other than English is greater than ever. Yet, the task of transferring a model from one language to another can be expensive in terms…

There are two main methodologies for constructing the knowledge base of a natural language analyser: the linguistic and the data-driven. Recent state-of-the-art part-of-speech taggers are based on the data-driven approach. Because of the…

This paper investigates very low resource language model pretraining, when less than 100 thousand sentences are available. We find that, in very low resource scenarios, statistical n-gram language models outperform state-of-the-art neural…

Existing weak supervision approaches use all the data covered by weak signals to train a classifier. We show both theoretically and empirically that this is not always optimal. Intuitively, there is a tradeoff between the amount of…

We present a survey covering the state of the art in low-resource machine translation research. There are currently around 7000 languages spoken in the world and almost all language pairs lack significant resources for training machine…