Related papers: A Case Against Implicit Standards: Homophone Norma…

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,…

In this work, we address the problem of assessing and constructing feedback for early-stage writing automatically using machine learning. Early-stage writing is typically vastly different from conventional writing due to phonetic spelling…

With increasing globalization and immigration, various studies have estimated that about half of the world population is bilingual. Consequently, individuals concurrently use two or more languages or dialects in casual conversational…

Popular Neural Machine Translation model training uses strategies like backtranslation to improve BLEU scores, requiring large amounts of additional data and training. We introduce a class of conditional generative-discriminative hybrid…

Semi-supervised learning lately has shown much promise in improving deep learning models when labeled data is scarce. Common among recent approaches is the use of consistency training on a large amount of unlabeled data to constrain model…

Formality style transfer is the task of converting informal sentences to grammatically-correct formal sentences, which can be used to improve performance of many downstream NLP tasks. In this work, we propose a semi-supervised formality…

Cross-lingual word embeddings (CLWE) underlie many multilingual natural language processing systems, often through orthogonal transformations of pre-trained monolingual embeddings. However, orthogonal mapping only works on language pairs…

Recent advancements in large language models have demonstrated that extended inference through techniques can markedly improve performance, yet these gains come with increased computational costs and the propagation of inherent biases found…

We perform text normalization, i.e. the transformation of words from the written to the spoken form, using a memory augmented neural network. With the addition of dynamic memory access and storage mechanism, we present a neural architecture…

In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings. Self-supervised pre-training…

Historic variations of spelling poses a challenge for full-text search or natural language processing on historical digitized texts. To minimize the gap between the historic orthography and contemporary spelling, usually an automatic…

Text normalization is an essential preprocessing step in many natural language processing (NLP) tasks, and stemming is one such normalization technique that reduces words to their base or root form. However, evaluating stemming methods is…

Large language models (LLMs) have revolutionized natural language processing (NLP) tasks by achieving state-of-the-art performance across a range of benchmarks. Central to the success of these models is the integration of sophisticated…

Automatic text-based diacritic restoration models generally have high diacritic error rates when applied to speech transcripts as a result of domain and style shifts in spoken language. In this work, we explore the possibility of improving…

The field of machine translation faces an under-recognized problem because of inconsistency in the reporting of scores from its dominant metric. Although people refer to "the" BLEU score, BLEU is in fact a parameterized metric whose values…

Can pre-trained BERT for one language and GPT for another be glued together to translate texts? Self-supervised training using only monolingual data has led to the success of pre-trained (masked) language models in many NLP tasks. However,…

Social media data is a valuable resource for research, yet it contains a wide range of non-standard words (NSW). These irregularities hinder the effective operation of NLP tools. Current state-of-the-art methods for the Vietnamese language…

The capacity and effectiveness of pre-trained multilingual models (MLMs) for zero-shot cross-lingual transfer is well established. However, phenomena of positive or negative transfer, and the effect of language choice still need to be fully…

The cost of annotating transcriptions for large speech corpora becomes a bottleneck to maximally enjoy the potential capacity of deep neural network-based automatic speech recognition models. In this paper, we present a new training…

Capitalization normalization (truecasing) is the task of restoring the correct case (uppercase or lowercase) of noisy text. We propose a fast, accurate and compact two-level hierarchical word-and-character-based recurrent neural network…