Related papers: Unsupervised Pidgin Text Generation By Pivoting En…

This paper presents an accented text-to-speech (TTS) synthesis framework with limited training data. We study two aspects concerning accent rendering: phonetic (phoneme difference) and prosodic (pitch pattern and phoneme duration)…

Natural Language Processing (NLP) is increasingly used as a key ingredient in critical decision-making systems such as resume parsers used in sorting a list of job candidates. NLP systems often ingest large corpora of human text, attempting…

Generating coherent, grammatically correct, and meaningful text is very challenging, however, it is crucial to many modern NLP systems. So far, research has mostly focused on English language, for other languages both standardized datasets,…

This work aims to employ natural language generation (NLG) to rapidly generate items for English language learning applications: this requires both language models capable of generating fluent, high-quality English, and to control the…

Automatic question generation (QG) is a challenging problem in natural language understanding. QG systems are typically built assuming access to a large number of training instances where each instance is a question and its corresponding…

Generative models have gained more and more attention in recent years for their remarkable success in tasks that required estimating and sampling data distribution to generate high-fidelity synthetic data. In speech, text-to-speech…

Expressing natural language descriptions of structured facts or relations -- data-to-text generation (D2T) -- increases the accessibility of structured knowledge repositories. Previous work shows that pre-trained language models(PLMs)…

Previous work in phonetically-grounded language generation has mainly focused on domains such as lyrics and poetry. In this paper, we present work on the generation of tongue twisters - a form of language that is required to be phonetically…

Modern machine learning models for audio tasks often exhibit superior performance on English and other well-resourced languages, primarily due to the abundance of available training data. This disparity leads to an unfair performance gap…

Advances in speech and language technologies enable tools such as voice-search, text-to-speech, speech recognition and machine translation. These are however only available for high resource languages like English, French or Chinese.…

Large language models respond well in high-resource languages like English but struggle in low-resource languages. It may arise from the lack of high-quality instruction following data in these languages. Directly translating English…

The prevalence of social media presents a growing opportunity to collect and analyse examples of English varieties. Whilst usage of these varieties was - and, in many cases, still is - used only in spoken contexts or hard-to-access private…

Recent computational models of the acquisition of spoken language via grounding in perception exploit associations between the spoken and visual modalities and learn to represent speech and visual data in a joint vector space. A major…

Automated unit test generation is a well-known methodology aiming to reduce the developers' effort of writing tests manually. Prior research focused mainly on statically typed programming languages like Java. In practice, however,…

Recent progress in NLP is driven by pretrained models leveraging massive datasets and has predominantly benefited the world's political and economic superpowers. Technologically underserved languages are left behind because they lack such…

Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks. To address this issue, we propose an enhanced multi-flow sequence to sequence pre-training and fine-tuning…

Many text generation systems benefit from using a retriever to retrieve passages from a textual knowledge corpus (e.g., Wikipedia) which are then provided as additional context to the generator. For open-ended generation tasks (like…

LLMs like GPT are great at tasks involving English which dominates in their training data. In this paper, we look at how they cope with tasks involving languages that are severely under-represented in their training data, in the context of…

Code-mixing is a phenomenon of mixing words and phrases from two or more languages in a single utterance of speech and text. Due to the high linguistic diversity, code-mixing presents several challenges in evaluating standard natural…

Bilingual and multilingual language models offer a promising path toward scaling NLP systems across diverse languages and users. However, their performance often varies wildly between languages as prior works show that adding more languages…