Related papers: Analysing Zero-Shot Readability-Controlled Sentenc…

Well structured and readable source code is a pre-requisite for maintainable software and successful collaboration among developers. Static analysis enables the automated extraction of code complexity and readability metrics which can be…

Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks. In-Context Learning (ICL) typically achieves better accuracy than the 0-shot setting, but it pays in terms of…

Consensus maximisation learning can provide self-supervision when different views are available of the same data. The distributional hypothesis provides another form of useful self-supervision from adjacent sentences which are plentiful in…

Given a piece of speech and its transcript text, text-based speech editing aims to generate speech that can be seamlessly inserted into the given speech by editing the transcript. Existing methods adopt a two-stage approach: synthesize the…

When pre-trained on large unsupervised textual corpora, language models are able to store and retrieve factual knowledge to some extent, making it possible to use them directly for zero-shot cloze-style question answering. However, storing…

Leveraging multilingual parallel texts to automatically generate paraphrases has drawn much attention as size of high-quality paraphrase corpus is limited. Round-trip translation, also known as the pivoting method, is a typical approach to…

This paper proposes an approach to cross-language sentence selection in a low-resource setting. It uses data augmentation and negative sampling techniques on noisy parallel sentence data to directly learn a cross-lingual embedding-based…

Existing Large Language Model (LLM) based autoregressive (AR) text-to-speech (TTS) systems, while achieving state-of-the-art quality, still face critical challenges. The foundation of this LLM-based paradigm is the discretization of the…

The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters. To improve the decoding…

Zero-shot LLMs are now also used for textual classification tasks, e.g., sentiment and bias detection in a sentence or article. However, their performance can be suboptimal in such data annotation tasks. We introduce a novel technique that…

We explore the use of large language models (LLMs) for zero-shot semantic parsing. Semantic parsing involves mapping natural language utterances to task-specific meaning representations. Language models are generally trained on the publicly…

Controllable image captioning models generate human-like image descriptions, enabling some kind of control over the generated captions. This paper focuses on controlling the caption length, i.e. a short and concise description or a long and…

Large language models (LLMs) and high-capacity encoders have advanced zero and few-shot classification, but their inference cost and latency limit practical deployment. We propose training lightweight text classifiers using dynamically…

Text-to-speech (TTS) systems that scale up the amount of training data have achieved significant improvements in zero-shot speech synthesis. However, these systems have certain limitations: they require a large amount of training data,…

Given a document in a source language, cross-lingual summarization (CLS) aims at generating a concise summary in a different target language. Unlike monolingual summarization (MS), naturally occurring source-language documents paired with…

Test-time scaling (TTS) has enhanced the performance of Reasoning Models (RMs) on various tasks such as math and coding, yet its efficacy in machine translation (MT) remains underexplored. This paper investigates whether increased…

Short-utterance speaker verification presents significant challenges due to the limited information in brief speech segments, which can undermine accuracy and reliability. Recently, zero-shot text-to-speech (ZS-TTS) systems have made…

Large Language Models (LLMs) have demonstrated potential in predicting mental health outcomes from online text, yet traditional classification methods often lack interpretability and robustness. This study evaluates structured reasoning…

While Large Language Models (LLMs) exhibit remarkable capabilities in zero-shot and few-shot scenarios, they often require computationally prohibitive sizes. Conversely, smaller Masked Language Models (MLMs) like BERT and RoBERTa achieve…

Text attribute transfer aims to automatically rewrite sentences such that they possess certain linguistic attributes, while simultaneously preserving their semantic content. This task remains challenging due to a lack of supervised parallel…