Related papers: DialectGen: Benchmarking and Improving Dialect Rob…
Spoken Grammatical Error Correction (SGEC) and Feedback (SGECF) are crucial for second language learners, teachers and test takers. Traditional SGEC systems rely on a cascaded pipeline consisting of an ASR, a module for disfluency detection…
Unsupervised speech representation learning has shown remarkable success at finding representations that correlate with phonetic structures and improve downstream speech recognition performance. However, most research has been focused on…
Recent research has highlighted the risk of generative model collapse, where performance progressively degrades when continually trained on self-generated data. However, existing exploration on model collapse is limited to single, unimodal…
Despite advancements in English-dominant generative large language models, further development is needed for low-resource languages to enhance global accessibility. The primary methods for representing these languages are monolingual and…
Speech enhancement (SE) improves degraded speech's quality, with generative models like flow matching gaining attention for their outstanding perceptual quality. However, the flow-based model requires multiple numbers of function…
Neural machine translation (NMT) systems exhibit limited robustness in handling source-side linguistic variations. Their performance tends to degrade when faced with even slight deviations in language usage, such as different domains or…
Recent prompt optimisation approaches use the generative nature of language models to produce prompts -- even rivaling the performance of human-curated prompts. In this paper, we demonstrate that randomly sampling tokens from the model…
Deep neural models, in particular Transformer-based pre-trained language models, require a significant amount of data to train. This need for data tends to lead to problems when dealing with idiomatic multiword expressions (MWEs), which are…
Synthetic data has become a cornerstone for scaling large language models, yet its multilingual use remains bottlenecked by translation-based prompts. This strategy inherits English-centric framing and style and neglects cultural…
Recent work has shown that generation from a prompted or fine-tuned language model can perform well at semantic parsing when the output is constrained to be a valid semantic representation. We introduce BenchCLAMP, a Benchmark to evaluate…
Multi-modal data-sets are ubiquitous in modern applications, and multi-modal Variational Autoencoders are a popular family of models that aim to learn a joint representation of the different modalities. However, existing approaches suffer…
Singing voice synthesis (SVS) has advanced significantly, enabling models to generate vocals with accurate pitch and consistent style. As these capabilities improve, the need for reliable evaluation and optimization becomes increasingly…
The remarkable multimodal capabilities demonstrated by OpenAI's GPT-4 have sparked significant interest in the development of multimodal Large Language Models (LLMs). A primary research objective of such models is to align visual and…
The advent of large language models (LLMs) such as ChatGPT has attracted considerable attention in various domains due to their remarkable performance and versatility. As the use of these models continues to grow, the importance of…
How (dis)similar are the learning trajectories of vision-language models and children? Recent modeling work has attempted to understand the gap between models' and humans' data efficiency by constructing models trained on less data,…
The increasing capability of large language models (LLMs) to generate synthetic content has heightened concerns about their misuse, driving the development of Machine-Generated Text (MGT) detection models. However, these detectors face…
In recent years, Large Language Models (LLMs) have demonstrated remarkable proficiency in comprehending and generating natural language, with a growing prevalence in the domain of recommendation systems. However, LLMs still face a…
Evaluating text generation capabilities of large language models (LLMs) is challenging, particularly for low-resource languages where methods for direct assessment are scarce. We propose MUG-Eval, a novel framework that evaluates LLMs'…
Multiple modalities often co-occur when describing natural phenomena. Learning a joint representation of these modalities should yield deeper and more useful representations. Previous generative approaches to multi-modal input either do not…
Existing knowledge-grounded dialogue systems typically use finetuned versions of a pretrained language model (LM) and large-scale knowledge bases. These models typically fail to generalize on topics outside of the knowledge base, and…