Related papers: mHuBERT-147: A Compact Multilingual HuBERT Model
Hope speech language that fosters encouragement and optimism plays a vital role in promoting positive discourse online. However, its detection remains challenging, especially in multilingual and low-resource settings. This paper presents a…
Multilingual large language models (LLMs) are advancing rapidly, with new models frequently claiming support for an increasing number of languages. However, existing evaluation datasets are limited and lack cross-lingual alignment, leaving…
Human infants, with only a few hundred hours of speech exposure, acquire basic units of new languages, highlighting a striking efficiency gap compared to the data-hungry self-supervised speech models. To address this gap, this paper…
Lately, pre-trained language models advanced the field of natural language processing (NLP). The introduction of Bidirectional Encoders for Transformers (BERT) and its optimized version RoBERTa have had significant impact and increased the…
Reliable automatic evaluation of summarization systems is challenging due to the multifaceted and subjective nature of the task. This is especially the case for languages other than English, where human evaluations are scarce. In this work,…
Scaling semantic parsing models for task-oriented dialog systems to new languages is often expensive and time-consuming due to the lack of available datasets. Available datasets suffer from several shortcomings: a) they contain few…
State-of-the-art neural retrievers predominantly focus on high-resource languages like English, which impedes their adoption in retrieval scenarios involving other languages. Current approaches circumvent the lack of high-quality labeled…
Large-scale generative language models such as GPT-3 are competitive few-shot learners. While these models are known to be able to jointly represent many different languages, their training data is dominated by English, potentially limiting…
Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with only a few examples or simple instructions. GPT-3 has shown…
Building ASR models across many languages is a challenging multi-task learning problem due to large variations and heavily unbalanced data. Existing work has shown positive transfer from high resource to low resource languages. However,…
The automated classification of stuttered speech has significant implications for timely assessments providing assistance to speech language pathologists. Despite notable advancements in the field, the cases in which multiple disfluencies…
Reward models (RMs) have driven the state-of-the-art performance of LLMs today by enabling the integration of human feedback into the language modeling process. However, RMs are primarily trained and evaluated in English, and their…
Code-switching, or alternating between languages within a single conversation, presents challenges for multilingual language models on NLP tasks. This research investigates if pre-training Multilingual BERT (mBERT) on code-switched datasets…
We present our journey in training a speech language model for Wolof, an underrepresented language spoken in West Africa, and share key insights. We first emphasize the importance of collecting large-scale, spontaneous, high-quality…
While various end-to-end models for spoken language understanding tasks have been explored recently, this paper is probably the first known attempt to challenge the very difficult task of end-to-end spoken question answering (SQA). Learning…
BERT is inefficient for sentence-pair tasks such as clustering or semantic search as it needs to evaluate combinatorially many sentence pairs which is very time-consuming. Sentence BERT (SBERT) attempted to solve this challenge by learning…
Training state-of-the-art large language models requires vast amounts of clean and diverse textual data. However, building suitable multilingual datasets remains a challenge. In this work, we present HPLT v2, a collection of high-quality…
Large Language models (LLMs) have demonstrated impressive performance on a wide range of tasks, including in multimodal settings such as speech. However, their evaluation is often limited to English and a few high-resource languages. For…
While pretrained language models (PLMs) primarily serve as general-purpose text encoders that can be fine-tuned for a wide variety of downstream tasks, recent work has shown that they can also be rewired to produce high-quality word…
Multimodal Large Language Models (MLLMs) have achieved significant success in Speech-to-Text Translation (S2TT) tasks. While most existing research has focused on English-centric translation directions, the exploration of many-to-many…