Related papers: Improving Spoken Language Identification with Map-…

A fundamental problem in robotic perception is matching identical objects or data, with applications such as loop closure detection, place recognition, object tracking, and map fusion. While the problem becomes considerably more challenging…

Fine-tuning a pre-trained language model via the contrastive learning framework with a large amount of unlabeled sentences or labeled sentence pairs is a common way to obtain high-quality sentence representations. Although the contrastive…

In language model training, it is desirable to equip models with capabilities from various tasks. However, it is not clear how to directly obtain the right data mixtures for these capabilities as the relationship between data and tasks is…

Data augmentation with mixup has shown to be effective on various computer vision tasks. Despite its great success, there has been a hurdle to apply mixup to NLP tasks since text consists of discrete tokens with variable length. In this…

In this paper, we aim to unveil the impact of data augmentation in audio-language multi-modal learning, which has not been explored despite its importance. We explore various augmentation methods at not only train-time but also test-time…

Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. Oftentimes fine-tuned models are readily available but their training data is not, due to data privacy or intellectual property…

Labeled audio data is insufficient to build satisfying speech recognition systems for most of the languages in the world. There have been some zero-resource methods trying to perform phoneme or word-level speech recognition without labeled…

Reasoning capabilities are crucial for Large Language Models (LLMs), yet a notable gap exists between English and non-English languages. To bridge this disparity, some works fine-tune LLMs to relearn reasoning capabilities in non-English…

We propose a novel framework for filtering image-text data by leveraging fine-tuned Multimodal Language Models (MLMs). Our approach outperforms predominant filtering methods (e.g., CLIPScore) via integrating the recent advances in MLMs. We…

Multimodal Person Reidentification is gaining popularity in the research community due to its effectiveness compared to counter-part unimodal frameworks. However, the bottleneck for multimodal deep learning is the need for a large volume of…

Multilingual training is effective in improving low-resource ASR, which may partially be explained by phonetic representation sharing between languages. In end-to-end (E2E) ASR systems, graphemes are often used as basic modeling units,…

In recent years, the use of large language models (LLMs) for text classification has attracted widespread attention. Despite this, the classification accuracy of LLMs has not yet universally surpassed that of smaller models. LLMs can…

Large language models (LLMs) are demonstrating significant promise as an alternate strategy to facilitate analyses and optimizations of high-performance computing programs, circumventing the need for resource-intensive manual tool creation.…

In this study we address the problem of training a neuralnetwork for language identification using both labeled and unlabeled speech samples in the form of i-vectors. We propose a neural network architecture that can also handle out-of-set…

The problem of data sparsity has long been a challenge in recommendation systems, and previous studies have attempted to address this issue by incorporating side information. However, this approach often introduces side effects such as…

Mixup is an effective data augmentation method that generates new augmented samples by aggregating linear combinations of different original samples. However, if there are noises or aberrant features in the original samples, Mixup may…

A common problem for automatic speech recognition systems is how to recognize words that they did not see during training. Currently there is no established method of evaluating different techniques for tackling this problem. We propose…

Rare word recognition can be improved by adapting ASR models to synthetic data that includes these words. Further improvements can be achieved through contextual biasing, which trains and adds a biasing module into the model architecture to…

Inspired by the great success of Deep Neural Networks (DNNs) in natural language processing (NLP), DNNs have been increasingly applied in source code analysis and attracted significant attention from the software engineering community. Due…

The performance of large language models (LLMs) is significantly affected by the quality and composition of their pre-training data, which is inherently diverse, spanning various languages, sources, and topics. Effectively integrating these…