Ngoc Thang Vu

Neural-based Noise Filtering from Word Embeddings

2016 · arXiv (Cornell University)

Word embeddings have been demonstrated to benefit NLP tasks impressively. Yet, there is room for improvement in the vector representations, because current word embeddings typically contain unnecessary information, i.e., noise. We propose two novel models …

BPE vs. Morphological Segmentation: A Case Study on Machine Translation of Four Polysynthetic Languages

2022 · Findings of the Association for Computational Linguistics: ACL 2022

Morphologically-rich polysynthetic languages present a challenge for NLP systems due to data sparsity, and a common strategy to handle this issue is to apply subword segmentation. We investigate a wide variety of supervised and unsupervised …

Neural-based Context Representation Learning for Dialog Act\n Classification

2017 · arXiv (Cornell University)

We explore context representation learning methods in neural-based models for\ndialog act classification. We propose and compare extensively different methods\nwhich combine recurrent neural network architectures and attention mechanisms\n(AMs) at different context levels. Our experimental results on …

Improving Semi-supervised End-to-end Automatic Speech Recognition using CycleGAN and Inter-domain Losses

2022 · arXiv (Cornell University)

We propose a novel method that combines CycleGAN and inter-domain losses for semi-supervised end-to-end automatic speech recognition. Inter-domain loss targets the extraction of an intermediate shared representation of speech and text inputs using a shared …

Neighboring Words Affect Human Interpretation of Saliency Explanations

2023 · arXiv (Cornell University)

Word-level saliency explanations ("heat maps over words") are often used to communicate feature-attribution in text-based models. Recent studies found that superficial factors such as word length can distort human interpretation of the communicated saliency scores. …

DIAGRAPH: An Open-Source Graphic Interface for Dialog Flow Design

2023

In this work, we present DIAGRAPH, an open-source graphical dialog flow editor built on the ADVISER toolkit. Our goal for this tool is threefold: 1) To support subject-experts to intuitively create complex and flexible dialog …

Ethical Considerations for Machine Translation of Indigenous Languages: Giving a Voice to the Speakers

2023

In recent years machine translation has become very successful for high-resource language pairs. This has also sparked new interest in research on the automatic translation of low-resource languages, including Indigenous languages. However, the latter are …

Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training

2024 · arXiv (Cornell University)

Recent advancements in language modeling have led to the emergence of Large Language Models (LLMs) capable of various natural language processing tasks. Despite their success in text-based tasks, applying LLMs to the speech domain remains …