Related papers: Building a Word Segmenter for Sanskrit Overnight

Deep Learning techniques are powerful in mimicking humans in a particular set of problems. They have achieved a remarkable performance in complex learning tasks. Deep learning inspired Neural Machine Translation (NMT) is a proficient…

As text generative models can give increasingly long answers, we tackle the problem of synthesizing long text in digital ink. We show that the commonly used models for this task fail to generalize to long-form data and how this problem can…

Tokenization is the act of breaking down text into smaller parts, or tokens, that are easier for machines to process. This is a key phase in machine translation (MT) models. Subword tokenization enhances this process by breaking down words…

A wide variety of neural-network architectures have been proposed for the task of Chinese word segmentation. Surprisingly, we find that a bidirectional LSTM model, when combined with standard deep learning techniques and best practices, can…

Despite being the seventh most widely spoken language in the world, Bengali has received much less attention in machine translation literature due to being low in resources. Most publicly available parallel corpora for Bengali are not large…

Text segmentation aims to divide text into contiguous, semantically coherent segments, while segment labeling deals with producing labels for each segment. Past work has shown success in tackling segmentation and labeling for documents and…

Structured State Spaces for Sequences (S4) is a recently proposed sequence model with successful applications in various tasks, e.g. vision, language modeling, and audio. Thanks to its mathematical formulation, it compresses its input to a…

Pretrained, large, generative language models (LMs) have had great success in a wide range of sequence tagging and structured prediction tasks. Casting a sequence tagging task as a Seq2Seq one requires deciding the formats of the input and…

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are…

Improving the performance of end-to-end ASR models on long utterances ranging from minutes to hours in length is an ongoing challenge in speech recognition. A common solution is to segment the audio in advance using a separate voice…

This paper proposes a transformer over transformer framework, called Transformer$^2$, to perform neural text segmentation. It consists of two components: bottom-level sentence encoders using pre-trained transformers, and an upper-level…

Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite…

Due to the high impact of the fast-evolving fields of machine learning and deep learning, Natural Language Processing (NLP) tasks have further obtained comprehensive performances for highly resourced languages such as English and Chinese.…

In the cascaded approach to spoken language translation (SLT), the ASR output is typically punctuated and segmented into sentences before being passed to MT, since the latter is typically trained on written text. However, erroneous…

In natural speech, the speaker does not pause between words, yet a human listener somehow perceives this continuous stream of phonemes as a series of distinct words. The detection of boundaries between spoken words is an instance of a…

The performance of a text-to-speech (TTS) synthesis model depends on various factors, of which the quality of the training data is of utmost importance. Millions of data are collected around the globe for various languages, but resources…

The success of deep learning in natural language processing raises intriguing questions about the nature of linguistic meaning and ways in which it can be processed by natural and artificial systems. One such question has to do with subword…

Rapidly developed neural models have achieved competitive performance in Chinese word segmentation (CWS) as their traditional counterparts. However, most of methods encounter the computational inefficiency especially for long sentences…

Previous attempts at RST-style discourse segmentation typically adopt features centered on a single token to predict whether to insert a boundary before that token. In contrast, we develop a discourse segmenter utilizing a set of pairing…

Building large-scale datasets for training code-switching language models is challenging and very expensive. To alleviate this problem using parallel corpus has been a major workaround. However, existing solutions use linguistic constraints…