Punctuation restoration using transformer models for high-and low-resource languages
Punctuation restoration is a common post-processing problem for Automatic Speech
Recognition (ASR) systems. It is important to improve the readability of the transcribed text …
Recognition (ASR) systems. It is important to improve the readability of the transcribed text …
A review of bangla natural language processing tasks and the utility of transformer models
Bangla--ranked as the 6th most widely spoken language across the world (https://www.
ethnologue. com/guides/ethnologue200), with 230 million native speakers--is still …
ethnologue. com/guides/ethnologue200), with 230 million native speakers--is still …
Capitalization and punctuation restoration: a survey
Ensuring proper punctuation and letter casing is a key pre-processing step towards applying
complex natural language processing algorithms. This is especially significant for textual …
complex natural language processing algorithms. This is especially significant for textual …
Efficient automatic punctuation restoration using bidirectional transformers with robust inference
M Courtland, A Faulkner… - Proceedings of the 17th …, 2020 - aclanthology.org
Though people rarely speak in complete sentences, punctuation confers many benefits to
the readers of transcribed speech. Unfortunately, most ASR systems do not produce …
the readers of transcribed speech. Unfortunately, most ASR systems do not produce …
Adversarial transfer learning for punctuation restoration
Previous studies demonstrate that word embeddings and part-of-speech (POS) tags are
helpful for punctuation restoration tasks. However, two drawbacks still exist. One is that word …
helpful for punctuation restoration tasks. However, two drawbacks still exist. One is that word …
Automatic punctuation restoration with bert models
We present an approach for automatic punctuation restoration with BERT models for English
and Hungarian. For English, we conduct our experiments on Ted Talks, a commonly used …
and Hungarian. For English, we conduct our experiments on Ted Talks, a commonly used …
Token-level supervised contrastive learning for punctuation restoration
Punctuation is critical in understanding natural language text. Currently, most automatic
speech recognition (ASR) systems do not generate punctuation, which affects the …
speech recognition (ASR) systems do not generate punctuation, which affects the …
[PDF][PDF] Focal Loss for Punctuation Prediction.
Many approaches have been proposed to predict punctuation marks. Previous results
demonstrate that these methods are effective. However, there still exists class imbalance …
demonstrate that these methods are effective. However, there still exists class imbalance …
Towards better subtitles: A multilingual approach for punctuation restoration of speech transcripts
This paper proposes a flexible approach for punctuation prediction that can be used to
produce state-of-the-art results in a multilingual scenario. We have performed experiments …
produce state-of-the-art results in a multilingual scenario. We have performed experiments …
Boosting punctuation restoration with data generation and reinforcement learning
Punctuation restoration is an important task in automatic speech recognition (ASR) which
aim to restore the syntactic structure of generated ASR texts to improve readability. While …
aim to restore the syntactic structure of generated ASR texts to improve readability. While …