Related papers: Synthetic Error Dataset Generation Mimicking Benga…
Progress in neural grammatical error correction (GEC) is hindered by the lack of annotated training data. Sufficient amounts of high-quality manually annotated data are not available, so recent research has relied on generating synthetic…
Word embedding or vector representation of word holds syntactical and semantic characteristics of a word which can be an informative feature for any machine learning-based models of natural language processing. There are several deep…
At present Automatic Speaker Recognition system is a very important issue due to its diverse applications. Hence, it becomes absolutely necessary to obtain models that take into consideration the speaking style of a person, vocal tract…
We describe our end-to-end system for Bengali long-form speech recognition (ASR) and speaker diarization submitted to the DL Sprint 4.0 competition on Kaggle. Bengali presents substantial challenges for both tasks: a large phoneme…
Scholars in the humanities rely heavily on ancient manuscripts to study history, religion, and socio-political structures in the past. Many efforts have been devoted to digitizing these precious manuscripts using OCR technology, but most…
The paper presents the capability of an HMM-based TTS system to produce Bengali speech. In this synthesis method, trajectories of speech parameters are generated from the trained Hidden Markov Models. A final speech waveform is synthesized…
The Bangla language includes many regional dialects, adding to its cultural richness. The translation of Bangla Language into regional dialects presents a challenge due to significant variations in vocabulary, pronunciation, and sentence…
Bengali is spoken by over 230 million people yet remains severely under-served in automatic speech recognition (ASR) and speaker diarization research. In this paper, we present our system for the DL Sprint 4.0 Bengali Long-Form Speech…
Automatic question generation is one of the most challenging tasks of Natural Language Processing. It requires "bidirectional" language processing: firstly, the system has to understand the input text (Natural Language Understanding) and it…
Despite being one of the most spoken languages in the world ($6^{th}$ based on population), research regarding Bengali handwritten grapheme (smallest functional unit of a writing system) classification has not been explored widely compared…
Code-switching (CSW) is a common phenomenon among multilingual speakers where multiple languages are used in a single discourse or utterance. Mixed language utterances may still contain grammatical errors however, yet most existing Grammar…
When learning grammar of the new language, a teacher should routinely check student's exercises for grammatical correctness. The paper describes a method of automatically detecting and reporting grammar mistakes, regarding an order of…
The Byte Pair Encoding algorithm can be safely batched to merge hundreds of pairs of tokens at a time when building up a tokenizer's vocabulary. This technique combined with reducing the memory footprint of text used in vocabulary training…
This paper presents a simple recipe to train state-of-the-art multilingual Grammatical Error Correction (GEC) models. We achieve this by first proposing a language-agnostic method to generate a large number of synthetic examples. The second…
Modern large language models often encode sensitive, harmful, or copyrighted knowledge, raising the need for post-hoc unlearning-the ability to remove specific domains of knowledge from a model without full retraining. A major bottleneck in…
Modern semantic parsers suffer from two principal limitations. First, training requires expensive collection of utterance-program pairs. Second, semantic parsers fail to generalize at test time to new compositions/structures that have not…
Generating coherent, grammatically correct, and meaningful text is very challenging, however, it is crucial to many modern NLP systems. So far, research has mostly focused on English language, for other languages both standardized datasets,…
Question answer generation using Natural Language Processing models is ubiquitous in the world around us. It is used in many use cases such as the building of chat bots, suggestive prompts in google search and also as a way of navigating…
Natural Language Inference is an important task for Natural Language Understanding. It is concerned with classifying the logical relation between two sentences. In this paper, we propose several text generative neural networks for…
In Sanskrit, small words (morphemes) are combined to form compound words through a process known as Sandhi. Sandhi splitting is the process of splitting a given compound word into its constituent morphemes. Although rules governing word…