Related papers: Pointer over Attention: An Improved Bangla Text Su…
Text-to-Speech (TTS) system is a system where speech is synthesized from a given text following any particular approach. Concatenative synthesis, Hidden Markov Model (HMM) based synthesis, Deep Learning (DL) based synthesis with multiple…
We describe an attentive encoder that combines tree-structured recursive neural networks and sequential recurrent neural networks for modelling sentence pairs. Since existing attentive models exert attention on the sequential structure, we…
Sentences produced by abstractive summarization systems can be ungrammatical and fail to preserve the original meanings, despite being locally fluent. In this paper we propose to remedy this problem by jointly generating a sentence and its…
This paper describes our system used in the BLP-2025 Task 1: Hate Speech Detection. We participated in Subtask 1A and Subtask 1B, addressing hate speech classification in Bangla text. Our approach employs a unified architecture that…
Summarization is a way to represent same information in concise way with equal sense. This can be categorized in two type Abstractive and Extractive type. Our work is focused around Extractive summarization. A generic approach to extractive…
Comment generation, a new and challenging task in Natural Language Generation (NLG), attracts a lot of attention in recent years. However, comments generated by previous work tend to lack pertinence and diversity. In this paper, we propose…
Bangla is the seventh most spoken language by a total number of speakers in the world, and yet the development of an automated grammar checker in this language is an understudied problem. Bangla grammatical error detection is a task of…
Interleaved texts, where posts belonging to different threads occur in one sequence, are a common occurrence, e.g., online chat conversations. To quickly obtain an overview of such texts, existing systems first disentangle the posts by…
Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention…
Transformer-based models have achieved state-of-the-art results in a wide range of natural language processing (NLP) tasks including document summarization. Typically these systems are trained by fine-tuning a large pre-trained model to the…
We propose a unified model combining the strength of extractive and abstractive summarization. On the one hand, a simple extractive model can obtain sentence-level attention with high ROUGE scores but less readable. On the other hand, a…
Most existing neural network based task-oriented dialogue systems follow encoder-decoder paradigm, where the decoder purely depends on the source texts to generate a sequence of words, usually suffering from instability and poor…
Is the output softmax layer, which is adopted by most language models (LMs), always the best way to compute the next word probability? Given so many attention layers in a modern transformer-based LM, are the pointer networks redundant…
The availability of a vast array of research papers in any area of study, necessitates the need of automated summarisation systems that can present the key research conducted and their corresponding findings. Scientific paper summarisation…
Code summarization aims to generate concise natural language descriptions for source code. The prevailing approaches adopt transformer-based encoder-decoder architectures, where the Abstract Syntax Tree (AST) of the source code is utilized…
Neural network-based approaches have become widespread for abstractive text summarization. Though previously proposed models for abstractive text summarization addressed the problem of repetition of the same contents in the summary, they…
Understanding linguistics and morphology of resource-scarce code-mixed texts remains a key challenge in text processing. Although word embedding comes in handy to support downstream tasks for low-resource languages, there are plenty of…
Generating images according to natural language descriptions is a challenging task. Prior research has mainly focused to enhance the quality of generation by investigating the use of spatial attention and/or textual attention thereby…
Recognition of handwritten Bangla compound characters remains a challenging problem due to complex character structures, large intra-class variation, and limited availability of high-quality annotated data. Existing Bangla handwritten…
The neural attention model has achieved great success in data-to-text generation tasks. Though usually excelling at producing fluent text, it suffers from the problem of information missing, repetition and "hallucination". Due to the…