Search Results for author: Shammur Absar Chowdhury

Found 21 papers, 5 papers with code

Improving Arabic Text Categorization Using Transformer Training Diversification

1 code implementation COLING (WANLP) 2020 Shammur Absar Chowdhury, Ahmed Abdelali, Kareem Darwish, Jung Soon-Gyo, Joni Salminen, Bernard J. Jansen

Automatic categorization of short texts, such as news headlines and social media posts, has many applications ranging from content analysis to recommendation systems.

Recommendation Systems Text Categorization

SpeechBlender: Speech Augmentation Framework for Mispronunciation Data Generation

no code implementations2 Nov 2022 Yassine El Kheir, Shammur Absar Chowdhury, Hamdy Mubarak, Shazia Afzal, Ahmed Ali

With SpeechBlender augmentation, we observed a 3% and 2% increase in Pearson correlation coefficient (PCC) compared to no-augmentation and goodness of pronunciation augmentation scenarios respectively for Speechocean762 testset.

Data Augmentation Multi-Task Learning

ArabGend: Gender Analysis and Inference on Arabic Twitter

no code implementations COLING (WNUT) 2022 Hamdy Mubarak, Shammur Absar Chowdhury, Firoj Alam

Gender analysis of Twitter can reveal important socio-cultural differences between male and female users.

Emojis as Anchors to Detect Arabic Offensive Language and Hate Speech

no code implementations18 Jan 2022 Hamdy Mubarak, Sabit Hassan, Shammur Absar Chowdhury

We evaluate our models on external datasets - a Twitter dataset collected using a completely different method, and a multi-platform dataset containing comments from Twitter, YouTube and Facebook, for assessing generalization capability.

Textual Data Augmentation for Arabic-English Code-Switching Speech Recognition

no code implementations7 Jan 2022 Amir Hussein, Shammur Absar Chowdhury, Ahmed Abdelali, Najim Dehak, Ahmed Ali, Sanjeev Khudanpur

The pervasiveness of intra-utterance code-switching (CS) in spoken content requires that speech recognition (ASR) systems handle mixed language.

Language Modelling speech-recognition +4

A Review of Bangla Natural Language Processing Tasks and the Utility of Transformer Models

1 code implementation8 Jul 2021 Firoj Alam, Arid Hasan, Tanvirul Alam, Akib Khan, Janntatul Tajrin, Naira Khan, Shammur Absar Chowdhury

In this study, we first provide a review of Bangla NLP tasks, resources, and tools available to the research community; we benchmark datasets collected from various platforms for nine NLP tasks using current state-of-the-art algorithms (i. e., transformer-based models).

What do End-to-End Speech Models Learn about Speaker, Language and Channel Information? A Layer-wise and Neuron-level Analysis

no code implementations1 Jul 2021 Shammur Absar Chowdhury, Nadir Durrani, Ahmed Ali

Our results reveal: (i) channel and gender information is omnipresent and is redundantly distributed (ii) complex properties such as dialectal information is encoded only in the task-oriented pretrained network and is localised in the upper layers (iii) a minimal subset of neurons can be extracted to encode the predefined property (iv) salient neurons are sometimes shared between properties and can highlights presence of biases in the network.

Decision Making Dialect Identification +2

Towards One Model to Rule All: Multilingual Strategy for Dialectal Code-Switching Arabic ASR

no code implementations31 May 2021 Shammur Absar Chowdhury, Amir Hussein, Ahmed Abdelali, Ahmed Ali

We evaluate the system performance handling: (i) monolingual (Ar, En and Fr); (ii) multi-dialectal (Modern Standard Arabic, along with dialectal variation such as Egyptian and Moroccan); (iii) code-switching -- cross-lingual (Ar-En/Fr) and dialectal (MSA-Egyptian dialect) test cases, and compare with current state-of-the-art systems.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Sentiment Classification in Bangla Textual Content: A Comparative Study

1 code implementation19 Nov 2020 Md. Arid Hasan, Jannatul Tajrin, Shammur Absar Chowdhury, Firoj Alam

In this study, we explore several publicly available sentiment labeled datasets and designed classifiers using both classical and deep learning algorithms.

Classification General Classification +2

An LSTM Adaptation Study of (Un)grammaticality

1 code implementation WS 2019 Shammur Absar Chowdhury, Roberto Zamparelli

We propose a novel approach to the study of how artificial neural network perceive the distinction between grammatical and ungrammatical sentences, a crucial task in the growing field of synthetic linguistics.

CoLA Language Modelling

RNN Simulations of Grammaticality Judgments on Long-distance Dependencies

1 code implementation COLING 2018 Shammur Absar Chowdhury, Roberto Zamparelli

The paper explores the ability of LSTM networks trained on a language modeling task to detect linguistic structures which are ungrammatical due to extraction violations (extra arguments and subject-relative clause island violations), and considers its implications for the debate on language innatism.

Language Modelling

Depression Severity Estimation from Multiple Modalities

no code implementations10 Nov 2017 Evgeny Stepanov, Stephane Lathuiliere, Shammur Absar Chowdhury, Arindam Ghosh, Radu-Laurentiu Vieriu, Nicu Sebe, Giuseppe Riccardi

In this AVEC challenge we explore different modalities (speech, language and visual features extracted from face) to design and develop automatic methods for the detection of depression.

Functions of Silences towards Information Flow in Spoken Conversation

no code implementations WS 2017 Shammur Absar Chowdhury, Evgeny Stepanov, Morena Danieli, Giuseppe Riccardi

It is also observed that sometimes long silences can be used deliberately to get a forced response from another speaker thus making silence a multi-functional and an important catalyst towards information flow.

How Interlocutors Coordinate with each other within Emotional Segments?

no code implementations COLING 2016 Firoj Alam, Shammur Absar Chowdhury, Morena Danieli, Giuseppe Riccardi

In this paper, we aim to investigate the coordination of interlocutors behavior in different emotional segments.

Transfer of Corpus-Specific Dialogue Act Annotation to ISO Standard: Is it worth it?

no code implementations LREC 2016 Shammur Absar Chowdhury, Evgeny Stepanov, Giuseppe Riccardi

In this paper we test the utility of the ISO standard through comparative evaluation of the corpus-specific legacy and the semi-automatically transferred DiAML DA annotations on supervised dialogue act classification task.

Classification Dialogue Act Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.