Search Results for author: Md Mahfuz ibn Alam

Found 11 papers, 6 papers with code

Fine-Tuning MT systems for Robustness to Second-Language Speaker Variations

1 code implementation EMNLP (WNUT) 2020 Md Mahfuz ibn Alam, Antonios Anastasopoulos

The performance of neural machine translation (NMT) systems only trained on a single language variant degrades when confronted with even slightly different language variations.

Machine Translation NMT +1

Language and Speech Technology for Central Kurdish Varieties

1 code implementation4 Mar 2024 Sina Ahmadi, Daban Q. Jaff, Md Mahfuz ibn Alam, Antonios Anastasopoulos

Kurdish, an Indo-European language spoken by over 30 million speakers, is considered a dialect continuum and known for its diversity in language varieties.

Automatic Speech Recognition Language Identification +3

A Morphologically-Aware Dictionary-based Data Augmentation Technique for Machine Translation of Under-Represented Languages

no code implementations2 Feb 2024 Md Mahfuz ibn Alam, Sina Ahmadi, Antonios Anastasopoulos

In this paper, we propose strategies to synthesize parallel data relying on morpho-syntactic information and using bilingual lexicons along with a small amount of seed parallel data.

Data Augmentation Machine Translation

A Case Study on Filtering for End-to-End Speech Translation

no code implementations2 Feb 2024 Md Mahfuz ibn Alam, Antonios Anastasopoulos

It is relatively easy to mine a large parallel corpus for any machine learning task, such as speech-to-text or speech-to-speech translation.

Speech-to-Speech Translation Translation

CODET: A Benchmark for Contrastive Dialectal Evaluation of Machine Translation

no code implementations26 May 2023 Md Mahfuz ibn Alam, Sina Ahmadi, Antonios Anastasopoulos

Neural machine translation (NMT) systems exhibit limited robustness in handling source-side linguistic variations.

Machine Translation NMT +1

LIMIT: Language Identification, Misidentification, and Translation using Hierarchical Models in 350+ Languages

1 code implementation23 May 2023 Milind Agarwal, Md Mahfuz ibn Alam, Antonios Anastasopoulos

Second, we propose a novel misprediction-resolution hierarchical model, LIMIt, for language identification that reduces error by 55% (from 0. 71 to 0. 32) on our compiled children's stories dataset and by 40% (from 0. 23 to 0. 14) on the FLORES-200 benchmark.

Language Identification Translation

SD-QA: Spoken Dialectal Question Answering for the Real World

1 code implementation Findings (EMNLP) 2021 Fahim Faisal, Sharlina Keshava, Md Mahfuz ibn Alam, Antonios Anastasopoulos

Question answering (QA) systems are now available through numerous commercial applications for a wide variety of domains, serving millions of users that interact with them via speech interfaces.

Fairness Question Answering +2

On the Evaluation of Machine Translation for Terminology Consistency

1 code implementation22 Jun 2021 Md Mahfuz ibn Alam, Antonios Anastasopoulos, Laurent Besacier, James Cross, Matthias Gallé, Philipp Koehn, Vassilina Nikoulina

As neural machine translation (NMT) systems become an important part of professional translator pipelines, a growing body of work focuses on combining NMT with terminologies.

Domain Adaptation Machine Translation +2

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