Papers by Tasnim Mohiuddin

12 papers
Ready to Translate, Not to Represent? Bias and Performance Gaps in Multilingual LLMs Across Language Families and Domains (2026.findings-acl)

Copied to clipboard

Challenge: Large Language Models (LLMs) have redefined Machine Translation, enabling context-aware and fluent translations across hundreds of languages and textual domains.
Approach: They propose a framework and dataset to evaluate the translation quality and fairness of open-source LLMs.
Outcome: The proposed framework and dataset evaluates translation quality and fairness of open-source LLMs.
MathMist: A Parallel Multilingual Benchmark Dataset for Mathematical Problem Solving and Reasoning (2026.findings-eacl)

Copied to clipboard

Challenge: Existing benchmarks primarily focus on English or a narrow subset of high-resource languages, leaving significant gaps in assessing multilingual and cross-lingual mathematical reasoning.
Approach: They propose a parallel multilingual benchmark for mathematical problem solving and reasoning that encompasses 2,890 parallel Bangla-English gold standard artifacts.
Outcome: The proposed model encompasses 2,890 parallel Bangla-English gold standard artifacts, totaling 30K aligned question–answer pairs across thirteen languages, representing high-, medium-, and low-resource linguistic settings.
UXLA: A Robust Unsupervised Data Augmentation Framework for Zero-Resource Cross-Lingual NLP (2021.acl-long)

Copied to clipboard

Challenge: Transfer learning has yielded state-of-the-art (SoTA) results, but annotated data for every target task in every target language is rare, especially for low-resource languages.
Approach: They propose a framework for unsupervised data augmentation for zero-resource transfer learning scenarios that performs simultaneous self-training with data hausse and unsupervised sample selection.
Outcome: The proposed framework outperforms baselines on three zero-resource transfer tasks and achieves SoTA results in all the tasks.
LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Space (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for bilingual lexicon induction are mapping-based, but they do not hold for closely related languages.
Approach: They propose a semi-supervised method to learn cross-lingual word embeddings for BLI using a linear mapping function and a latent space of two independently trained autoencoders.
Outcome: The proposed method outperforms existing models on 15 different language pairs on both directions.
Adaptation of Hierarchical Structured Models for Speech Act Recognition in Asynchronous Conversation (N19-1)

Copied to clipboard

Challenge: asynchronous domains lack large labeled datasets to train an effective speech act recognition model.
Approach: They propose methods to leverage abundant unlabeled conversational data and available labeled data from synchronous domains to train an effective SAR model.
Outcome: The proposed method outperforms existing methods when trained on in-domain data only.
DM-Codec: Distilling Multimodal Representations for Speech Tokenization (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing speech tokenization models lack contextual representations for speech synthesis . absence of contextual representation results in elevated WER and WIL scores .
Approach: They propose a language model-guided distillation method that incorporates contextual information into a comprehensive speech tokenizer.
Outcome: The proposed method outperforms state-of-the-art tokenization models in reducing WER and WIL scores.
Rethinking Coherence Modeling: Synthetic vs. Downstream Tasks (2021.eacl-main)

Copied to clipboard

Challenge: Coherence models are typically evaluated only on synthetic tasks, which may not be representative of their performance in downstream applications.
Approach: They compare models' performance on synthetic sentences with those on retrieval-based dialog.
Outcome: The proposed models perform poorly on synthetic sentences and retrieval-based dialog tasks.
Data Selection Curriculum for Neural Machine Translation (2022.findings-emnlp)

Copied to clipboard

Challenge: Neural Machine Translation models are typically trained on heterogeneous data that are concatenated and randomly shuffled.
Approach: They propose a two-stage curriculum training framework where a NMT model is fine-tuned on subsets of data, selected by deterministic scoring and online scoring.
Outcome: The proposed framework improves on six language pairs comprising low- and high-resource languages and shows up to +2.2 BLEU improvement and faster convergence.
A Unified Neural Coherence Model (D19-1)

Copied to clipboard

Challenge: Existing models for coherence modeling fail on harder tasks with more realistic application scenarios.
Approach: They propose a unified coherence model that incorporates sentence grammar, inter-sentence coherent relations, and global coherency patterns into a common neural framework.
Outcome: The proposed model outperforms existing models on local and global discrimination tasks and outperformed existing models by a good margin.
Revisiting Adversarial Autoencoder for Unsupervised Word Translation with Cycle Consistency and Improved Training (N19-1)

Copied to clipboard

Challenge: Recent work has shown superior performance for non-adversarial methods in more challenging language pairs.
Approach: They propose to use adversarial autoencoder to map monolingual embeddings to a shared space and to put the target encoders as an adversary against the corresponding discriminator.
Outcome: The proposed method is more robust and achieves better performance than previously proposed adversarial and non-adversarial methods.
AugVic: Exploiting BiText Vicinity for Low-Resource NMT (2021.findings-acl)

Copied to clipboard

Challenge: Neural Machine Translation (NMT) systems often exhibit poor performance due to the lack of large bitext training corpora in low-resource languages.
Approach: They propose a data augmentation framework which exploits the vicinal samples of the given bitext without using extra monolingual data explicitly.
Outcome: The proposed framework can diversify in-domain bitext data with finer level control on four low-resource language pairs.
Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models (2026.eacl-long)

Copied to clipboard

Challenge: Subword tokenization approaches misalign with linguistic structure and waste capacity across languages and domains.
Approach: They argue for a context-aware framework that integrates tokenizer and model co-design . they argue that tokenization should be treated as a core design problem, not an afterthought .
Outcome: The proposed framework integrates tokenizer and model co-design, guided by linguistic, domain, and deployment considerations.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations