Fatemeh Azadi — accepted AI-conference papers

2024

EPOQUE: An English-Persian Quality Estimation Dataset

Mohammed Hossein Jafari Harandi, Fatemeh Azadi, Mohammad Javad Dousti, Heshaam Faili

COLING 2024main

Translation quality estimation (QE) is an important component in real-world machine translation applications. Unfortunately, human labeled QE datasets, which play an important role in developing and assessing QE models, are only available for limited language pairs. In this paper, we present the fir…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

PMI-Align: Word Alignment With Point-Wise Mutual Information Without Requiring Parallel Training Data

Fatemeh Azadi, Heshaam Faili, Mohammad Javad Dousti

ACL 2023findings

Word alignment has many applications including cross-lingual annotation projection, bilingual lexicon extraction, and the evaluation or analysis of translation outputs. Recent studies show that using contextualized embeddings from pre-trained multilingual language models could give us high quality w…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗