Papers by Dimitar Shterionov

4 papers
Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation (2021.eacl-main)

Copied to clipboard

Challenge: Existing studies have shown that existing models amplify biases observed in training data.
Approach: They propose to use MT and NLP to amplify biases observed in training data to investigate how bias amplification might affect language in a broader sense.
Outcome: The proposed model amplifys biases observed in training data and could lead to an artificially impoverished language, the authors show.
Challenges with Sign Language Datasets for Sign Language Recognition and Translation (2022.lrec-1)

Copied to clipboard

Challenge: Sign Languages are the primary means of communication for at least half a million people in Europe . however, the development of SL recognition and translation tools is slowed down by resource scarcity and data formats are not suitable for machine learning.
Approach: They propose a framework to unify available resources and facilitate SL research for different languages.
Outcome: The proposed framework is based on a set of ELAN files and returns textual and visual data ready to train SL recognition and translation models.
Selecting Backtranslated Data from Multiple Sources for Improved Neural Machine Translation (2020.acl-main)

Copied to clipboard

Challenge: incorporating backtranslated data from different sources has led to improved results in machine translation (MT)
Approach: They use a low-resource use-case and a high-resourced language pair to test different backtranslation scenarios and employ data selection to optimise the synthetic corpora.
Outcome: The proposed method reduces the amount of data used while maintaining high-quality MT systems.
NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender Neutral Alternatives (2021.emnlp-main)

Copied to clipboard

Challenge: Recent years have seen an increasing need for gender-neutral and inclusive language.
Approach: They propose a rule-based and a neural approach to gender-neutral rewriting for English . they use manually curated synthetic and natural data to train a rewriter .
Outcome: The proposed approach improves on the rule-based approach with word error rates below 0.18% on synthetic, in-domain and out-domain test sets.

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