Papers by Eleftherios Avramidis
Observing the Learning Curve of NMT Systems With Regard to Linguistic Phenomena (2021.acl-srw)
Copied to clipboard
| Challenge: | Using a semi-automatic process, we observe the linguistic performance of various neural machine translation models. |
| Approach: | They observe the linguistic performance of a neural machine translation model on several steps on the training process. |
| Outcome: | The proposed system performs well on training of English-to-German models. |
Train, Sort, Explain: Learning to Diagnose Translation Models (N19-4)
Copied to clipboard
| Challenge: | Evaluating translation models is a trade-off between effort and detail. |
| Approach: | They propose to use a neural text classifier to automatically expose systematic differences between human and machine translations to human experts. |
| Outcome: | The proposed method exposes systematic differences between human and machine translations to human experts. |
Neural Machine Translation Methods for Translating Text to Sign Language Glosses (2023.acl-long)
Copied to clipboard
| Challenge: | State-of-the-art techniques common to low resource Machine Translation (MT) are applied to improve MT of spoken language text to Sign Language glosses. |
| Approach: | They propose to use data augmentation, semi-supervised Neural Machine Translation, transfer learning and multilingual NMT to improve MT of spoken language to Sign Language glosses. |
| Outcome: | The proposed models outperform previous work on two German SL corpora and are confirmed by human evaluation. |
A Linguistically Motivated Test Suite to Semi-Automatically Evaluate German–English Machine Translation Output (2022.lrec-1)
Copied to clipboard
Vivien Macketanz, Eleftherios Avramidis, Aljoscha Burchardt, He Wang, Renlong Ai, Shushen Manakhimova, Ursula Strohriegel, Sebastian Möller, Hans Uszkoreit
| Challenge: | Using fine-grained evaluation techniques, translation outputs have become better and more fluent. |
| Approach: | They propose a fine-grained test suite for the language pair German–English . they describe the creation and implementation of the test suite in detail . |
| Outcome: | The proposed test suite is based on linguistically motivated categories and phenomena and semi-automatic evaluation is carried out with regular expressions. |
DGS-Fabeln-1: A Multi-Angle Parallel Corpus of Fairy Tales between German Sign Language and German Text (2024.lrec-main)
Copied to clipboard
Fabrizio Nunnari, Eleftherios Avramidis, Cristina España-Bonet, Marco González, Anna Hennes, Patrick Gebhard
| Challenge: | a parallel corpus of German text and videos containing fairy tales interpreted into the German Sign Language (DGS) is the first corpus filmed from 7 angles and one of the few sign language corpora globally which have been filmed simultaneously. |
| Approach: | They present a parallel corpus of German fairy tales interpreted by a native DGS signer. |
| Outcome: | The proposed corpus is the first semi-naturally expressed DGS that has been filmed from 7 angles and where the listener has been simultaneously filmed. |
Using Neural Machine Translation Methods for Sign Language Translation (2022.acl-srw)
Copied to clipboard
| Challenge: | Sign languages are the main medium of exchanging information for the deaf and hard of hearing. |
| Approach: | They propose to use two NMT architectures to train models on parallel German Sign Language corpora . they achieve substantial improvement in BLEU scores for the models trained on the two corporales . |
| Outcome: | The proposed models achieve significant improvements on the two corpora trained on the german sign language . the proposed models outperform the models trained on both corporales . |
Sign Language Video Segmentation Using Temporal Boundary Identification (2025.acl-srw)
Copied to clipboard
| Challenge: | Sign language segmentation focuses on identifying temporal boundaries within video . previous methods have relied on frame-level and phrase-level segmentation. |
| Approach: | They propose to use synchronized subtitle data to facilitate temporal boundary recognition by a sequence-to-sequence model with and without attention for subtitle boundary identification. |
| Outcome: | The proposed model outperforms baseline models on optical flow data and aligned subtitles from BOBSL and YouTube-ASL. |