Papers by Arda Tezcan
Beyond Reproduction: A Paired-Task Framework for Assessing LLM Comprehension and Creativity in Literary Translation (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly used for creative tasks such as literary translation. |
| Approach: | They propose a paired-task framework that assesses translational creativity using Units of Creative Potential (UCPs) they benchmark 23 models and four creativity-oriented prompts to assess translational comprehension . |
| Outcome: | The proposed framework compares 23 models and four creativity-oriented prompts on literary excerpts from 11 books. |
Literary Machine Translation under the Magnifying Glass: Assessing the Quality of an NMT-Translated Detective Novel on Document Level (2020.lrec-1)
Copied to clipboard
| Challenge: | Several studies have demonstrated that translation quality has improved enormously since the emergence of neural machine translation systems. |
| Approach: | They performed a document-level evaluation of the raw NMT output of an entire novel and annotated it in two steps: first all fluency errors, then all accuracy errors. |
| Outcome: | The results show that translation quality has improved enormously since the emergence of neural machine translation systems. |
A fine-grained error analysis of NMT, SMT and RBMT output for English-to-Dutch (L18-1)
Copied to clipboard
| Challenge: | Since 2016, the landscape of automated translation has substantially changed with the arrival of neural machine translation (NMT). |
| Approach: | They propose to use an annotated SCATE corpus of MT errors to enrich the SCATE error taxonomy to fit the neural MT output. |
| Outcome: | The proposed system outperforms phrase-based and rule-based systems except for lexical issues. |
Neural Fuzzy Repair: Integrating Fuzzy Matches into Neural Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Several configurations are tested on the DGT-TM data set for the language directions English into Dutch (ENNL) and English into Hungarian (ENHU). |
| Approach: | They propose and test two methods for augmenting NMT training data with fuzzy TM matches by concatenation. |
| Outcome: | The proposed method improves on the DGT-TM data set for two language pairs and is easy to implement. |