Papers by Anne Vilnat
Detecting Non-literal Translations by Fine-tuning Cross-lingual Pre-trained Language Models (2020.coling-main)
Copied to clipboard
| Challenge: | Non-literal translations are difficult to produce even for human translators, especially for foreign language learners, and machine translations have not yet been developed to simulate human translations. |
| Approach: | They propose to fine-tune generic sentence representations produced by a pre-trained cross-lingual language model to detect non-literal translations. |
| Outcome: | The proposed model can predict human translations and distinguish literal and non-literal translations at phrase level with a moderate positive correlation. |
Introducing CQuAE : A New French Contextualised Question-Answering Corpus for the Education Domain (2024.lrec-main)
Copied to clipboard
| Challenge: | a new question answering corpus in french is designed to educational domain . we propose more complex questions and can justify the answers on validated material . |
| Approach: | They propose a question answering corpus in French designed to educational domain . they propose to propose more complex questions and justify answers on validated material . |
| Outcome: | The proposed question answering corpus is designed to be useful in educational domain . it proposes more complex questions and can justify answers on validated material . the proposed corpus could be used in the education domain, but it's not yet ready for use . |
Building an English-Chinese Parallel Corpus Annotated with Sub-sentential Translation Techniques (2020.lrec-1)
Copied to clipboard
| Challenge: | a recent study shows that human translators often resort to different non-literal translation techniques besides literal translation . however, they receive less attention in developing natural language processing (NLP) applications. |
| Approach: | They propose to have a better semantic control of extracting paraphrases from bilingual parallel corpora. |
| Outcome: | The proposed method can automatically recognize different non-literal translation techniques . the results confirm the hypothesis of the proposed method . |
Evaluating Tokenizers Impact on OOVs Representation with Transformers Models (2022.lrec-1)
Copied to clipboard
| Challenge: | Pre-trained Transformer models have proven their effectiveness in adapting to multiple NLP tasks and domains. |
| Approach: | They evaluated three categories of out-of-vocabulary words using three French domain-specific datasets on the legal, medical, and energetical domains to robustly analyze these categories. |
| Outcome: | The proposed models can create new representations for out-of-vocabulary words by adding external morpho-syntactic context rather than improving the semantic understanding of the words directly. |