{"ID":3084690,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-06T20:54:36.964885582Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05444","arxiv_id":"2606.05444","title":"Multilingual Coreference Resolution via Cycle-Consistent Machine Translation","abstract":"Coreference resolution is a core NLP task, having a broad range of downstream applications, e.g.~machine translation, question answering, document summarization, etc. While the task is well-studied in English, comparatively less attention is dedicated to coreference resolution in other languages, especially low-resource ones. To mitigate this gap, we propose a novel coreference resolution pipeline that harnesses machine translation (MT) from English to a target low-resource language, to generate or expand training data. To automatically validate the quality of the translated samples, we back-translate the samples and assess the similarity with the original English samples via cosine similarity in the latent space of a BERT model. The resulting similarity scores are integrated into the loss function to weight training samples according to their MT cycle consistency. Extensive experiments on four low-resource languages show that our pipeline brings significant performance gains in coreference resolution. Moreover, our pipeline enables accurate coreference resolution in languages where no previous corpora were available.","short_abstract":"Coreference resolution is a core NLP task, having a broad range of downstream applications, e.g.~machine translation, question answering, document summarization, etc. While the task is well-studied in English, comparatively less attention is dedicated to coreference resolution in other languages, especially low-resourc...","url_abs":"https://arxiv.org/abs/2606.05444","url_pdf":"https://arxiv.org/pdf/2606.05444v1","authors":"[\"Adriana-Valentina Costache\",\"Eduard Poesina\",\"Silviu-Florin Gheorghe\",\"Paul Irofti\",\"Radu Tudor Ionescu\"]","published":"2026-06-03T21:06:55Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.LG\"]","methods":"[]","has_code":false}