ساهمت نماذج اللغة الملثمين (MLMS) في تحسينات أداء جذرية فيما يتعلق بدقة anaphora الصفر (ZAR).لتعزيز هذا النهج، في هذه الدراسة، قدمنا مقترحين.الأول هو مهمة محتملة جديدة تدرب MLMS على علاقات الاستعمارية مع الإشراف الصريح، والاقتراح الثاني هو طريقة أصلية جديدة ستصطدم بمسألة سيئة السمعة، والتناقض في التباين المؤمنأظهرت تجاربنا على ZAR اليابانية أن مقترحنا تعزز الأداء الحديثة، وتحليلنا التفصيلي يوفر رؤى جديدة حول التحديات المتبقية.
Masked language models (MLMs) have contributed to drastic performance improvements with regard to zero anaphora resolution (ZAR). To further improve this approach, in this study, we made two proposals. The first is a new pretraining task that trains MLMs on anaphoric relations with explicit supervision, and the second proposal is a new finetuning method that remedies a notorious issue, the pretrain-finetune discrepancy. Our experiments on Japanese ZAR demonstrated that our two proposals boost the state-of-the-art performance, and our detailed analysis provides new insights on the remaining challenges.
References used
https://aclanthology.org/
Resolving pronouns to their referents has long been studied as a fundamental natural language understanding problem. Previous works on pronoun coreference resolution (PCR) mostly focus on resolving pronouns to mentions in text while ignoring the exop
The state-of-the-art on basic, single-antecedent anaphora has greatly improved in recent years. Researchers have therefore started to pay more attention to more complex cases of anaphora such as split-antecedent anaphora, as in Time-Warner is conside
For Japanese-to-English translation, zero pronouns in Japanese pose a challenge, since the model needs to infer and produce the corresponding pronoun in the target side of the English sentence. However, although fully resolving zero pronouns often ne
Natural language generation (NLG) tasks on pro-drop languages are known to suffer from zero pronoun (ZP) problems, and the problems remain challenging due to the scarcity of ZP-annotated NLG corpora. In this case, we propose a highly adaptive two-sta
Relating entities and events in text is a key component of natural language understanding. Cross-document coreference resolution, in particular, is important for the growing interest in multi-document analysis tasks. In this work we propose a new mod