في تصنيف علاقة الخطاب الضمني، نريد التنبؤ بالعلاقة بين الجمل المجاورة في غياب أي اتصال خطاب علني. هذا أمر صعب حتى بالنسبة للبشر، مما يؤدي إلى نقص البيانات المشروح، وهي حقيقة تجعل المهمة أكثر صعوبة في نهج التعلم الآلي الإشراف. في الدراسة الحالية، نؤدي تصنيف علاقة الخطاب الضمني دون الاعتماد على أي علاقة ضمنية المسمى. نحن غاضب من عدم وجود بيانات من خلال تفسير العلاقات الضمنية لتقليل المهمة إلى مشكلتين فرعيين: نمذجة اللغة وتصنيف علاقة خطاب صريحة، مشكلة أسهل بكثير. تبين نتائجنا التجريبية أن هذه الطريقة يمكن أن تتفوق حتى الآن على الرغم من أن الحديث، على الرغم من أن تكون أبسط بكثير من النماذج البديلة لأداء مماثل. علاوة على ذلك، نوضح أن الأداء المحقق قوي عبر المجالات كما اقترحته التجارب الصفرية في مجال مختلف تماما. يشير هذا إلى أن التطورات الحديثة في النمذجة اللغوية جعلت نماذج لغة جيدة بما فيه الكفاية في التقاط علاقات بين الجملة دون مساعدة من علامات الخطاب الصريحة.
In implicit discourse relation classification, we want to predict the relation between adjacent sentences in the absence of any overt discourse connectives. This is challenging even for humans, leading to shortage of annotated data, a fact that makes the task even more difficult for supervised machine learning approaches. In the current study, we perform implicit discourse relation classification without relying on any labeled implicit relation. We sidestep the lack of data through explicitation of implicit relations to reduce the task to two sub-problems: language modeling and explicit discourse relation classification, a much easier problem. Our experimental results show that this method can even marginally outperform the state-of-the-art, in spite of being much simpler than alternative models of comparable performance. Moreover, we show that the achieved performance is robust across domains as suggested by the zero-shot experiments on a completely different domain. This indicates that recent advances in language modeling have made language models sufficiently good at capturing inter-sentence relations without the help of explicit discourse markers.
References used
https://aclanthology.org/
Implicit discourse relation recognition (IDRR) aims to identify logical relations between two adjacent sentences in the discourse. Existing models fail to fully utilize the contextual information which plays an important role in interpreting each loc
For over thirty years, researchers have developed and analyzed methods for latent tree induction as an approach for unsupervised syntactic parsing. Nonetheless, modern systems still do not perform well enough compared to their supervised counterparts
We present ReasonBert, a pre-training method that augments language models with the ability to reason over long-range relations and multiple, possibly hybrid contexts. Unlike existing pre-training methods that only harvest learning signals from local
Scientific literature analysis needs fine-grained named entity recognition (NER) to provide a wide range of information for scientific discovery. For example, chemistry research needs to study dozens to hundreds of distinct, fine-grained entity types
Implicit discourse relation recognition (IDRR) is a critical task in discourse analysis. Previous studies only regard it as a classification task and lack an in-depth understanding of the semantics of different relations. Therefore, we first view IDR