يشير العمل السابق إلى أن معلومات خطاب المعلومات المتعلقة بالتلخيص.في هذه الورقة، نستكشف ما إذا كان هذا التآزر بين الخطاب والتلخيص ثنائي الاتجاه، من خلال استنتاج أشجار الخطاب على مستوى المستند من الملخصات العصبية المدربة مسبقا.على وجه الخصوص، نولد أشجار خطاب على الطراز الأول غير المسموح به من مصفوفات الانتباه الذاتي لنموذج المحول.تكشف التجارب عبر النماذج ومجموعات البيانات أن الملخصات تتعلم كل من معلومات الخطاب على حد سواء، والاعتماد على نمط الدوائر الانتخابية، والتي يتم ترميزها عادة في رأس واحد، تغطي تبعيات الخطاب طويلا وقصيرا.بشكل عام، تشير النتائج التجريبية إلى أن معلومات الخطاب المستفادة عامة ومباشرة قابلة للتحويل.
Previous work indicates that discourse information benefits summarization. In this paper, we explore whether this synergy between discourse and summarization is bidirectional, by inferring document-level discourse trees from pre-trained neural summarizers. In particular, we generate unlabeled RST-style discourse trees from the self-attention matrices of the transformer model. Experiments across models and datasets reveal that the summarizer learns both, dependency- and constituency-style discourse information, which is typically encoded in a single head, covering long- and short-distance discourse dependencies. Overall, the experimental results suggest that the learned discourse information is general and transferable inter-domain.
References used
https://aclanthology.org/
Sentence splitting involves the segmentation of a sentence into two or more shorter sentences. It is a key component of sentence simplification, has been shown to help human comprehension and is a useful preprocessing step for NLP tasks such as summa
Most of the existing studies of language use in social media content have focused on the surface-level linguistic features (e.g., function words and punctuation marks) and the semantic level aspects (e.g., the topics, sentiment, and emotions) of the
This paper presents a global summarization method for live sport commentaries for which we have a human-written summary available. This method is based on a neural generative summarizer. The amount of data available for training is limited compared t
Abstract Interpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependenc
Machine reading comprehension (MRC) is one of the most challenging tasks in natural language processing domain. Recent state-of-the-art results for MRC have been achieved with the pre-trained language models, such as BERT and its modifications. Despi