يتعرف محللون المحاورون على العلاقات المتعمدة والتنزاعية التي تنظم النصوص الموسعة. لقد كان لديهم تأثير كبير على مجموعة متنوعة من مهام NLP وكذلك الدراسات النظرية في اللغويات والعلوم المعرفية. ومع ذلك، غالبا ما يكون من الصعب تحقيق نتائج جيدة من نماذج الخطاب الحالية، ويعزى ذلك إلى حد كبير إلى صعوبة المهمة، لا سيما الاعتراف بعلاقات الخطاب الضمني. أظهرت التطورات الأخيرة في النماذج القائمة على المحولات وعد كبير على هذه التحليلات، لكن التحديات لا تزال تبقى. نقدم ورقة وضع توفر تحليلا منهيا لحالة محلل خطاب الفن. نحن نهدف إلى فحص أداء نماذج تحليل الخطاب الحالي عبر نوبة المجال التدريجي: داخل Corpus، على النصوص داخل المجال، وعلى النصوص خارج المجال، ونناقش الاختلافات بين النماذج القائمة على المحولات والنماذج السابقة في التنبؤ بأنواع مختلفة من العلاقات الضمنية كل من العلاقات الأساسية. نستنتج عن طريق وصف العديد من أوجه القصور في النماذج الحالية ومناقشة حول كيفية اتباع العمل في المستقبل هذه المشكلة.
Discourse parsers recognize the intentional and inferential relationships that organize extended texts. They have had a great influence on a variety of NLP tasks as well as theoretical studies in linguistics and cognitive science. However it is often difficult to achieve good results from current discourse models, largely due to the difficulty of the task, particularly recognizing implicit discourse relations. Recent developments in transformer-based models have shown great promise on these analyses, but challenges still remain. We present a position paper which provides a systematic analysis of the state of the art discourse parsers. We aim to examine the performance of current discourse parsing models via gradual domain shift: within the corpus, on in-domain texts, and on out-of-domain texts, and discuss the differences between the transformer-based models and the previous models in predicting different types of implicit relations both inter- and intra-sentential. We conclude by describing several shortcomings of the existing models and a discussion of how future work should approach this problem.
References used
https://aclanthology.org/
In this position paper, we present a research agenda and ideas for facilitating exposure to diverse viewpoints in news recommendation. Recommending news from diverse viewpoints is important to prevent potential filter bubble effects in news consumpti
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
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
Dialogue summarization is a long-standing task in the field of NLP, and several data sets with dialogues and associated human-written summaries of different styles exist. However, it is unclear for which type of dialogue which type of summary is most
We propose a method to learn contextualized and generalized sentence representations using contrastive self-supervised learning. In the proposed method, a model is given a text consisting of multiple sentences. One sentence is randomly selected as a