التعرف على علاقة الخطاب الضمني (IDRR) هو مهمة حاسمة في تحليل الخطاب. الدراسات السابقة فقط اعتبارها مهمة التصنيف وتفتقر إلى فهم متعمق لدل العلاقات المختلفة. لذلك، نرى أولا EDRR كامرأة توليد ومزيد من اقتراح طريقة النمذجة المشتركة للتصنيف والجيل. على وجه التحديد، نقترح نموذجا مشتركا، CG-T5، للتعرف على تسمية العلاقة وتوليد الجملة المستهدفة التي تحتوي على معنى العلاقات في وقت واحد. علاوة على ذلك، نقوم بتصميم ثلاث نماذج جملة مستهدفة، بما في ذلك نموذج الأسئلة، لنموذج الجيل لإدماج المعرفة السابقة. لمعالجة مشكلة أن وحدات الخطاب الكبيرة غير متضمنة بالكاد في الجملة المستهدفة، نقترح أيضا آلية بناء الجملة المستهدفة التي تستخرج الجمل الأساسية تلقائيا من تلك الوحدات الخطابية الكبيرة. تظهر النتائج التجريبية على حد سواء على مجموعات بيانات MCDTB والإنجليزية الصينية أن نموذج CG-T5 لدينا يحقق أفضل أداء ضد العديد من الأنظمة الحديثة.
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 IDRR as a generation task and further propose a method joint modeling of the classification and generation. Specifically, we propose a joint model, CG-T5, to recognize the relation label and generate the target sentence containing the meaning of relations simultaneously. Furthermore, we design three target sentence forms, including the question form, for the generation model to incorporate prior knowledge. To address the issue that large discourse units are hardly embedded into the target sentence, we also propose a target sentence construction mechanism that automatically extracts core sentences from those large discourse units. Experimental results both on Chinese MCDTB and English PDTB datasets show that our model CG-T5 achieves the best performance against several state-of-the-art systems.
References used
https://aclanthology.org/
This paper describes our submission to theSemEval'21: Task 7- HaHackathon: Detecting and Rating Humor and Offense. In this challenge, we explore intermediate finetuning, backtranslation augmentation, multitask learning, and ensembling of different la
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
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
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
In natural language generation tasks, a neural language model is used for generating a sequence of words forming a sentence. The topmost weight matrix of the language model, known as the classification layer, can be viewed as a set of vectors, each r