النصوص التي تلتقط المعرفة المنطقية حول الأنشطة اليومية والمشاركين.أثبتت معرفة البرنامج النصي مفيدة في عدد من مهام NLP، مثل التنبؤ المراجع، تصنيف الخطاب، وتوليد القصة.إن خطوة حاسمة لاستغلال معرفة البرنامج النصي هي تحليل البرنامج النصي، ومهمة وضع علامة النص مع الأحداث والمشاركين من نشاط معين.هذه المهمة تحديا: إنها تتطلب معلومات حول طرق الأحداث والمشاركين عادة ما يتم نطقها في اللغة السطحية وكذلك الترتيب الذي تحدث فيه في العالم.نظهر كيفية إجراء تحليلات نصية دقيقة مع نموذج التسلسل الهرمي والتعلم التحويل.يعمل نموذجنا على تحسين حالة تقييد الأحداث بأكثر من 16 نقطة F-Score، وللمرة الأولى، يقوم المشاركين بدقة في البرامج النصية.
Scripts capture commonsense knowledge about everyday activities and their participants. Script knowledge proved useful in a number of NLP tasks, such as referent prediction, discourse classification, and story generation. A crucial step for the exploitation of script knowledge is script parsing, the task of tagging a text with the events and participants from a certain activity. This task is challenging: it requires information both about the ways events and participants are usually uttered in surface language as well as the order in which they occur in the world. We show how to do accurate script parsing with a hierarchical sequence model and transfer learning. Our model improves the state of the art of event parsing by over 16 points F-score and, for the first time, accurately tags script participants.
References used
https://aclanthology.org/
Robust sequence-to-sequence modelling is an essential task in the real world where the inputs are often noisy. Both user-generated and machine generated inputs contain various kinds of noises in the form of spelling mistakes, grammatical errors, char
Recently, the focus of dialogue state tracking has expanded from single domain to multiple domains. The task is characterized by the shared slots between domains. As the scenario gets more complex, the out-of-vocabulary problem also becomes severer.
We introduce Self-CRItic Pretraining Transformers (SCRIPT) for representation learning of text. The popular masked language modeling (MLM) pretraining methods like BERT replace some tokens with [MASK] and an encoder is trained to recover them, while
Understanding spatial expressions and using them appropriately is necessary for seamless and natural human-machine interaction. However, capturing the semantics and appropriate usage of spatial prepositions is notoriously difficult, because of their
With the increasing abundance of meeting transcripts, meeting summary has attracted more and more attention from researchers. The unsupervised pre-training method based on transformer structure combined with fine-tuning of downstream tasks has achiev