تلعب الحساب دورا رئيسيا في فهم اللغة الطبيعية.ومع ذلك، فإن نهج NLP الحالية، وليس فقط نهج Word2VEC التقليدي أو نماذج اللغة المستندة إلى المحولات السياقية، تفشل في تعلم الحساب.ونتيجة لذلك، فإن أداء هذه النماذج محدود عند تطبيقه على التطبيقات المكثفة في المجالات السريرية والمالية.في هذا العمل، نقترح نهج تضمين عدد بسيط بناء على الرسم البياني للمعرفة.نحن نبني رسم بياني للمعرفة يتكون من كيانات الأرقام وعلاقات الحجم.يتم بعد ذلك تطبيق طريقة تضمين الرسم البياني للمعرفة للحصول على ناقلات الرقم.نهجنا سهل التنفيذ، وتجربة نتائج التجربة على مختلف مهام NLP ذات الصلة بالكمال إظهار فعالية وكفاءة طريقتنا.
Numeracy plays a key role in natural language understanding. However, existing NLP approaches, not only traditional word2vec approach or contextualized transformer-based language models, fail to learn numeracy. As the result, the performance of these models is limited when they are applied to number-intensive applications in clinical and financial domains. In this work, we propose a simple number embedding approach based on knowledge graph. We construct a knowledge graph consisting of number entities and magnitude relations. Knowledge graph embedding method is then applied to obtain number vectors. Our approach is easy to implement, and experiment results on various numeracy-related NLP tasks demonstrate the effectiveness and efficiency of our method.
References used
https://aclanthology.org/
Relations in most of the traditional knowledge graphs (KGs) only reflect static and factual connections, but fail to represent the dynamic activities and state changes about entities. In this paper, we emphasize the importance of incorporating events
Visual dialog is a task of answering a sequence of questions grounded in an image using the previous dialog history as context. In this paper, we study how to address two fundamental challenges for this task: (1) reasoning over underlying semantic st
Static knowledge graph (SKG) embedding (SKGE) has been studied intensively in the past years. Recently, temporal knowledge graph (TKG) embedding (TKGE) has emerged. In this paper, we propose a Recursive Temporal Fact Embedding (RTFE) framework to tra
Knowledge Graph Embeddings (KGEs) have been intensively explored in recent years due to their promise for a wide range of applications. However, existing studies focus on improving the final model performance without acknowledging the computational c
Conditioned dialogue generation suffers from the scarcity of labeled responses. In this work, we exploit labeled non-dialogue text data related to the condition, which are much easier to collect. We propose a multi-task learning approach to leverage