أداء النماذج العصبية للتعرف على الكيان المسمى يتحلل مع مرور الوقت، أصبحت قديمة.هذا التدهور يرجع إلى الانجراف الزمني، والتغيير في الخصائص الإحصائية المتغيرات المستهدفة لدينا مع مرور الوقت.هذه المسألة مشكلة خاصة لبيانات وسائل التواصل الاجتماعي، حيث تتغير المواضيع بسرعة.من أجل التخفيف من المشكلة، فإن شرح البيانات وإعادة تدريب النماذج أمر شائع.على الرغم من فائدتها، فإن هذه العملية مكلفة وتستغرق وقتا طويلا، مما يحفز بحثا جديدا على التحديث النموذجي الفعال.في هذه الورقة، نقترح نهجا بديهيا لقياس الوعي المحتمل للتغريدات واستخدام هذا المقياس لتحديد أكثر الحالات إعلامية للاستخدام للتدريب.نقوم بإجراء تجارب على ثلاث نماذج من أحدث طراز على مجموعة بيانات Twitter الزمنية.يظهر نهجنا زيادة أكبر في دقة التنبؤ مع بيانات تدريب أقل من البدائل، مما يجعلها حل جذابة وعملية.
Performance of neural models for named entity recognition degrades over time, becoming stale. This degradation is due to temporal drift, the change in our target variables' statistical properties over time. This issue is especially problematic for social media data, where topics change rapidly. In order to mitigate the problem, data annotation and retraining of models is common. Despite its usefulness, this process is expensive and time-consuming, which motivates new research on efficient model updating. In this paper, we propose an intuitive approach to measure the potential trendiness of tweets and use this metric to select the most informative instances to use for training. We conduct experiments on three state-of-the-art models on the Temporal Twitter Dataset. Our approach shows larger increases in prediction accuracy with less training data than the alternatives, making it an attractive, practical solution.
References used
https://aclanthology.org/
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
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
There is an emerging interest in the application of natural language processing models to source code processing tasks. One of the major problems in applying deep learning to software engineering is that source code often contains a lot of rare ident
While pre-trained language models (PTLMs) have achieved noticeable success on many NLP tasks, they still struggle for tasks that require event temporal reasoning, which is essential for event-centric applications. We present a continual pre-training
When intelligent agents communicate to accomplish shared goals, how do these goals shape the agents' language? We study the dynamics of learning in latent language policies (LLPs), in which instructor agents generate natural-language subgoal descript