نظرا لأن أنظمة NLP تصبح أفضل في اكتشاف الآراء والمعتقدات من النص، فمن المهم التأكد من أن النماذج ليس فقط دقيقة ولكنها تصل أيضا إلى تنبؤاتها بطرق تتماشى مع المنطق البشري.في هذا العمل، نقدم طريقة لإنقاذ الترشيد يشبه الإنسان نموذجا للكشف عن الموقف باستخدام التعليقات التوضيحية الجماعية على جزء صغير من بيانات التدريب.نظرا لأنه في بيئة نادرة بيانات، فإن نهجنا يمكن أن يحسن منطق مصنف أحدث --- لا سيما للمدخلات التي تحتوي على ظواهر صعبة مثل السخرية - - دون أي تكلفة في الأداء التنبئي.علاوة على ذلك، نوضح أن الأوزان الاهتمام تتفوق على طريقة رائدة في تقديم تفسيرات مخلصة لتنبؤات النماذج لدينا، مما يخدم كمصدر رخيص وموثوق بحسب حسابي لنموذجنا.
As NLP systems become better at detecting opinions and beliefs from text, it is important to ensure not only that models are accurate but also that they arrive at their predictions in ways that align with human reasoning. In this work, we present a method for imparting human-like rationalization to a stance detection model using crowdsourced annotations on a small fraction of the training data. We show that in a data-scarce setting, our approach can improve the reasoning of a state-of-the-art classifier---particularly for inputs containing challenging phenomena such as sarcasm---at no cost in predictive performance. Furthermore, we demonstrate that attention weights surpass a leading attribution method in providing faithful explanations of our model's predictions, thus serving as a computationally cheap and reliable source of attributions for our model.
References used
https://aclanthology.org/
The goal of stance detection is to identify whether the author of a text is in favor of, neutral or against a specific target. Despite substantial progress on this task, one of the remaining challenges is the scarcity of annotations. Data augmentatio
Detecting stance on Twitter is especially challenging because of the short length of each tweet, the continuous coinage of new terminology and hashtags, and the deviation of sentence structure from standard prose. Fine-tuned language models using lar
The widespread use of the Internet and the rapid dissemination of information poses the challenge of identifying the veracity of its content. Stance detection, which is the task of predicting the position of a text in regard to a specific target (e.g
The problem of detecting psychological stress in online posts, and more broadly, of detecting people in distress or in need of help, is a sensitive application for which the ability to interpret models is vital. Here, we present work exploring the us
Stance detection (SD) entails classifying the sentiment of a text towards a given target, and is a relevant sub-task for opinion mining and social media analysis. Recent works have explored knowledge infusion supplementing the linguistic competence a