مجلة نجد أن متطلبات الترجمة النموذجية لتكون مخلصا غامضة وغير مكتملة. مع التفسير من خلال أبرز النصوص النصية كدراسة حالة، نقدم العديد من حالات الفشل. استعارة مفاهيم الاقتراض من العلوم الاجتماعية، نحدد أن المشكلة هي اختلال بين السلسلة السببية للقرارات (الإسناد السببية) وإقامة السلوك الإنساني للتفسير (الإسناد الاجتماعي). إننا نعيد بإعادة صياغة الإخلاص كإسعار دقيق للسببية للنموذج، وإدخال مفهوم الإخلاص المحاذاة: سلاسل سببية مخلصة تتماشى مع سلوكها الاجتماعي المتوقع. خطوتين من الإسناد السببي والإسناد الاجتماعي معا إكمال عملية شرح السلوك. مع هذه الإجراءات الرسمية، فإننا نورد إخفاقات مختلفة من التفسيرات النادرة المؤمنة المخيفة، واقتراح سلسلة سببية بديلة لعلاج القضايا. أخيرا، نقوم بتنفيذ توضيحات تسليط الضوء على التنسيق السببي المقترح باستخدام تفسيرات مضادة للتناقض.
Abstract We find that the requirement of model interpretations to be faithful is vague and incomplete. With interpretation by textual highlights as a case study, we present several failure cases. Borrowing concepts from social science, we identify that the problem is a misalignment between the causal chain of decisions (causal attribution) and the attribution of human behavior to the interpretation (social attribution). We reformulate faithfulness as an accurate attribution of causality to the model, and introduce the concept of aligned faithfulness: faithful causal chains that are aligned with their expected social behavior. The two steps of causal attribution and social attribution together complete the process of explaining behavior. With this formalization, we characterize various failures of misaligned faithful highlight interpretations, and propose an alternative causal chain to remedy the issues. Finally, we implement highlight explanations of the proposed causal format using contrastive explanations.
References used
https://aclanthology.org/
In this paper, we propose to align sentence representations from different languages into a unified embedding space, where semantic similarities (both cross-lingual and monolingual) can be computed with a simple dot product. Pre-trained language mode
Recent studies have demonstrated that pre-trained cross-lingual models achieve impressive performance in downstream cross-lingual tasks. This improvement benefits from learning a large amount of monolingual and parallel corpora. Although it is genera
Recipe texts are an idiosyncratic form of instructional language that pose unique challenges for automatic understanding. One challenge is that a cooking step in one recipe can be explained in another recipe in different words, at a different level o
Machine Reading Comprehension (MRC), which requires a machine to answer questions given the relevant documents, is an important way to test machines' ability to understand human language. Multiple-choice MRC is one of the most studied tasks in MRC du
Multimodal Machine Translation (MMT) enriches the source text with visual information for translation. It has gained popularity in recent years, and several pipelines have been proposed in the same direction. Yet, the task lacks quality datasets to i