في الإجابة على الأسئلة المفتوحة للنطاق الرد (ضمان الجودة)، فإن آلية استرداد وقراءة القراءة لها الاستفادة المتأصلة من الترجمة الترجمة من الترجمة الشفوية وسهولة إضافة أو إزالة أو تحرير المعرفة مقارنة بالنهج المعلمة لنماذج QA كتاب مغلقة.ومع ذلك، من المعروف أيضا أن تعاني من بصمة التخزين الكبيرة بسبب كوربوس وثائقها ومؤشرها.هنا، نناقش العديد من الاستراتيجيات المتعامدة لتقليل البصمة بشكل كبير من نظام QA لاسترداد ونظام QA المتسترف والقراءة بنسبة تصل إلى 160X.تشير نتائجنا إلى أن استرداد وقراءة القراءة يمكن أن يكون خيارا قابلا للتطبيق حتى في بيئة تخدم عالية للغاية مثل أجهزة الحافة، حيث نظهر أنه يمكن أن يحقق دقة أفضل من نموذج حزم بحزم مع حجم نظام منخفض المستوى من Docker.
In open-domain question answering (QA), retrieve-and-read mechanism has the inherent benefit of interpretability and the easiness of adding, removing, or editing knowledge compared to the parametric approaches of closed-book QA models. However, it is also known to suffer from its large storage footprint due to its document corpus and index. Here, we discuss several orthogonal strategies to drastically reduce the footprint of a retrieve-and-read open-domain QA system by up to 160x. Our results indicate that retrieve-and-read can be a viable option even in a highly constrained serving environment such as edge devices, as we show that it can achieve better accuracy than a purely parametric model with comparable docker-level system size.
References used
https://aclanthology.org/
Dense neural text retrieval has achieved promising results on open-domain Question Answering (QA), where latent representations of questions and passages are exploited for maximum inner product search in the retrieval process. However, current dense
Abstract Progress in cross-lingual modeling depends on challenging, realistic, and diverse evaluation sets. We introduce Multilingual Knowledge Questions and Answers (MKQA), an open- domain question answering evaluation set comprising 10k question-an
Information seeking is an essential step for open-domain question answering to efficiently gather evidence from a large corpus. Recently, iterative approaches have been proven to be effective for complex questions, by recursively retrieving new evide
Recent work (Feng et al., 2018) establishes the presence of short, uninterpretable input fragments that yield high confidence and accuracy in neural models. We refer to these as Minimal Prediction Preserving Inputs (MPPIs). In the context of question
Open-domain question answering aims at locating the answers to user-generated questions in massive collections of documents. Retriever-readers and knowledge graph approaches are two big families of solutions to this task. A retriever-reader first app