بناء نظام الدعم الفني التلقائي هو مهمة مهمة ولكن التحدي.من الناحية النظرية، للإجابة على سؤال المستخدم في منتدى فني، يتعين على خبير بشري استرداد المستندات ذات الصلة أولا، ثم اقرأها بعناية لتحديد مقتطف الإجابة.على الرغم من النجاح الهائل، فقد حقق الباحثون في التعامل مع أسئلة النطاق العامة الإجابة (ضمان الجودة)، وقد تم دفع الاهتمام الأقل بكثير مقابل التحقيق الفني في تشاينا.على وجه التحديد، تعاني الأساليب الموجودة من العديد من التحديات الفريدة (I) تتداخل السؤال والإجابة نادرا ما يتداخل بشكل كبير و (2) بحجم بيانات محدود للغاية.في هذه الورقة، نقترح إطارا جديدا لتعلم النقل العميق لمعالجة ضمان الجودة الفنية بشكل فعال عبر المهام والمجالات.تحقيقا لهذه الغاية، نقدم نهجا للتعلم المشترك قابل للتعديل لمهام استدعاء المستندات والقراءة.تجاربنا على Techqa توضح أداء فائق مقارنة بالطرق الحديثة.
Building automatic technical support system is an important yet challenge task. Conceptually, to answer a user question on a technical forum, a human expert has to first retrieve relevant documents, and then read them carefully to identify the answer snippet. Despite huge success the researchers have achieved in coping with general domain question answering (QA), much less attentions have been paid for investigating technical QA. Specifically, existing methods suffer from several unique challenges (i) the question and answer rarely overlaps substantially and (ii) very limited data size. In this paper, we propose a novel framework of deep transfer learning to effectively address technical QA across tasks and domains. To this end, we present an adjustable joint learning approach for document retrieval and reading comprehension tasks. Our experiments on the TechQA demonstrates superior performance compared with state-of-the-art methods.
References used
https://aclanthology.org/
Abstract Most combinations of NLP tasks and language varieties lack in-domain examples for supervised training because of the paucity of annotated data. How can neural models make sample-efficient generalizations from task--language combinations with
Question answering (QA) is one of the most challenging and impactful tasks in natural language processing. Most research in QA, however, has focused on the open-domain or monolingual setting while most real-world applications deal with specific domai
Supervised deep learning-based approaches have been applied to task-oriented dialog and have proven to be effective for limited domain and language applications when a sufficient number of training examples are available. In practice, these approache
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
Current textual question answering (QA) models achieve strong performance on in-domain test sets, but often do so by fitting surface-level patterns, so they fail to generalize to out-of-distribution settings. To make a more robust and understandable