التفكير الشديد هو وضع المنطق حيث يمكن إقليم الاستنتاجات من خلال مراعاة الأدلة الجديدة.أدب الأدب العلوم المعرفي الموجود بشأن التفكير الشديد يشير إلى أن الشخص يشكل نموذجا عقليا "سيناريو المشكلة قبل الإجابة على الأسئلة.يسأل هدفنا البحثي عما إذا كانت النماذج العصبية يمكن أن تستفيد بالمثل من تصور سيناريو الأسئلة قبل الإجابة على استعلام دافئ.نهجنا هو، بالنظر إلى سؤال، أن يكون لديك نموذج أولا إنشاء رسم بياني للتأثيرات ذات الصلة، ثم الاستفادة من ذلك الرسم البياني كمدخل إضافي عند الإجابة على السؤال.نظامنا، فضولي، يحقق حالة جديدة من بين الفنين في ثلاث مجموعات من أدوات التفكير المختلفة.هذه النتيجة مهمة حيث توضح أنه يمكن تحسين الأداء من خلال توجيه نظام للتفكير في "السؤال والنموذج الصريح السيناريو، بدلا من الإجابة عن الانعكاس.
Defeasible reasoning is the mode of reasoning where conclusions can be overturned by taking into account new evidence. Existing cognitive science literature on defeasible reasoning suggests that a person forms a mental model'' of the problem scenario before answering questions. Our research goal asks whether neural models can similarly benefit from envisioning the question scenario before answering a defeasible query. Our approach is, given a question, to have a model first create a graph of relevant influences, and then leverage that graph as an additional input when answering the question. Our system, CURIOUS, achieves a new state-of-the-art on three different defeasible reasoning datasets. This result is significant as it illustrates that performance can be improved by guiding a system to think about'' a question and explicitly model the scenario, rather than answering reflexively.
References used
https://aclanthology.org/
Recently, language models (LMs) have achieved significant performance on many NLU tasks, which has spurred widespread interest for their possible applications in the scientific and social area. However, LMs have faced much criticism of whether they a
Numerical reasoning skills are essential for complex question answering (CQA) over text. It requires opertaions including counting, comparison, addition and subtraction. A successful approach to CQA on text, Neural Module Networks (NMNs), follows the
We deal with the navigation problem where the agent follows natural language instructions while observing the environment. Focusing on language understanding, we show the importance of spatial semantics in grounding navigation instructions into visua
Knowledge Base Question Answering (KBQA) is to answer natural language questions posed over knowledge bases (KBs). This paper targets at empowering the IR-based KBQA models with the ability of numerical reasoning for answering ordinal constrained que
Despite excellent performance on tasks such as question answering, Transformer-based architectures remain sensitive to syntactic and contextual ambiguities. Question Paraphrasing (QP) offers a promising solution as a means to augment existing dataset