تعرف حلال الرياضيات العصبي الحالي دمج المعرفة المنطقية أو المجال عن طريق الاستفادة من الثوابت أو الصيغ المحددة مسبقا.ومع ذلك، نظرا لأن هذه الثوابت والصيغ هي أساسا، فإن تعميمات الحلول محدودة.في هذه الورقة، نقترح استعادة المعرفة المطلوبة صراحة من مشكلة الرياضيات.وبهذه الطريقة، يمكننا مصممة معرفة المعرفة المطلوبة Andimprove شرح الحلول.خوارمنا لدينا تأخذ مشكلة النص ومعادلات الحل كمدخل.ثم، يحاولون استنتاج المعرفة المنطقية والمجال المطلوبة عن طريق دمج المعلومات من كلا الجزأين.نبني اثنين من مجموعات بيانات الرياضيات وتظهر فعالية خوارزمياتنا التي يمكنهم استرداد المعرفة المطلوبة لحل المشكلات.
Current neural math solvers learn to incorporate commonsense or domain knowledge by utilizing pre-specified constants or formulas. However, as these constants and formulas are mainly human-specified, the generalizability of the solvers is limited. In this paper, we propose to explicitly retrieve the required knowledge from math problemdatasets. In this way, we can determinedly characterize the required knowledge andimprove the explainability of solvers. Our two algorithms take the problem text andthe solution equations as input. Then, they try to deduce the required commonsense and domain knowledge by integrating information from both parts. We construct two math datasets and show the effectiveness of our algorithms that they can retrieve the required knowledge for problem-solving.
References used
https://aclanthology.org/
The problem of designing NLP solvers for math word problems (MWP) has seen sustained research activity and steady gains in the test accuracy. Since existing solvers achieve high performance on the benchmark datasets for elementary level MWPs containi
In this article, we tackle the math word problem, namely, automatically answering a mathematical problem according to its textual description. Although recent methods have demonstrated their promising results, most of these methods are based on templ
While solving math word problems automatically has received considerable attention in the NLP community, few works have addressed probability word problems specifically. In this paper, we employ and analyse various neural models for answering such wo
We study the problem of generating arithmetic math word problems (MWPs) given a math equation that specifies the mathematical computation and a context that specifies the problem scenario. Existing approaches are prone to generating MWPs that are eit
Pre-trained language models have led to substantial gains over a broad range of natural language processing (NLP) tasks, but have been shown to have limitations for natural language generation tasks with high-quality requirements on the output, such