Predicting algorithmic approach for programming problems from natural language problem description
نویسندگان
چکیده
In this paper, we study the problem of predicting the algorithmic approach useful for solving a programming problem given its natural language description. As an auxiliary task, we also try to predict the difficulty of a problem given its natural language description. In order to solve this problem, we built our own dataset using 2 popular algorithmic programming websites, namely, Codechef www. codechef.com and Codeforces www.codeforces. com. In this paper we present an attempt at solving this problem. We use hashing, bag of words and word embeddings (word2vec) for feature extraction. We train a Long Short Term Memory (LSTM) network for the tasks. We also propose and evaluate a novel pre-training idea specific to our problem. The code for this project can be found at https://github.com/AshishBora/ nlp-project.
منابع مشابه
A dynamic programming approach for solving nonlinear knapsack problems
Nonlinear Knapsack Problems (NKP) are the alternative formulation for the multiple-choice knapsack problems. A powerful approach for solving NKP is dynamic programming which may obtain the global op-timal solution even in the case of discrete solution space for these problems. Despite the power of this solu-tion approach, it computationally performs very slowly when the solution space of the pr...
متن کاملWiddowson and Classroom Discourse
Drawing on recent developments in linguistic description and applied linguistics, it can be concluded that learning a language necessitates getting to know something and being able to do something with that knowledge: competence, and performance. Structural approach to language description attaches importance to the former; communicative approach to the latter. Appropriate classroom discours...
متن کاملPresentation and Solving Non-Linear Quad-Level Programming Problem Utilizing a Heuristic Approach Based on Taylor Theorem
The multi-level programming problems are attractive for many researchers because of their application in several areas such as economic, traffic, finance, management, transportation, information technology, engineering and so on. It has been proven that even the general bi-level programming problem is an NP-hard problem, so the multi-level problems are practical and complicated problems therefo...
متن کاملEvaluation of Automatic Conversion of Text to Diagram
Text to diagram conversion is an emerging area of research towards automating solution of natural language scientific problems, developing intelligent tutoring tools and many other graphics-based applications. There are no standard tools for evaluating diagrams produced from textual description. This paper presents application of an algorithmic approach to evaluate geometry diagrams produced fr...
متن کاملA goal programming approach for fuzzy flexible linear programming problems
We are concerned with solving Fuzzy Flexible Linear Programming (FFLP) problems. Even though, this model is very practical and is useful for many applications, but there are only a few methods for its situation. In most approaches proposed in the literature, the solution process needs at least, two phases where each phase needs to solve a linear programming problem. Here, we propose a method t...
متن کامل