场景模型>> qag-web>> 返回
项目作者： agusgun

项目描述 ：
Website of Question Answer Generation
高级语言： Python
项目地址: git://github.com/agusgun/qag-web.git
创建时间： 2018-11-11T15:28:20Z
项目社区：https://github.com/agusgun/qag-web
开源协议：
下载


Automatic Question-Answer Pairs Generation from Text

Members

  1. Holy Lovenia

  2. Agus Gunawan

  3. Felix Limanta

English Paper

We have a technical report that explains our question-answer generation system here.

Architecture in overview

We propose an approach which is generally based on the framework of an ongoing work by A. Sarvaiya. Formally, given a passage , question-answer generation (QAG) system retrieves the most important sentence from . Then, QAG system produces a set of question-answer pairs , where each generated can be found in , and its pair is the interrogative version of or a clause from a set of clauses in , without in it. As shown in the figure below, here are four main modules in our QAG system.

architecture-overview

  1. Preprocessing, which cleans the input passage from unnecessary characters and shapes it into the desirable form (list of sentences).

  2. Sentence Selection, which picks top- most important sentences given . The text summarization method used can be chosen between TextRank, multi-word phrase extraction (MWPE), and latent semantic analysis (LSA). The chosen method ranks the sentences in P and selects the top- highest ranked sentences as the output.

  3. Gap Selection, which selects phrases in that can be used as answers based on constituent tree from syntactic parser and named entity recognition (NER).

  4. Question Formation, which creates the interrogative version of or in without to make a question for each answer in . The final output of this module is question-answer pairs related to .

Result

  1. Demonstration with Jupyter Notebook. Check it out!

  2. Source code for the web version is in this GitHub repository.

Installation

  1. Export ‘$STANFORD_PARSER’ environment variable using lib path using command EXPORT STANFORD_PARSER=<ABSOLUTE_PATH> e.g. EXPORT STANFORD_PARSER=/home/anonymous/qag-web/qag/lib
  2. Run using command gunicorn qag:app
  3. If the program stuck after loading the model. It’s because the port already used. This happened usually after you already run the program twice or several times. Please kill the process that runs on the port using lsof -i find java, kill the proces PID.

result