Skip to content

seriousran/awesome-qa

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

awesome-qa Awesome

A curated list of the Question Answering (QA) subject which is a computer science discipline within the fields of information retrieval and natural language processing (NLP)

问答系统主题的精选列表,是信息检索和自然语言处理领域的计算机科学学科

Contents

About QA

types of QA

  • Single-turn QA: answer without considering any context
  • Conversational QA: use previsous conversation turns

subtypes of QA

  • Knowledge-based QA
  • Table/List-based QA
  • Text-based QA
  • Community-based QA
  • Visual QA

Anlaysis and Parsing for Pre-processing in QA systems

Lanugage Analysis

  1. Morphological analysis
  2. Named Entity Recognition(NER)
  3. Homonyms / Polysemy Analysis
  4. Syntactic Parsing (Dependency Parsing)
  5. Semantic Recognition

most QA systems have roughly 3 parts

  1. Fact extraction
    1. Entity Extraction
      1. Named-Entity Recognition(NER)
    2. Relation Extraction
  2. Understanding the question
  3. Generating an answer

Events

  • Wolfram Alpha launced the answer engine in 2009.
  • IBM Watson system defeated top Jeopardy! champions in 2011.
  • Apple's Siri integrated Wolfram Alpha's answer engine in 2011.
  • Google embraced QA by launching its Knowledge Graph, leveraging the free base knowledge base in 2012.
  • Amazon Echo | Alexa (2015), Google Home | Google Assistant (2016), INVOKE | MS Cortana (2017), HomePod (2017)

Systems

  • IBM Watson - Has state-of-the-arts performance.
  • Facebook DrQA - Applied to the SQuAD1.0 dataset. The SQuAD2.0 dataset has released. but DrQA is not tested yet.
  • MIT media lab's Knowledge graph - Is a freely-available semantic network, designed to help computers understand the meanings of words that people use.

Codes

Lectures

Slides

Dataset Collections

Datasets

  • AI2 Science Questions v2.1(2017)
  • Children's Book Test
  • It is one of the bAbI project of Facebook AI Research which is organized towards the goal of automatic text understanding and reasoning. The CBT is designed to measure directly how well language models can exploit wider linguistic context.
  • DeepMind Q&A Dataset; CNN/Daily Mail
    • Hermann et al. (2015) created two awesome datasets using news articles for Q&A research. Each dataset contains many documents (90k and 197k each), and each document companies on average 4 questions approximately. Each question is a sentence with one missing word/phrase which can be found from the accompanying document/context.
    • paper: https://arxiv.org/abs/1506.03340
  • GraphQuestions
    • On generating Characteristic-rich Question sets for QA evaluation.
  • LC-QuAD
    • It is a gold standard KBQA (Question Answering over Knowledge Base) dataset containing 5000 Question and SPARQL queries. LC-QuAD uses DBpedia v04.16 as the target KB.
  • MS MARCO
  • MultiRC
  • NarrativeQA
  • NewsQA
  • Qestion-Answer Dataset by CMU
    • This is a corpus of Wikipedia articles, manually-generated factoid questions from them, and manually-generated answers to these questions, for use in academic research. These data were collected by Noah Smith, Michael Heilman, Rebecca Hwa, Shay Cohen, Kevin Gimpel, and many students at Carnegie Mellon University and the University of Pittsburgh between 2008 and 2010.
  • SQuAD1.0
    • Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage, or the question might be unanswerable.
    • paper: https://arxiv.org/abs/1606.05250
  • SQuAD2.0
    • SQuAD2.0 combines the 100,000 questions in SQuAD1.1 with over 50,000 new, unanswerable questions written adversarially by crowdworkers to look similar to answerable ones. To do well on SQuAD2.0, systems must not only answer questions when possible, but also determine when no answer is supported by the paragraph and abstain from answering.
    • paper: https://arxiv.org/abs/1806.03822
  • Story cloze test
    • 'Story Cloze Test' is a new commonsense reasoning framework for evaluating story understanding, story generation, and script learning. This test requires a system to choose the correct ending to a four-sentence story.
    • paper: https://arxiv.org/abs/1604.01696
  • TriviaQA
    • TriviaQA is a reading comprehension dataset containing over 650K question-answer-evidence triples. TriviaQA includes 95K question-answer pairs authored by trivia enthusiasts and independently gathered evidence documents, six per question on average, that provide high quality distant supervision for answering the questions.
    • paper: https://arxiv.org/abs/1705.03551
  • WikiQA
    • A publicly available set of question and sentence pairs for open-domain question answering.

Competitions in QA

Dataset When Top Rank Model over Human Performance
0 Story Cloze Test Univ. of Rochester ~2016 Radford et al LSDSem'17 x
1 MS MARCO Microsoft 2016~ YUANFUDAO research NLP MARS o
2 MS MARCO V2 Microsoft 2018~ Ming Yan Deep Cascade QA o
3 SQuAD Univ. of Stanford 2018~ Google AI Language BERT (ensemble) o
4 SQuAD 2.0 Univ. of Stanford 2018~ PINGAN GammaLab PAML+BERT (ensemble) x
5 TriviaQA Univ. of Washington 2017~ Ming Yan - -
6 decaNLP Salesforce Research 2018~ Salesforce Research MQAN x

Publications

The DeepQA Research Team in IBM Watson's publication within 5 years

MS Research's publication within 5 years

Google AI's publication within 5 years

Facebook AI Research's publication within 5 years

Books

  • Natural Language Question Answering system Paperback - Boris Galitsky (2003)
  • New Directions in Question Answering - Mark T. Maybury (2004)
  • Part 3. 5. Question Answering in The Oxford Handbook of Computational Linguistics - Sanda Harabagiu and Dan Moldovan (2005)
  • Chap.28 Question Answering in Speech and Language Processing - Daniel Jurafsky & James H. Martin (2017)

Links

Contributing

Contributions welcome! Read the contribution guidelines first.

License

CC0

To the extent possible under law, seriousmac (the maintainer) has waived all copyright and related or neighboring rights to this work.

About

😎 A curated list of the Question Answering (QA)

Topics

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •