SkillsCast

Building a Knowledge Base Question Answering Pipeline

28th January 2019 in London at CodeNode

This SkillsCast was filmed at Building a Knowledge Base Question Answering Pipeline

This session was not filmed.

In this session, we will discuss a semantic parsing approach to knowledge base question answering and the challenges of building a question answering pipeline.

Knowledge base question answering aims to provide a natural language interface to factual knowledge. It requires precise modeling of the question meaning through the entities and relations available in the knowledge base in order to retrieve the correct answer.

In this session, we will discuss a semantic parsing approach to knowledge base question answering and the challenges of building a question answering pipeline. It is common to break down the task into three main steps: entity linking, relation disambiguation and answer retrieval. We will focus on two aspects: entity linking across various categories of entities and using graph neural networks to jointly encode entities and relations.

Papers:

Code: * https://github.com/UKPLab/starsem2018-entity-linking * https://github.com/UKPLab/coling2018-graph-neural-networks-question-answering

Further Reading: * Elasticsearch for Developers with Itamar Syn-Hershko (in London on 23rd - 25th September 2019)

  • Real-time Systems with Spark Streaming and Kafka (in London on 30th September - 1st October 2019)
  • CloudNative London 2019 (in London on 25th - 27th September 2019)
  • Haskell eXchange 2019 (in London on 10th - 11th October 2019)
  • Transforming Customer Experience with Big Data (in London on 18th July 2019)
  • London Reinforcement Learning July (in London on 18th July 2019)
  • A Machine That Predicts the Global Economy in Real-Time (SkillsCast recorded in July 2019)
  • Keynote: AI, Natural Stupidity and Swimming Submarines (SkillsCast recorded in July 2019)
  • Thanks to our sponsors

    SkillsCast

    This session was not filmed.

    In this session, we will discuss a semantic parsing approach to knowledge base question answering and the challenges of building a question answering pipeline.

    Knowledge base question answering aims to provide a natural language interface to factual knowledge. It requires precise modeling of the question meaning through the entities and relations available in the knowledge base in order to retrieve the correct answer.

    In this session, we will discuss a semantic parsing approach to knowledge base question answering and the challenges of building a question answering pipeline. It is common to break down the task into three main steps: entity linking, relation disambiguation and answer retrieval. We will focus on two aspects: entity linking across various categories of entities and using graph neural networks to jointly encode entities and relations.

    Papers:

    Code: * https://github.com/UKPLab/starsem2018-entity-linking * https://github.com/UKPLab/coling2018-graph-neural-networks-question-answering

    Further Reading: * Elasticsearch for Developers with Itamar Syn-Hershko (in London on 23rd - 25th September 2019)

  • Real-time Systems with Spark Streaming and Kafka (in London on 30th September - 1st October 2019)
  • CloudNative London 2019 (in London on 25th - 27th September 2019)
  • Haskell eXchange 2019 (in London on 10th - 11th October 2019)
  • Transforming Customer Experience with Big Data (in London on 18th July 2019)
  • London Reinforcement Learning July (in London on 18th July 2019)
  • A Machine That Predicts the Global Economy in Real-Time (SkillsCast recorded in July 2019)
  • Keynote: AI, Natural Stupidity and Swimming Submarines (SkillsCast recorded in July 2019)
  • Thanks to our sponsors