Corpus ID: 836118

Dynamic Integration of Background Knowledge in Neural NLU Systems

@article{Weissenborn2018DynamicIO,
  title={Dynamic Integration of Background Knowledge in Neural NLU Systems},
  author={Dirk Weissenborn and Tom'avs Kovcisk'y and Chris Dyer},
  journal={arXiv: Computation and Language},
  year={2018}
}
  • Dirk Weissenborn, Tom'avs Kovcisk'y, Chris Dyer
  • Published 2018
  • Computer Science
  • arXiv: Computation and Language
  • Common-sense or background knowledge is required to understand natural language, but in most neural natural language understanding (NLU) systems, the requisite background knowledge is indirectly acquired from static corpora. [...] Key Method A new task-agnostic reading module provides refined word representations to a task-specific NLU architecture by processing background knowledge in the form of free-text statements, together with the task-specific inputs. Strong performance on the tasks of document question…Expand Abstract

    Figures, Tables, and Topics from this paper.

    Incorporating External Knowledge into Machine Reading for Generative Question Answering
    6
    Enhancing Answer Boundary Detection for Multilingual Machine Reading Comprehension
    3
    NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
    12
    Contextualized Representations Using Textual Encyclopedic Knowledge
    1
    Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge
    62
    Improving Question Answering by Commonsense-Based Pre-Training
    21
    Simple and Effective Multi-Paragraph Reading Comprehension
    218

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 34 REFERENCES
    A Neural Knowledge Language Model
    88
    Linguistic Knowledge as Memory for Recurrent Neural Networks
    32
    Dynamic Entity Representations in Neural Language Models
    52
    Ask Me Anything: Dynamic Memory Networks for Natural Language Processing
    772
    Natural Language Inference over Interaction Space
    134
    Enhancing and Combining Sequential and Tree LSTM for Natural Language Inference
    106