资源分类
》 资源 》论文》Unsupervised Lexicon Acquisition for HPSG-Based Relation Extraction

Unsupervised Lexicon Acquisition for HPSG-Based Relation Extraction

2019-11-13 | |  68 |   37 |   0

Abstract
The paper describes a method of relation extraction, which is based on parsing the input text using a combination of a generic HPSG-based grammar and a highly focused domainand relation-specific lexicon. We also show a method of unsupervised acquisition of such a lexicon from a large unlabeled corpus. Together, the methods introduce a novel approach to the “Open IE” task, which is superior in accuracy and in quality of relation identification to the existing approaches.

上一篇：On the Utility of Curricula in Unsupervised Learning of Probabilistic Grammars

下一篇：Unsupervised Learning of Patterns in Data Streams Using Compression and Edit Distance

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to learn...

    The move from hand-designed features to learned...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...