Corpus ID: 211097053

Hybrid Neural Tagging Model for Open Relation Extraction.

  title={Hybrid Neural Tagging Model for Open Relation Extraction.},
  author={Shengbin Jia and Yang Xiang},
  journal={arXiv: Computation and Language},
Open relation extraction (ORE) remains a challenge to obtain a semantic representation by discovering arbitrary relation tuples from the unstructured text. Conventional methods heavily depend on feature engineering or syntactic parsing, they are inefficient or error-cascading. Recently, leveraging supervised deep learning structures to address the ORE task is an extraordinarily promising way. However, there are two main challenges: (1) The lack of enough labeled corpus to support supervised… Expand
Explore BiLSTM-CRF-Based Models for Open Relation Extraction
This paper develops several Open RE models based on the bidirectional LSTM-CRF (BiL STF) neural network and different contextualized word embedding methods and proposes a new tagging scheme to solve overlapping problems and enhance models’ performance. Expand
Zero-shot Learning for Relation Extraction
This work proposes a zero-shot learning relation extraction (ZSLRE) framework, which focuses on recognizing novel relations that have no corresponding labeled data available for training, and builds an automatic hypernym extraction framework to help get hypernyms of various name entities directly from the web. Expand
Multiˆ2OIE: Multilingual Open Information Extraction based on Multi-Head Attention with BERT
Multi^2OIE is a sequence-labeling system with an efficient and effective argument extraction method that performs open information extraction (open IE) by combining BERT with multi-head attention. Expand


Leveraging Linguistic Structure For Open Domain Information Extraction
This work replaces this large pattern set with a few patterns for canonically structured sentences, and shifts the focus to a classifier which learns to extract self-contained clauses from longer sentences to determine the maximally specific arguments for each candidate triple. Expand
Supervised Open Information Extraction
A novel formulation of Open IE as a sequence tagging problem, addressing challenges such as encoding multiple extractions for a predicate, and a supervised model that outperforms the existing state-of-the-art Open IE systems on benchmark datasets. Expand
Distant supervision for relation extraction without labeled data
This work investigates an alternative paradigm that does not require labeled corpora, avoiding the domain dependence of ACE-style algorithms, and allowing the use of corpora of any size. Expand
Nested Propositions in Open Information Extraction
NESTIE is proposed, which uses a nested representation to extract higher-order relations, and complex, interdependent assertions, and Nesting the extracted propositions allows NESTIE to more accurately reflect the meaning of the original sentence. Expand
Open Information Extraction Using Wikipedia
WOE is presented, an open IE system which improves dramatically on TextRunner's precision and recall and is a novel form of self-supervised learning for open extractors -- using heuristic matches between Wikipedia infobox attribute values and corresponding sentences to construct training data. Expand
Open Language Learning for Information Extraction
Open Information Extraction (IE) systems extract relational tuples from text, without requiring a pre-specified vocabulary, by identifying relation phrases and associated arguments in arbitraryExpand
Open Information Extraction Systems and Downstream Applications
  • Mausam
  • Computer Science
  • 2016
A decade of progress on building Open IE extractors is described, which results in the latest extractor, OPENIE4, which is computationally efficient, outputs n-ary and nested relations, and also outputs relations mediated by nouns in addition to verbs. Expand
OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference
This paper proposes OpenKI to handle sparsity of OpenIE extractions by performing instance-level inference: for each entity, it is proposed to encode the rich information in its neighborhood in both KB and OpenIE Extractions, and leverage this information in relation inference by exploring different methods of aggregation and attention. Expand
MinIE: Minimizing Facts in Open Information Extraction
An experimental study with several real-world datasets found that MinIE achieves competitive or higher precision and recall than most prior systems, while at the same time producing shorter, semantically enriched extractions. Expand
ClausIE: clause-based open information extraction
ClausIE is a novel, clause-based approach to open information extraction, which extracts relations and their arguments from natural language text using a small set of domain-independent lexica, operates sentence by sentence without any post-processing, and requires no training data. Expand