Supervised Open Information Extraction

By Gabriel Stanovsky, Julian Michael, Luke S. Zettlemoyer, Ido Dagan. 2018

316 citations recorded by the source corpus.

We present data and methods that enable a supervised learning approach to Open Information Extraction (Open IE). Central to the approach is a novel formulation of Open IE as a sequence tagging problem, addressing challenges such as encoding multiple extractions for a predicate. We also develop a bi-LSTM transducer, extending recent deep Semantic Role Labeling models to extract Open IE tuples and provide confidence scores for tuning their precision-recall tradeoff. Furthermore, we show that the recently released Question-Answer Meaning Representation dataset can be automatically converted into an Open IE corpus which significantly increases the amount of available training data. Our supervised model outperforms the existing state-of-the-art Open IE systems on benchmark datasets.

Subfields: Artificial Intelligence, Management Science and Operations Research, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

In Natural Language Processing

Citations in the corpus

DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs (2019, methodology): “We used the AllenNLP implementations of state-of-theart models for all of these representations (Gardner et al., 2017; Dozat et al., 2017; He et al., 2017; Stanovsky et al., 2018).”
Matching the Blanks: Distributional Similarity for Relation Learning (2019, background): “…removes the limitations of a predeﬁned schema by instead representing relations using their surface forms (Banko et al., 2007; Fader et al., 2011; Stanovsky et al., 2018), which increases scope but also leads ∗ Work done as part of the Google AI residency. to an associated lack of generality…”
Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics (2021, methodology): “5We use the model and implementation from (Stanovsky et al., 2018) for OpenIE extraction.”
Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs (2019, methodology): “We apply Coreference Resolution (Clark and Man-ning, 2016a,b) 1 and Open Information Extraction (Stanovsky et al., 2018) 2 to convert sentences into a Triple of the form (subject, predicate, object).”
DeepStruct: Pretraining of Language Models for Structure Prediction (2022, methodology): “To handle different structure prediction problems, prior work presents a variety of task-speciﬁc models in the form of sequence tagging (Stanovsky et al., 2018; Li et al., 2019), machine reading comprehension (Zhao et al., 2020) and text classiﬁcation (Soares et al., 2019), which hinders the…”
Crowdsourcing Question-Answer Meaning Representations (2017, background): “We also highlight a recent result (Stanovsky et al., 2018) showing that QAMR data can be used to improve performance on a challenging task: Open Information Extraction.”