mlsanityData to 14 Oct 2026

When to Use What: An In-Depth Comparative Empirical Analysis of OpenIE Systems for Downstream Applications

arXiv 2211.08228 ↗First posted 15 Nov 2022cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Open Information Extraction (OpenIE) has been used in the pipelines of various NLP tasks. Unfortunately, there is no clear consensus on which models to use in which tasks. Muddying things further is the lack of comparisons that take differing training sets into account. In this paper, we present an application-focused empirical survey of neural OpenIE models, training sets, and benchmarks in an effort to help users choose the most suitable OpenIE systems for their applications. We find that the different assumptions made by different models and datasets have a statistically significant effect on performance, making it important to choose the most appropriate model for one's applications. We demonstrate the applicability of our recommendations on a downstream Complex QA application.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 17 of its 45 references that are in the map. First posted on arXiv 15 Nov 2022.

Builds on

17 of 45 references.

References · 17

  1. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  2. 2019BERT for Joint Intent Classification and Slot Fillingcited by 196
  3. 2017Faithful to the Original: Fact Aware Neural Abstractive Summarizationcited by 141
  4. 2018A Survey on Open Information Extractioncited by 51
  5. 2018Neural Open Information Extractioncited by 50
  6. 2020IMoJIE: Iterative Memory-Based Joint Open Information Extractioncited by 34
  7. 2019Span Model for Open Information Extraction on Accurate Corpuscited by 33
  8. 2022A Survey on Neural Open Information Extraction: Current Status and Future Directionscited by 27
  9. 2020Multi2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERTcited by 26
  10. 2017Answering Complex Questions Using Open Information Extractioncited by 25
  11. 2021BLEU, METEOR, BERTScore: Evaluation of Metrics Performance in Assessing Critical Translation Errors in Sentiment-oriented Textcited by 22
  12. 2019Answering Complex Questions by Joining Multi-Document Evidence with Quasi Knowledge Graphscited by 21
5 more
  1. 2018WiRe57 : A Fine-Grained Benchmark for Open Information Extractioncited by 16
  2. 2021LSOIE: A Large-Scale Dataset for Supervised Open Information Extractioncited by 15
  3. 2022DetIE: Multilingual Open Information Extraction Inspired by Object Detectioncited by 11
  4. 2017Supervising Unsupervised Learningcited by 5
  5. 2014Complex Question Answering: Unsupervised Learning Approaches and Experimentscited by 2

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2.

4 papers.

  1. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
  2. 2023Preserving Knowledge Invariance: Rethinking Robustness Evaluation of Open Information Extractioncited by 8
  3. 2023Mastering the Task of Open Information Extraction with Large Language Models and Consistent Reasoning Environmentcited by 1
  4. 2024textitBenchIEFL : A Manually Re-Annotated Fact-Based Open Information Extraction Benchmarkcited by 0