Papers with open information extraction

11 papers
EVIDENCEMINER: Textual Evidence Discovery for Life Sciences (2020.acl-demos)

Copied to clipboard

Challenge: EVIDENCEMINER is a web-based system that allows users to query a natural language statement and retrieve textual evidence from a background corpora for life sciences.
Approach: They propose a web-based system that lets users query a natural language statement and automatically retrieves textual evidence from a background corpora for life sciences.
Outcome: EVIDENCEMINER is a web-based system that lets users query a natural language statement and automatically retrieves textual evidence from a background corpora for life sciences.
mOKB6: A Multilingual Open Knowledge Base Completion Benchmark (2023.acl-short)

Copied to clipboard

Challenge: Open knowledge bases (Open KBCs) are constructed from triples of the form, which can be denoted as (s, r, o) by using open information extraction (Open IE) systems.
Approach: They construct a dataset with facts from Wikipedia in six languages . they use open information extraction systems to extract triples from text .
Outcome: The proposed dataset contains facts from Wikipedia in six languages including English . it improves existing Open KB construction pipeline by doing multilingual coreference resolution and keeping only entity-linked triples .
DeepStruct: Pretraining of Language Models for Structure Prediction (2022.findings-acl)

Copied to clipboard

Challenge: Pretrained language models perform structural understanding tasks that focus on understanding one aspect of the text.
Approach: They propose a method for improving the structural understanding abilities of language models by pretraining them to generate structures from the text on task-agnostic corpora.
Outcome: The proposed model performs state-of-the-art on 21 of 28 datasets.
Zero-Shot Information Extraction as a Unified Text-to-Triple Translation (2021.emnlp-main)

Copied to clipboard

Challenge: a number of information extraction tasks require task-specific training.
Approach: They propose a text-to-triple translation framework for information extraction tasks . they propose enabling task-agnostic translation by leveraging latent knowledge of a pre-trained language model .
Outcome: The proposed framework outperforms the existing methods on open information extraction tasks.
Multiˆ2OIE: Multilingual Open Information Extraction Based on Multi-Head Attention with BERT (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing open IE systems were based on handcrafted features or fine-grained rules.
Approach: They propose a multi-head argument extraction method using multi-lingual BERT . they use a query, key, and value setting inspired by the Multimodal Transformer .
Outcome: The proposed method outperforms existing sequence-labeling systems on two benchmark datasets and on two languages without training data.
Facts That Matter (D18-1)

Copied to clipboard

Challenge: Existing methods to discover facts from natural language text are based on relation extraction and open information extraction.
Approach: They propose a task of generating a machine-readable representation of the most prominent information in a text document as a set of facts.
Outcome: The proposed system outperforms baselines and text summarizers in a supervised evaluation of salience tasks.
Building a Web-Scale Dependency-Parsed Corpus from CommonCrawl (L18-1)

Copied to clipboard

Challenge: DepCC is the largest-to-date linguistically analyzed corpus in English . large corpora are essential for the modern data-driven approaches to natural language processing .
Approach: They present a large-to-date linguistically analyzed corpus in English with 365 million documents . they build an index of all sentences and their linguistic meta-data enabling quick search across the corpus .
Outcome: The proposed model outperforms state-of-the-art models on smaller corpora on the SimVerb3500 dataset.
Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for knowledge graph creation (KGC) are limited in their ability to scale up to text common in many real-world applications.
Approach: They propose a framework for knowledge graph creation from input text using a pre-defined schema and a trained component that retrieves schema elements relevant to the input text.
Outcome: The proposed framework extract-define-canonicalize extracts high-quality triplets with a succinct self-generated schema without any parameter tuning and with significantly larger schemas compared to prior works.
IELM: An Open Information Extraction Benchmark for Pre-Trained Language Models (2022.emnlp-main)

Copied to clipboard

Challenge: Recent studies show pre-trained LMs store linguistic and relational knowledge . pre-training LM models can answer "fill-in-the-blank" questions based on pre-defined relations .
Approach: They propose an open information extraction benchmark for pre-trained language models . they turn pre-trained LMs into zero-shot OIE systems to examine open relational information .
Outcome: The proposed benchmark outperforms state-of-the-art methods on factual OIE datasets without training sets.
Systematic Comparison of Neural Architectures and Training Approaches for Open Information Extraction (2020.emnlp-main)

Copied to clipboard

Challenge: Open information extraction (OIE) is a method for extracting facts from text in structured format . alternative formulations allow for longer tuples, but most work focuses on binary predicates only.
Approach: They propose to extract facts from natural language text and represent them as structured triples . they compare different neural network architectures and training approaches .
Outcome: The proposed approach improves the currently best models on the OIE16 benchmark by 0.421 F1 score and 0.420 AUC-PR .
MARIO-0.5B: A Multi-Agent Lightweight Model for Real-Time Open Information Extraction in Low-Resource Settings (2025.findings-emnlp)

Copied to clipboard

Challenge: Large language models have shown remarkable capabilities in open information extraction, but their resource requirements often restrict their deployment in resource-constrained industrial settings.
Approach: They introduce an ultra-lightweight large language model trained on instruction-based samples in Chinese, English, Korean, and Russian.
Outcome: The proposed model outperforms large-scale models with up to 70B parameters, reducing computational resources by 140x and delivering 11x faster response times.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations