natural-language-processing-11

Knowledge Base Population

3260 papers • 126 benchmarks • 313 datasets

Knowledge base population is the task of filling the incomplete elements of a given knowledge base by automatically processing a large corpus of text.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in knowledge-base-population-22

Trend

Dataset

Best Model

Actions

LM-KBC 2023

Libraries

i

Use these libraries to find knowledge-base-population-22 models and implementations

Datasets

Perlex

FarsBase-KBP

LM-KBC 2023

Subtasks

No subtasks available.

Most implemented papers

Joint Matrix-Tensor Factorization for Knowledge Base Inference

Prachi Jain, Mausam, Soumen Chakrabarti, Shikhar Murty•Thu Jun 01 2017

An extensive evaluation to compare popular KB inference models across popular datasets in the literature and proposes an extension to MF models so that they can better handle out-of-vocabulary (OOV) entity pairs, and develops a novel combination of TF and MF models.

0

Content

0

Paper Graph

Position-aware Attention and Supervised Data Improve Slot Filling

Christopher D. Manning, Yuhao Zhang, Danqi Chen, Gabor Angeli, Victor Zhong•Thu Aug 31 2017

An effective new model is proposed, which combines an LSTM sequence model with a form of entity position-aware attention that is better suited to relation extraction that builds TACRED, a large supervised relation extraction dataset obtained via crowdsourcing and targeted towards TAC KBP relations.

951 0

Paper Graph

Information Extraction of Clinical Trial Eligibility Criteria

Anuj Kumar, Yitong Tseo, A. Mohamed, MD Freddy Abnousi, M. Salkola, F. Abnousi•Thu Jun 11 2020

This work investigates an information extraction approach for grounding criteria from trials in ClinicalTrials(dot)gov to a shared knowledge base, and concludes that this system is competitive with Criteria2Query, which it is view as the current state-of-the-art in criteria extraction.

28 0

Paper Graph

Zero-shot Slot Filling with DPR and RAG

A. Gliozzo, Michael R. Glass, Gaetano Rossiello•Fri Apr 16 2021

Several strategies are described to improve the retriever and the generator of RAG in order to make it a better slot filler, which reached the top-1 position on the KILT leaderboard on both T-REx and zsRE dataset with a large margin.

1 0

Paper Graph

Benchmarking Commonsense Knowledge Base Population with an Effective Evaluation Dataset

Bin He, Hongming Zhang, Yangqiu Song, Weiqi Wang, Tianqing Fang, Sehyun Choi•Wed Sep 15 2021

Reasoning over commonsense knowledge bases (CSKB) whose elements are in the form of free-text is an important yet hard task in NLP. While CSKB completion only fills the missing links within the domain of the CSKB, CSKB population is alternatively proposed with the goal of reasoning unseen assertions from external resources. In this task, CSKBs are grounded to a large-scale eventuality (activity, state, and event) graph to discriminate whether novel triples from the eventuality graph are plausible or not. However, existing evaluations on the population task are either not accurate (automatic evaluation with randomly sampled negative examples) or of small scale (human annotation). In this paper, we benchmark the CSKB population task with a new large-scale dataset by first aligning four popular CSKBs, and then presenting a high-quality human-annotated evaluation set to probe neural models’ commonsense reasoning ability. We also propose a novel inductive commonsense reasoning model that reasons over graphs. Experimental results show that generalizing commonsense reasoning on unseen assertions is inherently a hard task. Models achieving high accuracy during training perform poorly on the evaluation set, with a large gap between human performance. We will make the data publicly available for future contributions. Codes and data are available at https://github.com/HKUST-KnowComp/CSKB-Population.

33 0

Paper Graph

TIMEN: An Open Temporal Expression Normalisation Resource

H. Llorens, Leon Derczynski, R. Gaizauskas, E. Boró•Mon Apr 30 2012

TIMEN is a community-driven tool for temporal expression normalisation derived from current best approaches and is an independent tool, enabling easy integration in existing systems and inviting the IE community to contribute to a knowledge base in order to solve the temporal expressionnormalisation problem.

68 0

Paper Graph

Entity Disambiguation with Web Links

Ben Hachey, Andrew Chisholm•Wed Mar 04 2015

This work explores whether web links can replace a curated encyclopaedia, obtaining entity prior, name, context, and coherence models from a corpus of web pages with links to Wikipedia.

83 0

Paper Graph

Knowledge-Guided Linguistic Rewrites for Inference Rule Verification

Prachi Jain, Mausam•Tue May 31 2016

This work investigates knowledge-guided linguistic rewrites as a secondary source of evidence and finds that they can vastly improve the quality of inference rule corpora, obtaining 27 to 33 point precision improvement while retaining substantial recall.

9 0

Paper Graph

TweeTime : A Minimally Supervised Method for Recognizing and Normalizing Time Expressions in Twitter

Alan Ritter, Jeniya Tabassum, Wei Xu•Sun Jul 31 2016

TweedTIME, a temporal tagger for recognizing and normalizing time expressions in Twitter, is described, a minimally supervised method that learns from large quantities of unlabeled data and requires no hand-engineered rules or hand-annotated training corpora.

17 0

Paper Graph

SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications

A. McCallum, Isabelle Augenstein, Sebastian Riedel, Mrinal Das, Lakshmi Vikraman•Sun Apr 09 2017

The SemEval task of extracting keyphrases and relations between them from scientific documents, which is crucial for understanding which publications describe which processes, tasks and materials, is described.

364 0

Paper Graph

Adding a benchmark result helps the community track progress.