@inproceedings{broscheit-etal-2020-predict,
title = "Can We Predict New Facts with Open Knowledge Graph Embeddings? A Benchmark for Open Link Prediction",
author = "Broscheit, Samuel and
Gashteovski, Kiril and
Wang, Yanjie and
Gemulla, Rainer",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.209",
doi = "10.18653/v1/2020.acl-main.209",
pages = "2296--2308",
abstract = "Open Information Extraction systems extract ({``}subject text{''}, {``}relation text{''}, {``}object text{''}) triples from raw text. Some triples are textual versions of facts, i.e., non-canonicalized mentions of entities and relations. In this paper, we investigate whether it is possible to infer new facts directly from the open knowledge graph without any canonicalization or any supervision from curated knowledge. For this purpose, we propose the open link prediction task,i.e., predicting test facts by completing ({``}subject text{''}, {``}relation text{''}, ?) questions. An evaluation in such a setup raises the question if a correct prediction is actually a new fact that was induced by reasoning over the open knowledge graph or if it can be trivially explained. For example, facts can appear in different paraphrased textual variants, which can lead to test leakage. To this end, we propose an evaluation protocol and a methodology for creating the open link prediction benchmark OlpBench. We performed experiments with a prototypical knowledge graph embedding model for openlink prediction. While the task is very challenging, our results suggests that it is possible to predict genuinely new facts, which can not be trivially explained.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="broscheit-etal-2020-predict">
<titleInfo>
<title>Can We Predict New Facts with Open Knowledge Graph Embeddings? A Benchmark for Open Link Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Samuel</namePart>
<namePart type="family">Broscheit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiril</namePart>
<namePart type="family">Gashteovski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanjie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rainer</namePart>
<namePart type="family">Gemulla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Open Information Extraction systems extract (“subject text”, “relation text”, “object text”) triples from raw text. Some triples are textual versions of facts, i.e., non-canonicalized mentions of entities and relations. In this paper, we investigate whether it is possible to infer new facts directly from the open knowledge graph without any canonicalization or any supervision from curated knowledge. For this purpose, we propose the open link prediction task,i.e., predicting test facts by completing (“subject text”, “relation text”, ?) questions. An evaluation in such a setup raises the question if a correct prediction is actually a new fact that was induced by reasoning over the open knowledge graph or if it can be trivially explained. For example, facts can appear in different paraphrased textual variants, which can lead to test leakage. To this end, we propose an evaluation protocol and a methodology for creating the open link prediction benchmark OlpBench. We performed experiments with a prototypical knowledge graph embedding model for openlink prediction. While the task is very challenging, our results suggests that it is possible to predict genuinely new facts, which can not be trivially explained.</abstract>
<identifier type="citekey">broscheit-etal-2020-predict</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.209</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.209</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>2296</start>
<end>2308</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can We Predict New Facts with Open Knowledge Graph Embeddings? A Benchmark for Open Link Prediction
%A Broscheit, Samuel
%A Gashteovski, Kiril
%A Wang, Yanjie
%A Gemulla, Rainer
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F broscheit-etal-2020-predict
%X Open Information Extraction systems extract (“subject text”, “relation text”, “object text”) triples from raw text. Some triples are textual versions of facts, i.e., non-canonicalized mentions of entities and relations. In this paper, we investigate whether it is possible to infer new facts directly from the open knowledge graph without any canonicalization or any supervision from curated knowledge. For this purpose, we propose the open link prediction task,i.e., predicting test facts by completing (“subject text”, “relation text”, ?) questions. An evaluation in such a setup raises the question if a correct prediction is actually a new fact that was induced by reasoning over the open knowledge graph or if it can be trivially explained. For example, facts can appear in different paraphrased textual variants, which can lead to test leakage. To this end, we propose an evaluation protocol and a methodology for creating the open link prediction benchmark OlpBench. We performed experiments with a prototypical knowledge graph embedding model for openlink prediction. While the task is very challenging, our results suggests that it is possible to predict genuinely new facts, which can not be trivially explained.
%R 10.18653/v1/2020.acl-main.209
%U https://aclanthology.org/2020.acl-main.209
%U https://doi.org/10.18653/v1/2020.acl-main.209
%P 2296-2308
Markdown (Informal)
[Can We Predict New Facts with Open Knowledge Graph Embeddings? A Benchmark for Open Link Prediction](https://aclanthology.org/2020.acl-main.209) (Broscheit et al., ACL 2020)
ACL