Papers › Syntactic Multi-view Learning for Open Information Extraction

Syntactic Multi-view Learning for Open Information Extraction

5 Dec 2022arXiv:2212.02068archive 2025-07-28

Kuicai Dong, Aixin Sun, Jung-jae Kim, XiaoLi Li

Open Information Extraction (OpenIE) aims to extract relational tuples from open-domain sentences. Traditional rule-based or statistical models have been developed based on syntactic structures of sentences, identified by syntactic parsers. However, previous neural OpenIE models under-explore the useful syntactic information. In this paper, we model both constituency and dependency trees into word-level graphs, and enable neural OpenIE to learn from the syntactic structures. To better fuse heterogeneous information from both graphs, we adopt multi-view learning to capture multiple relationships from them. Finally, the finetuned constituency and dependency representations are aggregated with sentential semantic representations for tuple generation. Experiments show that both constituency and dependency information, and the multi-view learning are effective.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

daviddongkc/smile_oie officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

MULTI-VIEW LEARNINGOpen Information Extraction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Open Information Extraction LSOIE-wiki SMiLe-OIE F1 51.73 #1 of 11 Archive leaderboard report
Open Information Extraction LSOIE-wiki BERT + Dep-GCN - Const-GCN F1 50.21 #2 of 11 Archive leaderboard report
Open Information Extraction LSOIE-wiki BERT + Dep-GCN [?] Const-GCN F1 49.89 #3 of 11 Archive leaderboard report
Open Information Extraction LSOIE-wiki BERT + Const-GCN F1 49.71 #4 of 11 Archive leaderboard report
Open Information Extraction LSOIE-wiki IMoJIE Kolluru et al. (2020) F1 49.24 #5 of 11 Archive leaderboard report
Open Information Extraction LSOIE-wiki BERT + Dep-GCN F1 48.71 #6 of 11 Archive leaderboard report
Open Information Extraction LSOIE-wiki BERT Solawetz and Larson (2021) F1 47.54 #7 of 11 Archive leaderboard report
Open Information Extraction LSOIE-wiki CIGL-OIE + IGL-CA Kolluru et al. (2020) F1 44.75 #8 of 11 Archive leaderboard report
Open Information Extraction LSOIE-wiki GloVe + bi-LSTM + CRF F1 44.48 #9 of 11 Archive leaderboard report
Open Information Extraction LSOIE-wiki GloVe + bi-LSTM Stanovsky et al. (2018) F1 43.9 #10 of 11 Archive leaderboard report
Open Information Extraction LSOIE-wiki CopyAttention Cui et al. (2018) F1 39.52 #11 of 11 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections