Graph Adaptation Network with Domain-Specific Word Alignment for Cross-Domain Relation Extraction
release_bjjnzbqdabfspmpfl7nkabtn7a
by
Wang Zhe, 博 闫, chunhua wu, Bin Wu, Xiujuan Wang, Kangfeng Zheng
Abstract
Cross-domain relation extraction has become an essential approach when target domain lacking labeled data. Most existing works adapted relation extraction models from the source domain to target domain through aligning sequential features, but failed to transfer non-local and non-sequential features such as word co-occurrence which are also critical for cross-domain relation extraction. To address this issue, in this paper, we propose a novel tripartite graph architecture to adapt non-local features when there is no labeled data in the target domain. The graph uses domain words as nodes to model the co-occurrence relation between domain-specific words and domain-independent words. Through graph convolutions on the tripartite graph, the information of domain-specific words is propagated so that the word representation can be fine-tuned to align domain-specific features. In addition, unlike the traditional graph structure, the weights of edges innovatively combine fixed weight and dynamic weight, to capture the global non-local features and avoid introducing noise to word representation. Experiments on three domains of ACE2005 datasets show that our method outperforms the state-of-the-art models by a big margin.
In application/xml+jats
format
Archived Files and Locations
application/pdf 1.1 MB
file_4m5n7j2wgngxbjon4ku7piywkq
|
res.mdpi.com (publisher) web.archive.org (webarchive) |
Open Access Publication
In DOAJ
In ISSN ROAD
In Keepers Registry
ISSN-L:
1424-8220
access all versions, variants, and formats of this works (eg, pre-prints)
Crossref Metadata (via API)
Worldcat
SHERPA/RoMEO (journal policies)
wikidata.org
CORE.ac.uk
Semantic Scholar
Google Scholar