Semanlink - [1911.02168] CoKE: Contextualized Knowledge Graph Embedding

Tags:

Au sujet de ce document

sl:arxiv_author :
- Pingping Huang
- Yong Zhu
- Quan Wang
- Songtai Dai
- Wenbin Jiang
- Jing Liu
- Haifeng Wang
- Hua Wu
- Yajuan Lyu
sl:arxiv_firstAuthor : Quan Wang
sl:arxiv_num : 1911.02168
sl:arxiv_published : 2019-11-06T02:27:39Z
sl:arxiv_summary : Knowledge graph embedding, which projects symbolic entities and relations into continuous vector spaces, is gaining increasing attention. Previous methods allow a single static embedding for each entity or relation, ignoring their intrinsic contextual nature, i.e., entities and relations may appear in different graph contexts, and accordingly, exhibit different properties. This work presents Contextualized Knowledge Graph Embedding (CoKE), a novel paradigm that takes into account such contextual nature, and learns dynamic, flexible, and fully contextualized entity and relation embeddings. Two types of graph contexts are studied: edges and paths, both formulated as sequences of entities and relations. CoKE takes a sequence as input and uses a Transformer encoder to obtain contextualized representations. These representations are hence naturally adaptive to the input, capturing contextual meanings of entities and relations therein. Evaluation on a wide variety of public benchmarks verifies the superiority of CoKE in link prediction and path query answering. It performs consistently better than, or at least equally well as current state-of-the-art in almost every case, in particular offering an absolute improvement of 21.0% in H@10 on path query answering. Our code is available at \url{https://github.com/PaddlePaddle/Research/tree/master/KG/CoKE}.@en
sl:arxiv_title : CoKE: Contextualized Knowledge Graph Embedding@en
sl:arxiv_updated : 2020-04-04T07:22:20Z
sl:bookmarkOf : https://arxiv.org/abs/1911.02168
sl:creationDate : 2020-03-22
sl:creationTime : 2020-03-22T17:34:10Z

Infos sur le fichier

Bookmark of: https://arxiv.org/abs/1911.02168

Documents with similar tags (experimental)

[2010.03496] Inductive Entity Representations from Text via Link Prediction

Tags:

BLP "BERT for Link Prediction". Central idea: **training an entity encoder with a
link prediction objective** (using the textual descriptions of entities when computing entity representations - hence not failing with entities unknown in training)

> a method for **learning representations
of entities**, that uses a **pre-trained Transformer** based
architecture as an entity encoder, and
**link prediction training on a knowledge graph
with textual entity descriptions**.

> using entity descriptions,
an entity encoder is trained for link prediction in
a knowledge graph. The encoder can then be used
without fine-tuning to obtain features for entity classification
and information retrieval

Cites [Xie et al](doc:2020/10/representation_learning_of_know) and [Kepler](doc:2020/11/1911_06136_kepler_a_unified_). They claim that their
objective targeted exclusively for link prediction (and not an objective that combines language modeling
and link prediction as Kepler)
performs better than Kepler's more complex one.

2020-11-03 A propos

[1906.01195] Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs

Tags:

2020-04-30 A propos