@prefix rdf:   <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
@prefix sl:    <http://www.semanlink.net/2001/00/semanlink-schema#> .
@prefix skos:  <http://www.w3.org/2004/02/skos/core#> .
@prefix rdfs:  <http://www.w3.org/2000/01/rdf-schema#> .
@prefix tag:   <http://www.semanlink.net/tag/> .
@prefix foaf:  <http://xmlns.com/foaf/0.1/> .
@prefix dc:    <http://purl.org/dc/elements/1.1/> .

tag:thewebconf_2021  a    sl:Tag ;
        rdfs:isDefinedBy  <http://semanlink.net/tag/thewebconf_2021.n3> ;
        skos:broader      tag:www_conference ;
        skos:prefLabel    "TheWebConf 2021" ;
        foaf:page         tag:thewebconf_2021.html .

tag:www_conference  a   sl:Tag ;
        skos:prefLabel  "TheWebConf" .

tag:good  a             sl:Tag ;
        skos:prefLabel  "Good" .

tag:link_prediction  a  sl:Tag ;
        skos:prefLabel  "Link Prediction" .

tag:blp  a              sl:Tag ;
        skos:prefLabel  "BLP" .

tag:discute_avec_raphael
        a               sl:Tag ;
        skos:prefLabel  "Discuté avec Raphaël" .

tag:attention_knowledge_graphs
        a               sl:Tag ;
        skos:prefLabel  "Attention + Knowledge Graphs" .

tag:text_aware_kg_embedding
        a               sl:Tag ;
        skos:prefLabel  "Text-Aware KG embedding" .

tag:arxiv_doc  a        sl:Tag ;
        skos:prefLabel  "Arxiv Doc" .

tag:entity_embeddings
        a               sl:Tag ;
        skos:prefLabel  "Entity embeddings" .

<http://www.semanlink.net/doc/2020/11/2010_03496_inductive_entity_r>
        dc:title         "[2010.03496] Inductive Entity Representations from Text via Link Prediction" ;
        sl:comment       "BLP \"BERT for Link Prediction\". Central idea: **training an entity encoder with a\r\nlink prediction objective** (using the textual descriptions of entities when computing entity representations - hence not failing with entities unknown in training)\r\n\r\n> a method for **learning representations\r\nof entities**, that uses a **pre-trained Transformer** based\r\narchitecture as an entity encoder, and\r\n**link prediction training on a knowledge graph\r\nwith textual entity descriptions**.\r\n\r\n> using entity descriptions,\r\nan entity encoder is trained for link prediction in\r\na knowledge graph. The encoder can then be used\r\nwithout fine-tuning to obtain features for entity classification\r\nand information retrieval\r\n\r\nCites [Xie et al](doc:2020/10/representation_learning_of_know) and [Kepler](doc:2020/11/1911_06136_kepler_a_unified_). They claim that their\r\nobjective targeted exclusively for link prediction (and not an objective that combines language modeling\r\nand link prediction as Kepler)\r\nperforms better than Kepler's more complex one.\r\n\r\n[Github](https://github.com/dfdazac/blp)" ;
        sl:creationDate  "2020-11-03" ;
        sl:tag           tag:good , tag:thewebconf_2021 , tag:attention_knowledge_graphs , tag:link_prediction , tag:entity_embeddings , tag:discute_avec_raphael , tag:arxiv_doc , tag:blp , tag:text_aware_kg_embedding .