-
Joint Multilingual Supervision for Cross-lingual Entity Linking
Cross-lingual Entity Linking (XEL) aims to ground entity mentions writte...
read it
-
Multilingual Autoregressive Entity Linking
We present mGENRE, a sequence-to-sequence system for the Multilingual En...
read it
-
MAG: A Multilingual, Knowledge-base Agnostic and Deterministic Entity Linking Approach
Entity linking has recently been the subject of a significant body of re...
read it
-
Entity Linking in 40 Languages using MAG
A plethora of Entity Linking (EL) approaches has recently been developed...
read it
-
Learning Dense Representations for Entity Retrieval
We show that it is feasible to perform entity linking by training a dual...
read it
-
Linking Entities to Unseen Knowledge Bases with Arbitrary Schemas
In entity linking, mentions of named entities in raw text are disambigua...
read it
-
High-Throughput and Language-Agnostic Entity Disambiguation and Linking on User Generated Data
The Entity Disambiguation and Linking (EDL) task matches entity mentions...
read it
Entity Linking in 100 Languages
We propose a new formulation for multilingual entity linking, where language-specific mentions resolve to a language-agnostic Knowledge Base. We train a dual encoder in this new setting, building on prior work with improved feature representation, negative mining, and an auxiliary entity-pairing task, to obtain a single entity retrieval model that covers 100+ languages and 20 million entities. The model outperforms state-of-the-art results from a far more limited cross-lingual linking task. Rare entities and low-resource languages pose challenges at this large-scale, so we advocate for an increased focus on zero- and few-shot evaluation. To this end, we provide Mewsli-9, a large new multilingual dataset (http://goo.gle/mewsli-dataset) matched to our setting, and show how frequency-based analysis provided key insights for our model and training enhancements.
READ FULL TEXT
Comments
There are no comments yet.