1 |
MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Network ...
|
|
|
|
Abstract:
We present an instance-based nearest neighbor approach to entity linking. In contrast to most prior entity retrieval systems which represent each entity with a single vector, we build a contextualized mention-encoder that learns to place similar mentions of the same entity closer in vector space than mentions of different entities. This approach allows all mentions of an entity to serve as "class prototypes" as inference involves retrieving from the full set of labeled entity mentions in the training set and applying the nearest mention neighbor's entity label. Our model is trained on a large multilingual corpus of mention pairs derived from Wikipedia hyperlinks, and performs nearest neighbor inference on an index of 700 million mentions. It is simpler to train, gives more interpretable predictions, and outperforms all other systems on two multilingual entity linking benchmarks. ... : Accepted to ACL 2021 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences; Information Retrieval cs.IR; Machine Learning cs.LG; Social and Information Networks cs.SI
|
|
URL: https://dx.doi.org/10.48550/arxiv.2106.07352 https://arxiv.org/abs/2106.07352
|
|
BASE
|
|
Hide details
|
|
3 |
Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Case-based Reasoning for Natural Language Queries over Knowledge Bases ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Benchmarking Scalable Methods for Streaming Cross Document Entity Coreference ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
MOLEMAN: Mention-Only Linking of Entities with a Mention Annotation Network ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Improved Latent Tree Induction with Distant Supervision via Span Constraints ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Scaling Within Document Coreference to Long Texts
|
|
|
|
In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 (2021)
|
|
BASE
|
|
Show details
|
|
11 |
Improved Latent Tree Induction with Distant Supervision via Span Constraints ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
The materials science procedural text corpus: Annotating materials synthesis procedures with shallow semantic structures
|
|
|
|
In: arXiv (2020)
|
|
BASE
|
|
Show details
|
|
13 |
Energy and Policy Considerations for Deep Learning in NLP ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
A Systematic Classification of Knowledge, Reasoning, and Context within the ARC Dataset ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Syntax Helps ELMo Understand Semantics: Is Syntax Still Relevant in a Deep Neural Architecture for SRL? ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Linguistically-Informed Self-Attention for Semantic Role Labeling ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Multilingual Relation Extraction using Compositional Universal Schema ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Learning Dynamic Feature Selection for Fast Sequential Prediction ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Compositional Vector Space Models for Knowledge Base Completion ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|