3260 papers • 126 benchmarks • 313 datasets
Assigning a unique identity to entities (such as famous individuals, locations, or companies) mentioned in text (Source: Wikipedia).
(Image credit: Papersgraph)
These leaderboards are used to track progress in entity-linking-9
Use these libraries to find entity-linking-9 models and implementations
No subtasks available.
A novel neural network architecture is presented that automatically detects word- and character-level features using a hybrid bidirectional LSTM and CNN architecture, eliminating the need for most feature engineering.
It is shown that strong reading comprehension models pre-trained on large unlabeled data can be used to generalize to unseen entities and proposed domain-adaptive pre-training (DAP) is proposed to address the domain shift problem associated with linking unseen entities in a new domain.
This paper introduces a conceptually simple, scalable, and highly effective BERT-based entity linking model, along with an extensive evaluation of its accuracy-speed trade-off. We present a two-stage zero-shot linking algorithm, where each entity is defined only by a short textual description. The first stage does retrieval in a dense space defined by a bi-encoder that independently embeds the mention context and the entity descriptions. Each candidate is then re-ranked with a cross-encoder, that concatenates the mention and entity text. Experiments demonstrate that this approach is state of the art on recent zero-shot benchmarks (6 point absolute gains) and also on more established non-zero-shot evaluations (e.g. TACKBP-2010), despite its relative simplicity (e.g. no explicit entity embeddings or manually engineered mention tables). We also show that bi-encoder linking is very fast with nearest neighbor search (e.g. linking with 5.9 million candidates in 2 milliseconds), and that much of the accuracy gain from the more expensive cross-encoder can be transferred to the bi-encoder via knowledge distillation. Our code and models are available at https://github.com/facebookresearch/BLINK.
It is found that a shared dense vector index coupled with a seq2seq model is a strong baseline, outperforming more tailor-made approaches for fact checking, open-domain question answering and dialogue, and yielding competitive results on entity linking and slot filling, by generating disambiguated text.
ELQ is presented, a fast end-to-end entity linking model for questions, which uses a biencoder to jointly perform mention detection and linking in one pass, and significantly improves the downstream QA performance of GraphRetriever.
Multimodal Entity Linking (MEL) which aims at linking mentions with multimodal contexts to the referent entities from a knowledge base (e.g., Wikipedia), is an essential task for many multimodal applications. Although much attention has been paid to MEL, the shortcomings of existing MEL datasets including limited contextual topics and entity types, simplified mention ambiguity, and restricted availability, have caused great obstacles to the research and application of MEL. In this paper, we present WikiDiverse, a high-quality human-annotated MEL dataset with diversified contextual topics and entity types from Wikinews, which uses Wikipedia as the corresponding knowledge base. A well-tailored annotation procedure is adopted to ensure the quality of the dataset. Based on WikiDiverse, a sequence of well-designed MEL models with intra-modality and inter-modality attentions are implemented, which utilize the visual information of images more adequately than existing MEL models do. Extensive experimental analyses are conducted to investigate the contributions of different modalities in terms of MEL, facilitating the future research on this task.
The proposed FUDGE model formulates this problem on a graph of text elements (the vertices) and uses a Graph Convolutional Network to predict changes to the graph and is state-of-the-art on the historical NAF dataset.
ReFinED is introduced, an efficient end-to-end entity linking model which uses fine-grained entity types and entity descriptions to perform linking and is an effective and cost-efficient system for extracting entities from web-scale datasets.
BLINKout is proposed, a new BERT-based Entity Linking (EL) method which can identify mentions that do not have corresponding KB entities by matching them to a special NIL entity, with synonym enhancement.
This work treats relations as latent variables in the neural entity-linking model so that the injected structural bias helps to explain regularities in the training data and achieves the best reported scores on the standard benchmark and substantially outperforms its relation-agnostic version.
Adding a benchmark result helps the community track progress.