Entity Disambiguation

Autoregressive Entity Retrieval

F. Petroni, Sebastian Riedel, Nicola De Cao, Gautier Izacard•Thu Oct 01 2020

Entities are at the center of how we represent and aggregate knowledge. For instance, Encyclopedias such as Wikipedia are structured by entities (e.g., one per article). The ability to retrieve such entities given a query is fundamental for knowledge-intensive tasks such as entity linking and open-domain question answering. One way to understand current approaches is as classifiers among atomic labels, one for each entity. Their weight vectors are dense entity representations produced by encoding entity information such as descriptions. This approach leads to several shortcomings: i) context and entity affinity is mainly captured through a vector dot product, potentially missing fine-grained interactions between the two; ii) a large memory footprint is needed to store dense representations when considering large entity sets; iii) an appropriately hard set of negative data has to be subsampled at training time. We propose GENRE, the first system that retrieves entities by generating their unique names, left to right, token-by-token in an autoregressive fashion, and conditioned on the context. This enables to mitigate the aforementioned technical issues: i) the autoregressive formulation allows us to directly capture relations between context and entity name, effectively cross encoding both; ii) the memory footprint is greatly reduced because the parameters of our encoder-decoder architecture scale with vocabulary size, not entity count; iii) the exact softmax loss can be efficiently computed without the need to subsample negative data. We show the efficacy of the approach with more than 20 datasets on entity disambiguation, end-to-end entity linking and document retrieval tasks, achieving new SOTA, or very competitive results while using a tiny fraction of the memory of competing systems. Finally, we demonstrate that new entities can be added by simply specifying their unambiguous name.

518 0

Paper Graph

Entity Disambiguation | State-of-the-Art

Benchmarks

Libraries

Datasets

Subtasks

Most implemented papers

Deep Joint Entity Disambiguation with Local Neural Attention

Content

EntEval: A Holistic Evaluation Benchmark for Entity Representations

Learning Dynamic Context Augmentation for Global Entity Linking

Autoregressive Entity Retrieval

Biomedical Interpretable Entity Representations

ReFinED: An Efficient Zero-shot-capable Approach to End-to-End Entity Linking

Improving Entity Disambiguation by Reasoning over a Knowledge Base

Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning

Entity Disambiguation with Web Links

Studying the Wikipedia Hyperlink Graph for Relatedness and Disambiguation