Entities as Experts: Sparse Memory Access with Entity Supervision
share
We focus on the problem of capturing declarative knowledge in the learned parameters of a language model. We introduce a new model, Entities as Experts (EaE), that can access distinct memories of the entities mentioned in a piece of text. Unlike previous efforts to integrate entity knowledge into sequence models, EaE's entity representations are learned directly from text. These representations capture sufficient knowledge to answer TriviaQA questions such as "Which Dr. Who villain has been played by Roger Delgado, Anthony Ainley, Eric Roberts?". EaE outperforms a Transformer model with 30× the parameters on this task. According to the Lama knowledge probes, EaE also contains more factual knowledge than a similar sized Bert. We show that associating parameters with specific entities means that EaE only needs to access a fraction of its parameters at inference time, and we show that the correct identification, and representation, of entities is essential to EaE's performance. We also argue that the discrete and independent entity representations in EaE make it more modular and interpretable than the Transformer architecture on which it is based.
READ FULL TEXT
