A Unified Encoder-Decoder Framework with Entity Memory
This addresses computational inefficiencies in entity-intensive NLP tasks like question answering and generation, but it appears incremental as it builds on existing encoder-decoder and memory-based approaches.
The authors tackled the problem of incorporating entity knowledge into encoder-decoder frameworks for NLP tasks by proposing EDMem, a unified framework with an entity memory, which outperformed existing memory-based and non-memory models in experiments.
Entities, as important carriers of real-world knowledge, play a key role in many NLP tasks. We focus on incorporating entity knowledge into an encoder-decoder framework for informative text generation. Existing approaches tried to index, retrieve, and read external documents as evidence, but they suffered from a large computational overhead. In this work, we propose an encoder-decoder framework with an entity memory, namely EDMem. The entity knowledge is stored in the memory as latent representations, and the memory is pre-trained on Wikipedia along with encoder-decoder parameters. To precisely generate entity names, we design three decoding methods to constrain entity generation by linking entities in the memory. EDMem is a unified framework that can be used on various entity-intensive question answering and generation tasks. Extensive experimental results show that EDMem outperforms both memory-based auto-encoder models and non-memory encoder-decoder models.