Leveraging external knowledge is crucial for achieving high performance in knowledge-intensive tasks, such as question answering. The retrieve-and-read approach is widely adopted for integrating external knowledge into a language model. However, this approach suffers from increased computational cost and latency due to the long context length, which grows proportionally with the number of retrieved knowledge. Furthermore, existing retrieval-augmented models typically retrieve information from a single type of knowledge source, limiting their scalability to diverse knowledge sources with varying structures. In this work, we introduce an efficient memory-augmented transformer called MATTER, designed to retrieve relevant knowledge from multiple heterogeneous knowledge sources. Specifically, our model retrieves and reads from both unstructured sources (paragraphs) and semi-structured sources (QA pairs) in the form of fixed-length neural memories. We demonstrate that our model outperforms existing efficient retrieval-augmented models on popular QA benchmarks in terms of both accuracy and speed. Furthermore, MATTER achieves competitive results compared to conventional read-and-retrieve models while having 100x throughput during inference.

Understanding human language often necessitates understanding entities and their place in a taxonomy of knowledge—their types.Previous methods to learn entity types rely on training classifiers on datasets with coarse, noisy, and incomplete labels. We introduce a method to instill fine-grained type knowledge in language models with text-to-text pre-training on type-centric questions leveraging knowledge base documents and knowledge graphs.We create the WikiWiki dataset: entities and passages from 10M Wikipedia articles linked to the Wikidata knowledge graph with 41K types.Models trained on WikiWiki achieve state-of-the-art performance in zero-shot dialog state tracking benchmarks, accurately infer entity types in Wikipedia articles, and can discover new types deemed useful by human judges.

Fine-tuning a pre-trained language model using annotated data has become the de-facto standard for adapting general-purpose pre-trained models like BERT to downstream tasks. However, given the trend of larger pre-trained models, fine-tuning these models for each downstream task is parameter-inefficient and computationally-expensive deeming this approach sub-optimal for adoption by NLU systems. In recent years, various approaches have been proposed for parameter efficient task adaptation such as Adaptor, Bitfit, Prompt tuning, Prefix tuning etc. However, most of these efforts propose to insert task specific parameters in-between or inside intermediate layers of the pre-trained encoder resulting in higher computational cost due to back-propagation of errors to all layers. To mitigate this issue, we propose a light but efficient, attention based fusion module which computes task-attuned token representations by aggregating intermediate layer representations from a pre-trained network. Our proposed fusion module trains only 0.0009% of total parameters and achieves competitive performance to the standard fine-tuning approach on various tasks. It is also decoupled from the pre-trained network making it efficient during computation and scalable during deployment. Last but not the least, we demonstrate that our proposed attention-fusion mechanism can transfer effectively to different languages for further re-use and expansion.