We study the problem of injecting knowledge into large pre-trained models like BERT and RoBERTa. Existing methods typically update the original parameters of pre-trained models when injecting knowledge. However, when multiple kinds of knowledge are injected, the historically injected knowledge would be flushed away. To address this, we propose K-ADAPTER, a framework that retains the original parameters of the pre-trained model fixed and supports the development of versatile knowledge-infused model. Taking RoBERTa as the backbone model, K-ADAPTER has a neural adapter for each kind of infused knowledge, like a plug-in connected to RoBERTa. There is no information flow between different adapters, thus multiple adapters can be efficiently trained in a distributed way. As a case study, we inject two kinds of knowledge in this work, including (1) factual knowledge obtained from automatically aligned texttriplets on Wikipedia and Wikidata and (2) linguistic knowledge obtained via dependency parsing. Results on three knowledge-driven tasks, including relation classification, entity typing, and question answering, demonstrate that each adapter improves the performance and the combination of both adapters brings further improvements. Further analysis indicates that K-ADAPTER captures versatile knowledge than RoBERTa. 1

We study the problem of injecting knowledge into large pre-trained models like BERT and RoBERTa. Existing methods typically update the original parameters of pre-trained models when injecting knowledge. However, when multiple kinds of knowledge are injected, they may suffer from catastrophic forgetting. To address this, we propose K-ADAPTER, which remains the original parameters of the pre-trained model fixed and supports continual knowledge infusion. Taking RoBERTa as the pre-trained model, K-ADAPTER has a neural adapter for each kind of infused knowledge, like a plug-in connected to RoBERTa. There is no information flow between different adapters, thus different adapters are efficiently trained in a distributed way. We inject two kinds of knowledge, including factual knowledge obtained from automatically aligned text-triplets on Wikipedia and Wikidata, and linguistic knowledge obtained from dependency parsing. Results on three knowledge-driven tasks (total six datasets) including relation classification, entity typing and question answering demonstrate that each adapter improves the performance, and the combination of both adapters brings further improvements. Probing experiments further show that K-ADAPTER captures richer factual and commonsense knowledge than RoBERTa.

No abstract

Visual storytelling aims at generating a story from an image stream. Most existing methods tend to represent images directly with the extracted high-level features, which is not intuitive and difficult to interpret. We argue that translating each image into a graph-based semantic representation, i.e., scene graph, which explicitly encodes the objects and relationships detected within image, would benefit representing and describing images. To this end, we propose a novel graph-based architecture for visual storytelling by modeling the two-level relationships on scene graphs. In particular, on the within-image level, we employ a Graph Convolution Network (GCN) to enrich local fine-grained region representations of objects on scene graphs. To further model the interaction among images, on the cross-images level, a Temporal Convolution Network (TCN) is utilized to refine the region representations along the temporal dimension. Then the relation-aware representations are fed into the Gated Recurrent Unit (GRU) with attention mechanism for story generation. Experiments are conducted on the public visual storytelling dataset. Automatic and human evaluation results indicate that our method achieves state-of-the-art.