No abstract

No abstract

Learning low-dimensional representations for entities and relations in knowledge graphs using contrastive estimation represents a scalable and effective method for inferring connectivity patterns. A crucial aspect of contrastive learning approaches is the choice of corruption distribution that generates hard negative samples, which force the embedding model to learn discriminative representations and find critical characteristics of observed data. While earlier methods either employ too simple corruption distributions, i.e. uniform, yielding easy uninformative negatives or sophisticated adversarial distributions with challenging optimization schemes, they do not explicitly incorporate known graph structure resulting in suboptimal negatives. In this paper, we propose Structure Aware Negative Sampling (SANS), an inexpensive negative sampling strategy that utilizes the rich graph structure by selecting negative samples from a node's k-hop neighborhood. Empirically, we demonstrate that SANS finds high-quality negatives that are highly competitive with SOTA methods, and requires no additional parameters nor difficult adversarial optimization.

Dialogue systems powered by large pretrained language models (LM) exhibit an innate ability to deliver fluent and naturallooking responses. Despite their impressive generation performance, these models can often generate factually incorrect statements impeding their widespread adoption. In this paper, we focus on the task of improving the faithfulness-and thus reduce hallucinationof Neural Dialogue Systems to known facts supplied by a Knowledge Graph (KG). We propose NEURAL PATH HUNTER which follows a generate-then-refine strategy whereby a generated response is amended using the k-hop subgraph of a KG. NEURAL PATH HUNTER leverages a separate token-level fact critic to identify plausible sources of hallucination followed by a refinement stage consisting of a chain of two neural LM's that retrieves correct entities by crafting a query signal that is propagated over the k-hop subgraph. Our proposed model can easily be applied to any dialogue generated responses without retraining the model. We empirically validate our proposed approach on the OpenDialKG dataset (Moon et al., 2019) against a suite of metrics and report a relative improvement of faithfulness over GPT2 dialogue responses by 8.4%.

No abstract