Knowledge Injection into Dialogue Generation via Language Models
This addresses the issue of knowledge scarcity in dialogue systems for online chatting, though it is incremental as it builds on existing knowledge injection techniques.
The paper tackles the problem of dialogue generation models producing generic responses due to limited external knowledge, proposing a two-stage method that injects knowledge via a language model to improve coherence and informativeness.
Dialogue generation has been successfully learned from scratch by neural networks, but tends to produce the same general response, e.g., "what are you talking about?", in many conversations. To reduce this homogeneity, external knowledge such as the speaker's profile and domain knowledge is applied as an additional condition to diversify a model's output. The required knowledge to develop an effective conversation, however, is not always available, which is different from prior work's assumption that a model always has acquired sufficient knowledge before chatting. This problem can be detrimental when applying a dialogue model like this chatting online with unconstrained people and topics, because the model does not have the needed knowledge. To address this problem, we propose InjK, which is a two-stage approach to inject knowledge into a dialogue generation model. First, we train a large-scale language model and query it as textual knowledge. Second, we frame a dialogue generation model to sequentially generate textual knowledge and a corresponding response. Empirically, when a dialogue generation model can only access limited knowledge, our method outperforms prior work by producing more coherent and informative responses.