A Neural Knowledge Language Model
This addresses the problem of factual knowledge acquisition in language models for natural language processing applications, representing a novel method for a known bottleneck.
The paper tackles the limitation of language models in encoding factual knowledge by proposing a Neural Knowledge Language Model (NKLM) that integrates symbolic knowledge from knowledge graphs with RNN language models, resulting in significant performance improvements and a reduction in unknown word generation.
Current language models have a significant limitation in the ability to encode and decode factual knowledge. This is mainly because they acquire such knowledge from statistical co-occurrences although most of the knowledge words are rarely observed. In this paper, we propose a Neural Knowledge Language Model (NKLM) which combines symbolic knowledge provided by the knowledge graph with the RNN language model. By predicting whether the word to generate has an underlying fact or not, the model can generate such knowledge-related words by copying from the description of the predicted fact. In experiments, we show that the NKLM significantly improves the performance while generating a much smaller number of unknown words.