Reference-Aware Language Models
arXiv:1611.01628
Abstract
We propose a general class of language models that treat reference as an explicit stochastic latent variable. This architecture allows models to create mentions of entities and their attributes by accessing external databases (required by, e.g., dialogue generation and recipe generation) and internal state (required by, e.g. language models which are aware of coreference). This facilitates the incorporation of information that can be accessed in predictable locations in databases or discourse context, even when the targets of the reference may be rare words. Experiments on three tasks shows our model variants based on deterministic attention.
emnlp camera ready
References in corpus (8)
- Exploring the Limits of Language Modeling
- Pointer Sentinel Mixture Models
- Deep Reinforcement Learning for Dialogue Generation
- A Network-based End-to-End Trainable Task-oriented Dialogue System
- End-to-end LSTM-based dialog control optimized with supervised and reinforcement learning
- Learning End-to-End Goal-Oriented Dialog
- Pointing the Unknown Words
- Learning Global Features for Coreference Resolution
Cited by in corpus (8)
- Challenges in Data-to-Document Generation
- Linguistic Knowledge as Memory for Recurrent Neural Networks
- Generative Encoder-Decoder Models for Task-Oriented Spoken Dialog Systems with Chatting Capability
- Dynamic Entity Representations in Neural Language Models
- Knowledge-Augmented Language Model and its Application to Unsupervised Named-Entity Recognition
- Data-to-Text Generation with Style Imitation
- SAM: Semantic Attribute Modulation for Language Modeling and Style Variation
- Incorporating Relevant Knowledge in Context Modeling and Response Generation