SAM: Semantic Attribute Modulation for Language Modeling and Style Variation
arXiv:1707.00117
Abstract
This paper presents a Semantic Attribute Modulation (SAM) for language modeling and style variation. The semantic attribute modulation includes various document attributes, such as titles, authors, and document categories. We consider two types of attributes, (title attributes and category attributes), and a flexible attribute selection scheme by automatically scoring them via an attribute attention mechanism. The semantic attributes are embedded into the hidden semantic space as the generation inputs. With the attributes properly harnessed, our proposed SAM can generate interpretable texts with regard to the input attributes. Qualitative analysis, including word semantic analysis and attention values, shows the interpretability of SAM. On several typical text datasets, we empirically demonstrate the superiority of the Semantic Attribute Modulated language model with different combinations of document attributes. Moreover, we present a style variation for the lyric generation using SAM, which shows a strong connection between the style variation and the semantic attributes.
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
- Building Natural-Language Generation Systems
- Language Modeling with Gated Convolutional Networks
- Exploring the Limits of Language Modeling
- An Empirical Study of Smoothing Techniques for Language Modeling
- Learning to Generate Reviews and Discovering Sentiment
- Contextual LSTM (CLSTM) models for Large scale NLP tasks
- A Neural Knowledge Language Model
- Context-aware Natural Language Generation with Recurrent Neural Networks
- Document Context Language Models
- Coherent Dialogue with Attention-based Language Models
- Generative Concatenative Nets Jointly Learn to Write and Classify Reviews
- Reference-Aware Language Models