An Extensible Plug-and-Play Method for Multi-Aspect Controllable Text Generation
Recently, multi-aspect controllable text generation that controls the generated text in multiple aspects (e.g., sentiment, topic, and keywords) has attracted increasing attention. Although methods based on parameter efficient tuning like prefix-tuning could achieve multi-aspect controlling in a plug...
Gespeichert in:
Hauptverfasser: | , , , , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Recently, multi-aspect controllable text generation that controls the
generated text in multiple aspects (e.g., sentiment, topic, and keywords) has
attracted increasing attention. Although methods based on parameter efficient
tuning like prefix-tuning could achieve multi-aspect controlling in a
plug-and-play way, the mutual interference of multiple prefixes leads to
significant degeneration of constraints and limits their extensibility to
training-time unseen aspect combinations. In this work, we provide a
theoretical lower bound for the interference and empirically found that the
interference grows with the number of layers where prefixes are inserted. Based
on these analyses, we propose using trainable gates to normalize the
intervention of prefixes to restrain the growing interference. As a result,
controlling training-time unseen combinations of aspects can be realized by
simply concatenating corresponding plugins such that new constraints can be
extended at a lower cost. In addition, we propose a unified way to process both
categorical and free-form constraints. Experiments on text generation and
machine translation demonstrate the superiority of our approach over baselines
on constraint accuracy, text quality, and extensibility. |
---|---|
DOI: | 10.48550/arxiv.2212.09387 |