Incremental Natural Language Processing: Challenges, Strategies, and Evaluation
arXiv:1805.12518
Abstract
Incrementality is ubiquitous in human-human interaction and beneficial for human-computer interaction. It has been a topic of research in different parts of the NLP community, mostly with focus on the specific topic at hand even though incremental systems have to deal with similar challenges regardless of domain. In this survey, I consolidate and categorize the approaches, identifying similarities and differences in the computation and data, and show trade-offs that have to be considered. A focus lies on evaluating incremental systems because the standard metrics often fail to capture the incremental properties of a system and coming up with a suitable evaluation scheme is non-trivial.
arXiv commentCOLING 2018 (accepted), camera-ready version
References in corpus (6)
- Neural Machine Translation by Jointly Learning to Align and Translate
- Transition-Based Dependency Parsing with Stack Long Short-Term Memory
- Regularizing and Optimizing LSTM Language Models
- Can neural machine translation do simultaneous translation?
- Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations
- Strongly Incremental Repair Detection