Disfluency Detection using Auto-Correlational Neural Networks
| Autor: | Mark Johnson, Paria Jamshid Lou, Peter Anderson |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Feature engineering
FOS: Computer and information sciences Parsing Dependency (UML) Computer Science - Computation and Language Artificial neural network Computer science Speech recognition 02 engineering and technology computer.software_genre Convolutional neural network Task (project management) 030507 speech-language pathology & audiology 03 medical and health sciences Feature (computer vision) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Language model 0305 other medical science computer Computation and Language (cs.CL) |
| Zdroj: | EMNLP Macquarie University |
| DOI: | 10.48550/arxiv.1808.09092 |
| Popis: | In recent years, the natural language processing community has moved away from task-specific feature engineering, i.e., researchers discovering ad-hoc feature representations for various tasks, in favor of general-purpose methods that learn the input representation by themselves. However, state-of-the-art approaches to disfluency detection in spontaneous speech transcripts currently still depend on an array of hand-crafted features, and other representations derived from the output of pre-existing systems such as language models or dependency parsers. As an alternative, this paper proposes a simple yet effective model for automatic disfluency detection, called an auto-correlational neural network (ACNN). The model uses a convolutional neural network (CNN) and augments it with a new auto-correlation operator at the lowest layer that can capture the kinds of “rough copy” dependencies that are characteristic of repair disfluencies in speech. In experiments, the ACNN model outperforms the baseline CNN on a disfluency detection task with a 5% increase in f-score, which is close to the previous best result on this task. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|