Papers › Disfluency Detection using Auto-Correlational Neural Networks

Disfluency Detection using Auto-Correlational Neural Networks

28 Aug 2018EMNLP 2018 10arXiv:1808.09092archive 2025-07-28

Paria Jamshid Lou, Peter Anderson, Mark Johnson

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.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

pariajm/deep-disfluency-detector officialmentioned in papertf report
pariajm/ACNN mentioned on GitHubtf report
pariajm/emnlp2018 mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Feature Engineering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Repair

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections