Strongly Incremental Repair Detection

2014-08-28 · EMNLP 2014 10 · Julian Hough, Matthew Purver

We present STIR (STrongly Incremental Repair detection), a system that detects speech repairs and edit terms on transcripts incrementally with minimal latency. STIR uses information-theoretic measures from n-gram models as its principal decision features in a pipeline of classifiers detecting the different stages of repairs. Results on the Switchboard disfluency tagged corpus show utterance-final accuracy on a par with state-of-the-art incremental repair detection methods, but with better incremental accuracy, faster time-to-detection and less computational overhead. We evaluate its performance using incremental metrics and propose new repair processing evaluation standards.

📄 PDF Abstract BibTeX arXiv:1408.6788

Code (0)

등록된 구현이 없습니다.

Time Series Data Cleaning: From Anomaly Detection to Anomaly Repairing

2017-06-10 · Proceedings of the VLDB Endowment 2017 6 · Aoqian Zhang, Shaoxu Song, Jian-Min Wang, Philip S. Yu

Errors are prevalent in time series data, such as GPS trajectories or sensor readings. Existing methods focus more on anomaly detection but not on repairing the detected anomalies. By simply filtering out the dirty data …

Anomaly Detection parameter estimation Time Series Time Series Analysis+1

Joint Incremental Disfluency Detection and Dependency Parsing

2014-01-01 · TACL 2014 1 · Matthew Honnibal, Mark Johnson

We present an incremental dependency parsing model that jointly performs disfluency detection. The model handles speech repairs using a novel non-monotonic transition system, and includes several novel classes of feature…

Dependency Parsing Speech Recognition Transition-Based Dependency Parsing

Incremental Satisfiability Modulo Theory for Verification of Deep Neural Networks

2023-02-10 · Pengfei Yang, Zhiming Chi, Zongxin Liu, Mengyu Zhao 외

Constraint solving is an elementary way for verification of deep neural networks (DNN). In the domain of AI safety, a DNN might be modified in its structure and parameters for its repair or attack. For such situations, w…

valid

VISTA: Knowledge-Driven Vessel Trajectory Imputation with Repair Provenance

2026-01-11 · Hengyu Liu, Tianyi Li, Haoyu Wang, Kristian Torp 외 arxiv

Repairing incomplete trajectory data is essential for downstream spatio-temporal applications. Yet, existing repair methods focus solely on reconstruction without documenting the reasoning behind repair decisions, underm…

Anomaly Detection

Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding

2026-06-29 · Tianyu Wang, Gourav Rattihalli, Aditya Dhakal, Junbo Li 외 arxiv

Dynamic sparse attention (DSA) accelerates long-context LLM decoding by attending to only the top-K KV blocks relevant to each query, but it introduces a serialized selection-to-attention dependency that emerges as a new…