Summary of Keyword-aware Asr Error Augmentation For Robust Dialogue State Tracking, by Jihyun Lee et al.
Keyword-Aware ASR Error Augmentation for Robust Dialogue State Tracking
by Jihyun Lee, Solee Im, Wonjun Lee, Gary Geunbae Lee
First submitted to arxiv on: 10 Sep 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a data augmentation method for improving Dialogue State Tracking (DST) models in task-oriented dialogue systems. The authors highlight the significant drop in DST accuracy when dealing with spoken dialogues due to named entity errors from Automatic Speech Recognition (ASR) systems. To address this issue, they introduce a simple yet effective approach that targets these entities and improves the robustness of DST models. The method uses keyword-highlighted prompts to control error placement and introduces phonetically similar errors, generating sufficient patterns for improved accuracy in noisy ASR environments. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making computer systems better at understanding what people are saying during conversations. When computers try to listen to spoken words, they sometimes get it wrong, which makes it harder for them to understand the conversation. The researchers developed a new way to make the computers better by introducing small mistakes in the words and then correcting those mistakes. This helps the computer systems learn to be more accurate even when people speak clearly but with some errors. |
Keywords
» Artificial intelligence » Data augmentation » Tracking
