Summary of Ronid: New Intent Discovery with Generated-reliable Labels and Cluster-friendly Representations, by Shun Zhang et al.
RoNID: New Intent Discovery with Generated-Reliable Labels and Cluster-friendly Representations
by Shun Zhang, Chaoran Yan, Jian Yang, Changyu Ren, Jiaqi Bai, Tongliang Li, Zhoujun Li
First submitted to arxiv on: 13 Apr 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
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 proposes Robust New Intent Discovery (RoNID), an approach to identify known and novel intent groups in open-world scenarios. Current methods are hindered by inaccurate pseudo-labels and poor representation learning, leading to a negative feedback loop that degrades performance. RoNID optimizes the NID framework using an EM-style method, focusing on reliable pseudo-label generation and cluster-friendly representations. The approach consists of two modules: pseudo-label generation and representation learning. The former assigns reliable synthetic labels by solving an optimal transport problem, while the latter combines intra-cluster and inter-cluster contrastive learning to produce discriminative features. Experimental results demonstrate RoNID’s effectiveness, outperforming previous state-of-the-art methods by 1-4 points. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a new way to understand what people are trying to do online. Current approaches have some big problems that make them not very good. The new method, called RoNID, tries to fix these issues by giving the computer better information and helping it learn more accurately. It does this by breaking down the task into two parts: making sure the labels (or categories) are correct and learning how to recognize patterns in the data. This approach is tested on different datasets and shows a big improvement over previous methods. |
Keywords
* Artificial intelligence * Representation learning
