Papers with clustering metrics
Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances (2024.acl-long)
Copied to clipboard
| Challenge: | Existing methods for semantics discovery focus on text, video, and audio, failing to leverage the rich multimodal information in the real world. |
| Approach: | They propose a method to construct augmentation views for multimodal data and use them to perform pre-training to establish well-initialized representations for subsequent clustering. |
| Outcome: | The proposed method improves on benchmark multimodal intent and dialogue act datasets by 2-6% over state-of-the-art methods. |
The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasure (2025.emnlp-main)
Copied to clipboard
| Challenge: | Embedding-based similarity metrics can be influenced by content dimensions and spurious attributes like the text’s source or language. |
| Approach: | They propose a debiasing algorithm that removes observed confounders from encoder representations and removes them from the encoder. |
| Outcome: | The proposed method improves on out-of-distribution benchmarks and on benchmarks, but performance is not affected. |
Spectral Gravity Formant Estimation for Phonetic Segmentation (2026.findings-acl)
Copied to clipboard
| Challenge: | a recent study suggests that end-to-end orthographic approaches miss the mark on time . linguistic applications which require high fidelity in the temporal domain, the loss of timing information is untenable . |
| Approach: | a new algorithm uses spectral gravity to estimate formants for enhanced phonetic segmentation . a deadline-bounded expectation maximization algorithm is proposed to estimate salient speech frequencies . |
| Outcome: | a new algorithm outperforms the state-of-the-art on key clustering metrics . the proposed algorithm generates reasonable alignments across multiple languages with no a priori training. |