Soft Contextualized Encoder For User Defined Text Classification
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911357607084032 |
|---|---|
| author | Maheshwari, Charu Raina, Vyas |
| author_facet | Maheshwari, Charu Raina, Vyas |
| contents | User-Defined Text Classification (UDTC) considers the challenge of classifying input text to user-specified, previously unseen classes, a setting that arises frequently in real-world applications such as enterprise analytics, content moderation, and domain-specific information retrieval. We propose a soft-contextualized encoder architecture for UDTC which contextualizes each candidate label with the label set and a static soft prompt representation of the input query. Training on diverse, multi-source datasets enables the model to generalize effectively to zero-shot classification over entirely unseen topic sets drawn from arbitrary domains. We evaluate the proposed architecture both on held-out in-distribution test data and on multiple unseen UDTC benchmarks. Across datasets, the model achieves state-of-the-art performance, consistently outperforming or matching the baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03450 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Soft Contextualized Encoder For User Defined Text Classification Maheshwari, Charu Raina, Vyas Machine Learning Artificial Intelligence User-Defined Text Classification (UDTC) considers the challenge of classifying input text to user-specified, previously unseen classes, a setting that arises frequently in real-world applications such as enterprise analytics, content moderation, and domain-specific information retrieval. We propose a soft-contextualized encoder architecture for UDTC which contextualizes each candidate label with the label set and a static soft prompt representation of the input query. Training on diverse, multi-source datasets enables the model to generalize effectively to zero-shot classification over entirely unseen topic sets drawn from arbitrary domains. We evaluate the proposed architecture both on held-out in-distribution test data and on multiple unseen UDTC benchmarks. Across datasets, the model achieves state-of-the-art performance, consistently outperforming or matching the baselines. |
| title | Soft Contextualized Encoder For User Defined Text Classification |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2601.03450 |