RSMLP: A light Sampled MLP Structure for Incomplete Utterance Rewrite

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Lunjun, Jiang, Weilai, Wang, Yaonan
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913695822512128
author Liu, Lunjun
Jiang, Weilai
Wang, Yaonan
author_facet Liu, Lunjun
Jiang, Weilai
Wang, Yaonan
contents The Incomplete Utterance Rewriting (IUR) task has garnered significant attention in recent years. Its goal is to reconstruct conversational utterances to better align with the current context, thereby enhancing comprehension. In this paper, we introduce a novel and versatile lightweight method, Rewritten-Sampled MLP (RSMLP). By employing an MLP based architecture with a carefully designed down-sampling strategy, RSMLP effectively extracts latent semantic information between utterances and makes appropriate edits to restore incomplete utterances. Due to its simple yet efficient structure, our method achieves competitive performance on public IUR datasets and in real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2502_12587
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RSMLP: A light Sampled MLP Structure for Incomplete Utterance Rewrite
Liu, Lunjun
Jiang, Weilai
Wang, Yaonan
Computation and Language
Artificial Intelligence
The Incomplete Utterance Rewriting (IUR) task has garnered significant attention in recent years. Its goal is to reconstruct conversational utterances to better align with the current context, thereby enhancing comprehension. In this paper, we introduce a novel and versatile lightweight method, Rewritten-Sampled MLP (RSMLP). By employing an MLP based architecture with a carefully designed down-sampling strategy, RSMLP effectively extracts latent semantic information between utterances and makes appropriate edits to restore incomplete utterances. Due to its simple yet efficient structure, our method achieves competitive performance on public IUR datasets and in real-world applications.
title RSMLP: A light Sampled MLP Structure for Incomplete Utterance Rewrite
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2502.12587