Vector of Locally Aggregated Embeddings for Text Representation

Hadi Amiri, Mitra Mohtarami


Abstract
We present Vector of Locally Aggregated Embeddings (VLAE) for effective and, ultimately, lossless representation of textual content. Our model encodes each input text by effectively identifying and integrating the representations of its semantically-relevant parts. The proposed model generates high quality representation of textual content and improves the classification performance of current state-of-the-art deep averaging networks across several text classification tasks.
Anthology ID:
N19-1143
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1408–1414
Language:
URL:
https://aclanthology.org/N19-1143
DOI:
10.18653/v1/N19-1143
Bibkey:
Cite (ACL):
Hadi Amiri and Mitra Mohtarami. 2019. Vector of Locally Aggregated Embeddings for Text Representation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1408–1414, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Vector of Locally Aggregated Embeddings for Text Representation (Amiri & Mohtarami, NAACL 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/N19-1143.pdf
Data
IMDb Movie Reviews