Cross-Topic Distributional Semantic Representations Via Unsupervised Mappings
2019
Conference Paper
In traditional Distributional Semantic Models (DSMs) the multiple senses of a polysemous word are conflated into a single vector space representation. In this work, we propose a DSM that learns multiple distributional representations of a word based on different topics. First, a separate DSM is trained for each topic and then each of the topic-based DSMs is aligned to a common vector space. Our unsupervised mapping approach is motivated by the hypothesis that words preserving their relative distances in different topic semantic sub-spaces constitute robust semantic anchors that define the mappings between them. Aligned cross-topic representations achieve state-of-the-art results for the task of contextual word similarity. Furthermore, evaluation on NLP downstream tasks shows that multiple topic-based embeddings outperform single-prototype models.
Author(s): | Eleftheria Briakou and Nikos Athanasiou and Alexandros Potamianos |
Book Title: | Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)) |
Year: | 2019 |
Month: | June |
Bibtex Type: | Conference Paper (inproceedings) |
Paper Type: | Conference |
Event Place: | Minneapolis, USA |
Attachments: |
pdf
|
BibTex @inproceedings{UTDSM:Naacl19, title = {Cross-Topic Distributional Semantic Representations Via Unsupervised Mappings}, author = {Briakou, Eleftheria and Athanasiou, Nikos and Potamianos, Alexandros}, booktitle = {Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL))}, month = jun, year = {2019}, doi = {}, month_numeric = {6} } |