A Trio Neural Model for Dynamic Entity Relatedness Ranking
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2018
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908677825363968 |
|---|---|
| author | Nguyen, Tu Tran, Tuan Nejdl, Wolfgang |
| author_facet | Nguyen, Tu Tran, Tuan Nejdl, Wolfgang |
| contents | Measuring entity relatedness is a fundamental task for many natural language processing and information retrieval applications. Prior work often studies entity relatedness in static settings and an unsupervised manner. However, entities in real-world are often involved in many different relationships, consequently entity-relations are very dynamic over time. In this work, we propose a neural networkbased approach for dynamic entity relatedness, leveraging the collective attention as supervision. Our model is capable of learning rich and different entity representations in a joint framework. Through extensive experiments on large-scale datasets, we demonstrate that our method achieves better results than competitive baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1808_08316 |
| institution | arXiv |
| publishDate | 2018 |
| record_format | arxiv |
| spellingShingle | A Trio Neural Model for Dynamic Entity Relatedness Ranking Nguyen, Tu Tran, Tuan Nejdl, Wolfgang Information Retrieval Computation and Language Machine Learning Measuring entity relatedness is a fundamental task for many natural language processing and information retrieval applications. Prior work often studies entity relatedness in static settings and an unsupervised manner. However, entities in real-world are often involved in many different relationships, consequently entity-relations are very dynamic over time. In this work, we propose a neural networkbased approach for dynamic entity relatedness, leveraging the collective attention as supervision. Our model is capable of learning rich and different entity representations in a joint framework. Through extensive experiments on large-scale datasets, we demonstrate that our method achieves better results than competitive baselines. |
| title | A Trio Neural Model for Dynamic Entity Relatedness Ranking |
| topic | Information Retrieval Computation and Language Machine Learning |
| url | https://arxiv.org/abs/1808.08316 |