Name
Title | ||
|---|---|---|
Combining and learning word embedding with WordNet for semantic relatedness and similarity measurement |
Abstract | ||
|---|---|---|
AbstractIn this research, we propose 3 different approaches to measure the semantic relatedness between 2 words: (i) boost the performance of GloVe word embedding model via removing or transforming abnormal dimensions; (ii) linearly combine the information extracted from WordNet and word embeddings; and (iii) utilize word embedding and 12 linguistic information extracted from WordNet as features for Support Vector Regression. We conducted our experiments on 8 benchmark data sets, and computed Spearman correlations between the outputs of our methods and the ground truth. We report our results together with 3 state‐of‐the‐art approaches. The experimental results show that our method can outperform state‐of‐the‐art approaches in all the selected English benchmark data sets. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1002/asi.24289 | Periodicals |
DocType | Volume | Issue |
Journal | 71 | 6 |
ISSN | Citations | PageRank |
2330-1635 | 1 | 0.35 |
References | Authors | |
0 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yang‐Yin Lee | 1 | 1 | 0.35 |
| Ke Hao | 2 | 22 | 4.08 |
| Ting‐Yu Yen | 3 | 1 | 0.35 |
| Hen-Hsen Huang | 4 | 63 | 37.14 |
| Hsin-hsi Chen | 5 | 2267 | 233.93 |