Improving taxonomic relation learning via incorporating relation descriptions into word embeddings

Abstract

SummaryTaxonomic relations play an important role in various Natural Language Processing (NLP) tasks (eg, information extraction, question answering and knowledge inference). Existing approaches on embedding‐based taxonomic relation learning mainly rely on the word embeddings trained using co‐occurrence‐based similarity learning. However, the performance of these approaches is not quite satisfactory due to the lack of sufficient taxonomic semantic knowledge within word embeddings. To solve this problem, we propose an improved embedding‐based approach to learn taxonomic relations via incorporating relation descriptions into word embeddings. First, to capture additional taxonomic semantic knowledge, we train special word embeddings using not only co‐occurrence information of words but also relation descriptions (eg, taxonomic seed relations and their contextual triples). Then, using the trained word embeddings as features, we employ two learning models to identify and predict taxonomic relations, namely, offset‐based classification model and offset‐based similarity model. Experimental results on four real‐world domain datasets demonstrate that our proposed approach can capture additional taxonomic semantic knowledge and reduce dependence on the training dataset, outperforming the state‐of‐the‐art compared approaches on the taxonomic relation learning task.

A bilateral context and filtering strategy-based approach to Chinese entity synonym set expansion

“…Mining entity synonym set is an important task for many entity-based downstream applications, such as knowledge graph construction [1][2][3][4], taxonomy learning [5][6][7][8], and question answering [9][10][11]. An entity synonym set usually contains several different strings representing an identical entity [12][13][14].…”

“…https://scikit-learn.org/stable/modules/clustering.html#k-means 6. https://scikit-learn.org/stable/modules/clustering.html#birch 7. https://scikit-learn.org/stable/modules/svm.html 8.…”

Unmanned surface vessel obstacle avoidance with prior knowledge‐based reward shaping

“…However, the use of reinforcement learning to solve the problem of USV autonomous obstacle avoidance has the challenge of lack of proper reward function prevents USV from achieving obstacle avoidance. In the field of text processing, the combination of neural networks and prior knowledge has achieved many successes 9,10 . Therefore, we can design a series of reward functions for USV obstacle avoidance based on reward shaping of prior knowledge that satisfies USV's navigation, acceleration, collision avoidance, and other behaviors.…”