Text clustering, as one of the most fundamental challenges in unsupervised learning, aims at grouping semantically similar text segments without relying on human annotations. With the rapid development of deep learning, deep clustering has achieved significant advantages over traditional clustering methods. Despite the effectiveness, most existing deep text clustering methods rely heavily on representations pre-trained in general domains, which may not be the most suitable solution for clustering in specific target domains. To address this issue, we propose CEIL, a novel Classification-Enhanced Iterative Learning framework for short text clustering, which aims at generally promoting the clustering performance by introducing a classification objective to iteratively improve feature representations. In each iteration, we first adopt a language model to retrieve the initial text representations, from which the clustering results are collected using our proposed Category Disentangled Contrastive Clustering (CDCC) algorithm. After strict data filtering and aggregation processes, samples with clean category labels are retrieved, which serve as supervision information to update the language model with the classification objective via a prompt learning approach. Finally, the updated language model with improved representation ability is used to enhance clustering in the next iteration. Extensive experiments demonstrate that the CEIL framework significantly improves the clustering performance over iterations, and is generally effective on various clustering algorithms. Moreover, by incorporating CEIL on CDCC, we achieve the state-of-the-art clustering performance on a wide range of short text clustering benchmarks outperforming other strong baseline methods.

The competitive performance of neural machine translation (NMT) critically relies on large amounts of training data. However, acquiring high-quality translation pairs requires expert knowledge and is costly. Therefore, how to best utilize a given dataset of samples with diverse quality and characteristics becomes an important yet understudied question in NMT. Curriculum learning methods have been introduced to NMT to optimize a model's performance by prescribing the data input order, based on heuristics such as the assessment of noise and difficulty levels. However, existing methods require training from scratch, while in practice most NMT models are pre-trained on big data already. Moreover, as heuristics, they do not generalize well. In this paper, we aim to learn a curriculum for improving a pre-trained NMT model by re-selecting influential data samples from the original training set and formulate this task as a reinforcement learning problem. Specifically, we propose a data selection framework based on Deterministic Actor-Critic, in which a critic network predicts the expected change of model performance due to a certain sample, while an actor network learns to select the best sample out of a random batch of samples presented to it. Experiments on several translation datasets show that our method can further improve the performance of NMT when original batch training reaches its ceiling, without using additional new training data, and significantly outperforms several strong baseline methods.

Rule execution is the core step of rule-based semantic web reasoning. However, most existing approaches are centralized, which cannot scale out to reason big semantic web datasets. In this paper, we described a kind of semantic web rule execution mechanism using MapReduce programming model, which not only can handle RDFS and OWL ter Horst semantic rules, but also can be used in SWRL reasoning. Theoretical analysis is present on the scalability of this rule execution mechanism. Result shows that it can scale well as Mapreduce framework.

Abstract With the drastic development of semantic‐driven applications, assessing the quality of ontologies has received more attention. Measuring and assessing the quality of ontologies can help ontology engineers to control project management and reduce the risk of project failures. However, most of the existing ontology metrics for measuring and assessing the quality of ontologies are defined based on ontology structure, and neglect the stability of ontology measurement. In this paper, we concentrate on stable ontology measurement by using semantically derived ontology metrics. We propose four ontology cohesion metrics, which fully consider the implicitly expressed semantic information and are defined based on ontological semantics rather than ontology structure. Before measuring and assessing an ontology, we materialize a pre‐processing for stable ontology measurement by treating the ontology. The proposed ontology cohesion metrics are theoretically validated by the validation criteria of object‐oriented software. The experimental results show that we can successfully collect more semantic knowledge from the testing ontologies for stable ontology measurement by using the proposed ontology cohesion metrics. The ontology cohesion metrics proposed in this paper can be reasonably used as a cogent complementarity of existing ontology metrics. Copyright © 2010 John Wiley & Sons, Ltd.