Topic modeling plays a vital role in uncovering hidden semantic structures within text corpora, but existing models struggle in lowresource settings where limited target-domain data leads to unstable and incoherent topic inference.We address this challenge by formally introducing domain adaptation for lowresource topic modeling, where a high-resource source domain informs a low-resource target domain without overwhelming it with irrelevant content.We establish a finite-sample generalization bound showing that effective knowledge transfer depends on robust performance in both domains, minimizing latent-space discrepancy, and preventing overfitting to the data.Guided by these insights, we propose DALTA (Domain-Aligned Latent Topic Adaptation), a new framework that employs a shared encoder for domain-invariant features, specialized decoders for domain-specific nuances, and adversarial alignment to selectively transfer relevant information.Experiments on diverse lowresource datasets demonstrate that DALTA consistently outperforms state-of-the-art methods in terms of topic coherence, stability, and transferability.

Unsupervised keyphrase prediction has gained growing interest in recent years.However, existing methods typically rely on heuristically defined importance scores, which may lead to inaccurate informativeness estimation.In addition, they lack consideration for time efficiency.To solve these problems, we propose ERU-KG, an unsupervised keyphrase generation (UKG) model that consists of an informativeness and a phraseness module.The former estimates the relevance of keyphrase candidates, while the latter generate those candidates.The informativeness module innovates by learning to model informativeness through references (e.g., queries, citation contexts, and titles) and at the term-level, thereby 1) capturing how the key concepts of documents are perceived in different contexts and 2) estimating informativeness of phrases more efficiently by aggregating term informativeness, removing the need for explicit modeling of the candidates.ERU-KG demonstrates its effectiveness on keyphrase generation benchmarks by outperforming unsupervised baselines and achieving on average 89% of the performance of a supervised model for top 10 predictions.Additionally, to highlight its practical utility, we evaluate the model on text retrieval tasks and show that keyphrases generated by ERU-KG are effective when employed as query and document expansions.Furthermore, inference speed tests reveal that ERU-KG is the fastest among baselines of similar model sizes.Finally, our proposed model can switch between keyphrase generation and extraction by adjusting hyperparameters, catering to diverse application requirements.1

In this work, we study the problem of unsupervised open-domain keyphrase generation, where the objective is a keyphrase generation model that can be built without using human-labeled data and can perform consistently across domains.To solve this problem, we propose a seq2seq model that consists of two modules, namely phraseness and informativeness module, both of which can be built in an unsupervised and open-domain fashion.The phraseness module generates phrases, while the informativeness module guides the generation towards those that represent the core concepts of the text.We thoroughly evaluate our proposed method using eight benchmark datasets from different domains.Results on in-domain datasets show that our approach achieves stateof-the-art results compared with existing unsupervised models, and overall narrows the gap between supervised and unsupervised methods down to about 16%.Furthermore, we demonstrate that our model performs consistently across domains, as it overall surpasses the baselines on out-of-domain datasets.1 .

We propose a new problem called coordinated topic modeling that imitates human behavior while describing a text corpus.It considers a set of well-defined topics like the axes of a semantic space with a reference representation.It then uses the axes to model a corpus for easily understandable representation.This new task helps represent a corpus more interpretably by reusing existing knowledge and benefits the corpora comparison task.We design ECTM, an embedding-based coordinated topic model that effectively uses the reference representation to capture the target corpus-specific aspects while maintaining each topic's global semantics.In ECTM, we introduce the topic-and documentlevel supervision with a self-training mechanism to solve the problem.Finally, extensive experiments on multiple domains show the superiority of our model over other baselines.1

Code smell is a sign of design and development flaws in a software system which reduces the reusability and maintainability of the system. Refactoring is a continuous practice of eliminating code smells from the source code. A God Class is one of the most common code smells where too many responsibilities are defined in a single class. God Classes reduce the quality of a system by increasing coupling and decreasing cohesion. In this paper, we propose an approach for extracting a God Class into new classes by increasing class cohesion. For this, both structural and semantic relationship between methods in a class are analyzed, and strongly related methods are clustered and suggested to be in the same class. We assessed the proposed approach on fifteen real God Classes from two well-known open source systems and it is shown that the cohesion among the classes is increased after refactoring. A comparative result of our approach with a similar existing approach is presented and it is found that our approach provides better results for almost all the experimented God Classes.

This paper introduces a new splitting criterion called Inter-node Hellinger Distance (iHD) and a weighted version of it (iHDw) for constructing decision trees. iHD measures the distance between the parent and each of the child nodes in a split using Hellinger distance. We prove that this ensures the mutual exclusiveness between the child nodes. The weight term in iHDw is concerned with the purity of individual child node considering the class imbalance problem. The combination of the distance and weight term in iHDw thus favors a partition where child nodes are purer and mutually exclusive, and skew insensitive. We perform an experiment over twenty balanced and twenty imbalanced datasets. The results show that decision trees based on iHD win against six other state-of-the-art methods on at least 14 balanced and 10 imbalanced datasets. We also observe that adding the weight to iHD improves the performance of decision trees on imbalanced datasets. Moreover, according to the result of the Friedman test, this improvement is statistically significant compared to other methods.