Chinese abbreviations improve communicative efficiency by extracting key components from longer expressions. They are widely used in both daily communication and professional domains. However, existing abbreviation generation methods still face two major challenges. First, sequence-labeling-based approaches often neglect contextual meaning by making binary decisions at the character level, leading to abbreviations that fail to capture semantic completeness. Second, generation-based methods rely heavily on a single decoding process, which frequently produces correct abbreviations but ranks them lower due to inadequate semantic evaluation. To address these limitations, we propose a novel two-stage framework with Generation–Iterative Optimization for Abbreviation (GIOA). In the first stage, we design a Chain-of-Thought prompting strategy and incorporate definitional and situational contexts to generate multiple abbreviation candidates. In the second stage, we introduce a Semantic Preservation Dynamic Adjustment mechanism that alternates between character-level importance estimation and semantic restoration to optimize candidate ranking. Experiments on two public benchmark datasets show that our method outperforms existing state-of-the-art approaches, achieving Hit@1 improvements of 15.15% and 13.01%, respectively, while maintaining consistent results in Hit@3.

In the process of constructing domain-specific knowledge graphs, the task of relational triple extraction plays a critical role in transforming unstructured text into structured information. Existing relational triple extraction models face multiple challenges when processing domain-specific data, including insufficient utilization of semantic interaction information between entities and relations, difficulties in handling challenging samples, and the scarcity of domain-specific datasets. To address these issues, our study introduces three innovative components: Relation semantic enhancement, data augmentation, and a voting strategy, all designed to significantly improve the model’s performance in tackling domain-specific relational triple extraction tasks. We first propose an innovative attention interaction module. This method significantly enhances the semantic interaction capabilities between entities and relations by integrating semantic information from relation labels. Second, we propose a voting strategy that effectively combines the strengths of large language models (LLMs) and fine-tuned small pre-trained language models (SLMs) to reevaluate challenging samples, thereby improving the model’s adaptability in specific domains. Additionally, we explore the use of LLMs for data augmentation, aiming to generate domain-specific datasets to alleviate the scarcity of domain data. Experiments conducted on three domain-specific datasets demonstrate that our model outperforms existing comparative models in several aspects, with F1 scores exceeding the State of the Art models by 2%, 1.6%, and 0.6%, respectively, validating the effectiveness and generalizability of our approach.