The accurate translation of domain-specific terminology remains a critical bottleneck for ensuring the fidelity and professionalism of machine translation systems. This paper presents our submission to the WMT26 Terminology Translation Shared Task: the TaT (Terminology-aware Translation) system. Built upon a structured, pipelined architecture, TaT integrates five specialized components designed to seamlessly ingest, process, and translate ambiguous textual inputs while strictly adhering to targeted terminology dictionary. Specifically, the framework comprises a sentence splitter, a terminology retriever, a lexical disambiguator, a baseline translator, and a dedicated terminology extractor tailored for Track 2 constraints. Both internal benchmarking and ablation studies demonstrate that our decoupled pipeline delivers robust performance, successfully meeting design expectations and substantially mitigating terminology omission and misalignment errors in domain-specific translations.

In natural language processing (NLP), state-of-the-art (SOTA) semi-supervised learning (SSL) frameworks have shown great performance on deep pre-trained language models such as BERT, and are expected to significantly reduce the demand for manual labeling. However, our empirical studies indicate that these frameworks are not suitable for lightweight models such as TextCNN, LSTM and etc. In this work, we develop a new SSL framework called FLiText, which stands for Faster and Lighter semi-supervised Text classification. FLiText introduces an inspirer network together with the consistency regularization framework, which leverages a generalized regular constraint on the lightweight models for efficient SSL. As a result, FLiText obtains new SOTA performance for lightweight models across multiple SSL benchmarks on text classification. Compared with existing SOTA SSL methods on TextCNN, FLiText improves the accuracy of lightweight model TextCNN from 51.00% to 90.49% on IMDb, 39.8% to 58.06% on Yelp-5, and from 55.3% to 65.08% on Yahoo! Answer. In addition, compared with the fully supervised method on the full dataset, FLiText just uses less than 1% of labeled data to improve the accuracy by 6.59%, 3.94%, and 3.22% on the datasets of IMDb, Yelp-5, and Yahoo! Answer respectively.