Juan Li

Jingjie Lv, Xian Lian, Ruihu Li et al.

Additive conjucyclic codes over $\F_{q^2}$ are closed under the conjugated cyclic shift and play an important role in constructing quantum error-correcting codes (QECCs). However, a systematic algebraic theory for such codes over general finite fields has been lacking. In this paper, we develop a unified framework by establishing a trace-based $\F_q$-linear isomorphism between $\F_{q^2}^n$ and $\F_q^{2n}$. This correspondence shows that additive conjucyclic codes of length $n$ correspond bijectively to $q$-ary linear cyclic codes of length $2n$, translating their structural analysis to the well-understood setting of cyclic codes. Using this isomorphism, we determine the enumeration of such codes and give explicit forms of their generator matrices. We then introduce an alternating inner product on $\F_{q^2}^n$, which is shown to be compatible with the symplectic inner product on $\F_q^{2n}$ under the trace isomorphism. Based on this inner product, we characterize the dual-containing condition for additive conjucyclic codes and derive explicit parity-check matrices. Finally, we construct $q$-ary QECCs from dual-containing additive conjucyclic codes. Our results unify and generalize previous studies on quaternary additive conjucyclic codes and present a construction method for $q$-ary QECCs from additive conjucyclic codes, together with an illustrative example.

Zhijie Qu, Juan Li, Zerui Ma et al.

Medical dialogue generation relies on natural language generation techniques to enable online medical consultations. Recently, the widespread adoption of large-scale models in the field of natural language processing has facilitated rapid advancements in this technology. Existing medical dialogue models are mostly based on BERT and pre-trained on English corpora, but there is a lack of high-performing models on the task of Chinese medical dialogue generation. To solve the above problem, this paper proposes CMed-GPT, which is the GPT pre-training language model based on Chinese medical domain text. The model is available in two versions, namely, base and large, with corresponding perplexity values of 8.64 and 8.01. Additionally, we incorporate lexical and entity embeddings into the dialogue text in a uniform manner to meet the requirements of downstream dialogue generation tasks. By applying both fine-tuning and p-tuning to CMed-GPT, we lowered the PPL from 8.44 to 7.35. This study not only confirms the exceptional performance of the CMed-GPT model in generating Chinese biomedical text but also highlights the advantages of p-tuning over traditional fine-tuning with prefix prompts. Furthermore, we validate the significance of incorporating external information in medical dialogue generation, which enhances the quality of dialogue generation.

Wen Zhang, Jiaoyan Chen, Juan Li et al.

Knowledge graph (KG) reasoning is becoming increasingly popular in both academia and industry. Conventional KG reasoning based on symbolic logic is deterministic, with reasoning results being explainable, while modern embedding-based reasoning can deal with uncertainty and predict plausible knowledge, often with high efficiency via vector computation. A promising direction is to integrate both logic-based and embedding-based methods, with the vision to have advantages of both. It has attracted wide research attention with more and more works published in recent years. In this paper, we comprehensively survey these works, focusing on how logics and embeddings are integrated. We first briefly introduce preliminaries, then systematically categorize and discuss works of logic and embedding-aware KG reasoning from different perspectives, and finally conclude and discuss the challenges and further directions.