Are compounds and phrases constructed by the same combinatorial principles? This is a long-standing topic in linguistic theory. As a highly isolating language, Chinese offers a particularly revealing case: its word–phrase boundary is weakly marked, thus compound-internal relations often parallel phrase-level syntactic relations. Although this continuity is well described in Chinese linguistics, no operational test has yet examined whether the same principles are similarly represented across the two levels. PLMs provide a shared representational space for operationalizing this question. Motivated by this idea, we build CompPhrase-7, a parallel Chinese compound–phrase dataset covering seven shared relation types, and conduct a multi-dimensional probing study of Chinese-language PLMs, which separates three levels of cross-scale continuity: transferable feature information, aligned category geometry, and localized dimension-level causal support. The results show a clear dissociation: feature transfer is stable across models; category geometry depends strongly on pre-training regime; and localized causal support is not detected. The findings point to a differentiated view of Chinese combinatorial principles: compounds and phrases retain comparable relational cues, while lexicalization reshapes how those cues are organized once phrase-like structures become words. This study connects a long-standing linguistic question to a more precise computational representation, showing that continuity can surface as transferable information without shared geometry or localized causal implementation.

Lexical Relation Mining (LRM) aims to identify and classify lexical relations between word pairs. In this paper, we focus on two subtypes of LRM: Lexical Relation Classification (LRC) and Lexical Entailment (LE). Existing top-performing methods for them rely heavily on Pre-trained Language Models (PLMs) yet fail to distinguish nuanced lexical relations. From a linguistic perspective, intralexical tree-structured sememe information can reflect interlexical relations. Inspired by this, we are motivated to explore leveraging such structured knowledge to enhance LRC and LE. We first propose an automated Sememe Tree Construction (STC) pipeline to predict sememe trees; Then, we present the SememeLRM method to fully leverage structured sememe knowledge; Experimental results show that it achieves a notable 1.6% improvement on average across benchmarks, even outperforming Large Language Model (LLM)-based methods that contain 20 times more parameters on most benchmarks. Further results also suggest that sememe trees predicted by our pipeline can rival the gold-standard in HowNet, extending their applicability to lexico-semantic computing. Overall, this paper presents a potentially generalizable framework for leveraging complete sememe trees and makes significant progress, helping to unlock the value of such intralexical knowledge in downstream tasks.

Lexical evolution is universal across languages, yet the mechanisms driving neologism formation vary substantially from one language to another. In Chinese, this variation is particularly reflected in the productivity of compounding, where morphemes are combined through word-formation relations to create interpretable lexical forms. This morphological productivity implies that the Chinese lexicon can be viewed not only as a set of attested words, but also as a dynamically latent space with potential neologisms to be realized. However, this perspective still remains underexplored in computation, as current approaches are largely reactive, focusing on detecting attested words from corpora. This raises a question about word-formation itself: which morpheme combinations do the rules license beyond those that corpora already attest? Motivated by this, we propose a proactive creation paradigm for Chinese neologism research. We introduce a three-stage pipeline: KG-Based Candidate Generation, Morphological Discarding, and LLM-Based Filtering. We then probe the candidates with three complementary signals: expert judgment, model perplexity, and corpus attestation. The three signals agree: accepted candidates sit close to real words and clearly apart from rejected combinations. The pipeline yields 18,662 candidates with definitions, examples, and formation metadata, released as material for follow-up work, such as lexical gaps and lexical change. Overall, this study substantiates a proactive creation paradigm for Chinese neologism research, and uses it to characterize what Chinese word-formation rules license beyond what dictionaries have already recorded.

Link Prediction (LP) aims to predict missing triple information within a Knowledge Graph (KG). Existing LP methods have sought to improve the performance by integrating structural and textual information. However, for lexico-semantic KGs designed to document fine-grained sense distinctions, these types of information may not be sufficient to support effective LP. From a linguistic perspective, word senses within lexico-semantic relations usually show systematic differences in their sememic components. In light of this, we are motivated to enhance LP with sememe knowledge. We first construct a Sememe Prediction (SP) dataset, SememeDef, for learning such knowledge, and two Chinese datasets, HN7 and CWN5, for LP evaluation; Then, we propose a method, SememeLP, to leverage this knowledge for LP fully. It consistently and significantly improves the LP performance in both English and Chinese, achieving SOTA MRR of 75.1%, 80.5%, and 77.1% on WN18RR, HN7, and CWN5, respectively; Finally, an in-depth analysis is conducted, making clear how sememic components can benefit LP for lexico-semantic KGs, which provides promising progress for the completion of them.

Word Sense Disambiguation (WSD) is a fundamental task critical for accurate semantic understanding. Conventional training strategies usually only consider predefined senses for target words and learn each of them from relatively limited instances, neglecting the influence of similar ones. To address these problems, we propose the method of Learning to Rank Senses (LTRS) to enhance the task. This method helps a model learn to represent and disambiguate senses from a broadened range of instances via ranking an expanded list of sense definitions. By employing LTRS, our model achieves a SOTA F1 score of 79.6% in Chinese WSD and exhibits robustness in low-resource settings. Moreover, it shows excellent training efficiency, achieving faster convergence than previous methods. This provides a new technical approach to WSD and may also apply to the task for other languages.

Morphemes serve as a strong linguistic feature to capture lexical semantics, with higher coverage than words and more natural than sememes. However, due to the lack of morpheme-informed resources and the expense of manual annotation, morpheme-enhanced methods remain largely unexplored in Computational Linguistics. To address this issue, we propose the task of Morpheme Sense Disambiguation (MSD), with two subtasks in-text and in-word, similar to Word Sense Disambiguation (WSD) and Sememe Prediction (SP), to generalize morpheme features on more tasks. We first build the MorDis resource for Chinese, including MorInv as a morpheme inventory, MorTxt and MorWrd as two types of morpheme-annotated datasets. Next, we provide two baselines in each evaluation; the best model yields a promising precision of 77.66% on in-text MSD and 88.19% on in-word MSD, indicating its comparability with WSD and superiority over SP. Finally, we demonstrate that predicted morphemes achieve comparable performance with the ground-truth ones on a downstream application of Definition Generation (DG). This validates the feasibility and applicability of our proposed tasks. The resources and workflow of MSD will provide new insights and solutions for downstream tasks, including DG as well as WSD, training pre-trained models, etc.

In parataxis languages like Chinese, word meanings are highly correlated with morphological knowledge, which can help to disambiguate word senses. However, in-depth exploration of morphological knowledge in previous word sense disambiguation (WSD) methods is still lacking due to the absence of publicly available resources. In this paper, we are motivated to enhance Chinese WSD with full morphological knowledge, including both word-formations and morphemes. We first construct the largest and releasable Chinese WSD resources, including the lexico-semantic inventories MorInv and WrdInv, a Chinese WSD dataset MiCLS, and an out-of-volcabulary (OOV) test set. Then, we propose a model, MorBERT, to fully leverage this morphology-informed knowledge for Chinese WSD and achieve a SOTA F1 of 92.18% in the task. Finally, we demonstrated the model’s robustness in low-resource settings and generalizability to OOV senses. These resources and methods may bring new insights into and solutions for various downstream tasks in both computational and humanistic fields.

“汉语是一种意合型语言,汉语中语素的构词方式与规律是描述、理解词义的重要因素。关于语素构词的方式,语言学界有语法构词与语义构词这两种观点,其中,语义构词对语素间关系的表达更为深入。本文采取语义构词的路线,基于语言学视角,考虑汉语构词特点,提出了一套面向计算的语义构词结构体系,通过随机森林自动标注与人工校验相结合的方式,构建汉语语义构词知识库,并在词义生成的任务上对该资源进行计算评估。实验取得了良好的结果,基于语义构词知识库的词义生成BLEU值达25.07,较此前的语法构词提升了3.17%,初步验证了这种知识表示方法的有效性。该知识表示方法与资源建设将为人文领域和信息处理等多方面的应用提供新的思路与方案。”