Kangyang Luo, Yuzhuo Bai, Shuzheng Si, Cheng Gao, Zhitong Wang, Yingli Shen, Wenhao Li, Zhu Liu, Yufeng Han, Jiayi Wu, Cunliang Kong, Maosong Sun. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Brian S. Lin, Jiaxin Yuan, Zihan Zhou, Shouli Wang, Shuo Wang, Cunliang Kong, Qi Shi, Yuxuan Li, Liner Yang, Zhiyuan Liu, Maosong Sun. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Zhu Liu, Cunliang Kong, Ying Liu, Maosong Sun. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

The task of complexity-controllable definition generation refers to providing definitions with different readability for words in specific contexts. This task can be utilized to help language learners eliminate reading barriers and facilitate language acquisition. However, the available training data for this task remains scarce due to the difficulty of obtaining reliable definition data and the high cost of data standardization. To tackle those challenges, we introduce a general solution from both the data-driven and method-driven perspectives. We construct a large-scale standard Chinese dataset, COMPILING, which contains both difficult and simple definitions and can serve as a benchmark for future research. Besides, we propose a multitasking framework SimpDefiner for unsupervised controllable definition generation. By designing a parameter-sharing scheme between two decoders, the framework can extract the complexity information from the non-parallel corpus. Moreover, we propose the SimpDefiner guided prompting (SGP) method, where simple definitions generated by SimpDefiner are utilized to construct prompts for GPT-4, hence obtaining more realistic and contextually appropriate definitions. The results demonstrate SimpDefiner's outstanding ability to achieve controllable generation and better results could be achieved when GPT-4 is incorporated.

The definition generation task can help language learners by providing explanations for unfamiliar words.This task has attracted much attention in recent years.We propose a novel task of Simple Definition Generation (SDG) to help language learners and low literacy readers.A significant challenge of this task is the lack of learner's dictionaries in many languages, and therefore the lack of data for supervised training.We explore this task and propose a multitasking framework SimpDefiner that only requires a standard dictionary with complex definitions and a corpus containing arbitrary simple texts.We disentangle the complexity factors from the text by carefully designing a parameter sharing scheme between two decoders.By jointly training these components, the framework can generate both complex and simple definitions simultaneously.We demonstrate that the framework can generate relevant, simple definitions for the target words through automatic and manual evaluations on English and Chinese datasets.Our method outperforms the baseline model by a 1.77 SARI score on the English dataset, and raises the proportion of the low level (HSK level 1-3) words in Chinese definitions by 3.87% 1 .

Chinese definition modeling is a challenging task that generates a dictionary definition in Chinese for a given Chinese word. To accomplish this task, we built two novel datasets based on Chinese Concept Dictionary (CCD) and Chinese WordNet (CWN) respectively. Each dataset contains triples of a word, sememes, and a corresponding definition. We present two novel models to improve Chinese definition modeling: the Adaptive-Attention model (AAM) and the Self- and Adaptive-Attention Model (SAAM). AAM successfully incorporates sememes for generating the definition with an adaptive attention mechanism. It has the capability to decide which sememes to focus on and when to pay attention to sememes. SAAM further replaces recurrent connections in AAM with self-attention and relies entirely on the attention mechanism, reducing the path length between word, sememes and definition. Experiments on both datasets demonstrate that by incorporating sememes, our model can generate definitions with more concrete information. And the best model that we proposed outperforms the state-of-the-art method by a large margin on both datasets.

Spoken language understanding (SLU), which mainly involves intent prediction and slot filling, is a core component of a spoken dialogue system. Usually, intent determination and slot filling are carried out independently. Recently, joint learning of intent determination and slot filling has been proved effective in SLU. In this paper, we propose a novel joint multi-task learning framework for SLU, which predicts user intent and slot label via shared LSTM architecture, as well as next word's part of speech (POS) via neural language model. The proposed model exploits the correlation among different tasks and makes full advantage of all supervised signals. We conduct experiments on popular benchmark ATIS dataset, which consists of rich dialogues collected from real world. The experiment results show that our model achieves state-of-the-art in terms of several popular metrics.