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.

Fact verification tasks aim to identify the integrity of textual contents according to the truthful corpus. Existing fact verification models usually build a fully connected reasoning graph, which regards claim-evidence pairs as nodes and connects them with edges. They employ the graph to propagate the semantics of the nodes. Nevertheless, the noisy nodes usually propagate their semantics via the edges of the reasoning graph, which misleads the semantic representations of other nodes and amplifies the noise signals. To mitigate the propagation of noisy semantic information, we introduce a Confidential Graph Attention Network (CO-GAT), which proposes a node masking mechanism for modeling the nodes. Specifically, CO-GAT calculates the node confidence score by estimating the relevance between the claim and evidence pieces. Then, the node masking mechanism uses the node confidence scores to control the noise information flow from the vanilla node to the other graph nodes. CO-GAT achieves a 73.59% FEVER score on the FEVER dataset and shows the generalization ability by broadening the effectiveness to the science-specific domain.

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.

Haoyu Wang, Shuo Wang, Yukun Yan, Xujia Wang, Zhiyu Yang, Yuzhuang Xu, Zhenghao Liu, Liner Yang, Ning Ding, Xu Han, Zhiyuan Liu, Maosong Sun. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Text simplification aims to make the text easier to understand by applying rewriting transformations. There has been very little research on Chinese text simplification for a long time. The lack of generic evaluation data is an essential reason for this phenomenon. In this paper, we introduce MCTS, a multi-reference Chinese text simplification dataset. We describe the annotation process of the dataset and provide a detailed analysis. Furthermore, we evaluate the performance of several unsupervised methods and advanced large language models. We additionally provide Chinese text simplification parallel data that can be used for training, acquired by utilizing machine translation and English text simplification. We hope to build a basic understanding of Chinese text simplification through the foundational work and provide references for future research. All of the code and data are released at https://github.com/blcuicall/mcts/.

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 .

The construct of linguistic complexity has been widely used in language learning research. Several text analysis tools have been created to automatically analyze linguistic complexity. However, the indexes supported by several existing Chinese text analysis tools are limited and different because of different research purposes. CTAP is an open-source linguistic complexity measurement extraction tool, which prompts any research purposes. Although it was originally developed for English, the Unstructured Information Management (UIMA) framework it used allows the integration of other languages. In this study, we integrated the Chinese component into CTAP, describing the index sets it incorporated and comparing it with three linguistic complexity tools for Chinese. The index set includes four levels of 196 linguistic complexity indexes: character level, word level, sentence level, and discourse level. So far, CTAP has implemented automatic calculation of complexity characteristics for four languages, aiming to help linguists without NLP background study language complexity.

Zhenghao Liu, Xiaoyuan Yi, Maosong Sun, Liner Yang, Tat-Seng Chua. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

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.

While part-of-speech (POS) tagging and dependency parsing are observed to be closely related, existing work on joint modeling with manually crafted feature templates suffers from the feature sparsity and incompleteness problems. In this paper, we propose an approach to joint POS tagging and dependency parsing using transition-based neural networks. Three neural network based classifiers are designed to resolve shift/reduce, tagging, and labeling conflicts. Experiments show that our approach significantly outperforms previous methods for joint POS tagging and dependency parsing across a variety of natural languages.

Word representations, aiming to build vectors for each word, have been successfully used in a variety of applications. Most word representations are learned from large amounts of documents ignoring other information. This is rather suboptimal because the side information of the documents, such as document labels, is not used in learning word representations. In this paper, we focus on how to exploit these side information to improve word representations. We propose to incorporate document labels into the learning process of word representations in two frameworks: neural network and matrix factorization. The experimental results on word analogy and word similarity task show that our models can better capture the semantic and syntactic information than the original models. Our models also improve the performance of word representations on text classification task.

Recently, topic modeling has been widely applied in data mining due to its powerful ability. A common, major challenge in applying such topic models to other tasks is to accurately interpret the meaning of each topic. Topic labeling, as a major interpreting method, has attracted significant attention recently. However, most of previous works only focus on the effectiveness of topic labeling, and less attention has been paid to quickly creating good topic descriptors; meanwhile, it’s hard to assign labels for new emerging topics by using most of existing methods. To solve the problems above, in this paper, we propose a novel fast topic labeling framework that casts the labeling problem as a k-nearest neighbor (KNN) search problem in a probability vector set. Our experimental results show that the proposed sequential interleaving method based on locality sensitive hashing (LSH) technology is efficient in boosting the comparison speed among probability distributions, and the proposed framework can generate meaningful labels to interpret topics, including new emerging topics.