Search Results (25)

This study investigates syntactic parafoveal processing in Chinese reading using a boundary paradigm with two-character verb–object phrases. Participants (N = 120 undergraduates) viewed sentences with manipulated previews (identity, syntactically consistent, and inconsistent previews). Results showed a selective syntactic preview effect: syntactical violations reduced target word skipping rates, but fixation durations remained unaffected. This dissociation contrasts with robust syntactic preview benefits observed in alphabetic languages, highlighting how Chinese’s lack of morphological markers constrains parafoveal processing. The findings challenge parallel processing models while supporting language-specific modulation of universal cognitive mechanisms. Our results advance understanding of hierarchical information extraction in reading, with implications for developing cross-linguistic reading models. Full article

Extant Chinese studies have documented that transposing characters within two-character words (e.g., 西装 suit) yields greater parafoveal preview benefits for target words compared to replacing the characters with unrelated ones (e.g., 型间 a nonword), i.e., the Chinese character transposition effect. This effect has been interpreted as evidence for flexible positional encoding in parafoveal processing, whereby readers tolerate character order disruptions. Alternatively, it has been attributed to morpheme-to-word activation. The present study aims to further clarify the mechanism of the transposition effect. We manipulated four preview conditions of target words in a sentence, identical, semantic, transposed semantic, and control preview, using an eye tracker to record eye movements. Experiment 1 employed reversible word pairs (e.g., 领带 tie-带领 lead) as semantical and transposed previews for targets (e.g., 西装suit). Experiment 2 used non-reversible word pairs (e.g., 衬衫 shirt-衫衬 a nonword). The results revealed comparable processing for both the semantic and transposed semantic preview conditions. Critically, the transposed semantic preview yielded a processing advantage over the unrelated preview. These findings demonstrated that Chinese readers efficiently extract semantic information from the parafoveal region even when character order is disrupted, indicating flexible character position encoding. Full article

Chinese lacks explicit word boundary markers, creating frequent temporary segmental ambiguities where character sequences permit multiple plausible lexical analyses. Skilled native (L1) Chinese readers resolve these ambiguities efficiently. However, mechanisms underlying word segmentation in second language (L2) Chinese reading remain poorly understood. Our study investigated: (1) whether L2 readers experience greater difficulty processing temporary segmental ambiguities compared to L1 readers, and (2) whether visual boundary cues can facilitate ambiguity resolution in L2 reading. We measured the eye movements of 102 skilled L1 and 60 high-proficiency L2 readers for sentences containing temporarily ambiguous three-character incremental words (e.g., “音乐剧” [musical]), where the initial two characters (“音乐” [music]) also form a valid word. Sentences were presented using either neutral mono-color displays providing no segmentation cues, or color-coded displays marking word boundaries. The color-coded displays employed either uniform coloring to promote resolution of the segmental ambiguity or contrasting colors for the two-character embedded word versus the final character to induce a segmental misanalysis. The L2 group read more slowly than the L1 group, employing a cautious character-by-character reading strategy. Both groups nevertheless appeared to process the segmental ambiguity effectively, suggesting shared segmentation strategies. The L1 readers showed little sensitivity to visual boundary cues, with little evidence that this influenced their ambiguity processing. By comparison, L2 readers showed greater sensitivity to these cues, with some indication that they affected ambiguity processing. The overall sentence-level effects of color coding word boundaries were nevertheless modest for both groups, suggesting little influence of visual boundary cues on overall reading fluency for either L1 or L2 readers. Full article

Two experiments were conducted to examine native and non-native speakers’ recognition of Chinese two-character words (2C-words) in the context of audio sentence comprehension. The recording was played of a sentence, in which a collocation composed of a number word, a sortal classifier, and a noun (NCN) was embedded. When the participants were about to hear the noun of the NCN (Noun), the playing stopped, and a target was visually presented, which was the Noun, the character-transposed word of the Noun (NounT), or a control word (NounC), or was a homophone nonword for Noun, NounT, or NounC. The participants were required to make a lexical decision on the target before they resumed listening. The results showed that both native and non-native speakers were able to take visually presented 2C-word targets as semantic whole entities in the context of audio sentence comprehension, which was mediated by their Chinese proficiency. Native speakers readily processed visually presented 2C-words both as wholes and according to their constituent characters, but non-native speakers were not likely to process the 2C-words according to their constituent characters. Full article

Chinese dialogue generation faces multiple challenges, such as semantic understanding, information matching, and response fluency. Generative dialogue systems for Chinese conversation are somehow difficult to construct because of the flexible word order, the great impact of word replacement on semantics, and the complex implicit context. Existing methods still have limitations in addressing these issues. To tackle these problems, this paper proposes an improved Chinese dialogue generation model based on transformer architecture. The model uses a multi-layer transformer decoder as the backbone and introduces two key techniques, namely incorporating pre-trained language model word embeddings and optimizing the sparse Softmax loss function. For word-embedding fusion, we concatenate the word vectors from the pre-trained model with character-based embeddings to enhance the semantic information of word representations. The sparse Softmax optimization effectively mitigates the overfitting issue by introducing a sparsity regularization term. Experimental results on the Chinese short text conversation (STC) dataset demonstrate that our proposed model significantly outperforms the baseline models on automatic evaluation metrics, such as BLEU and Distinct, with an average improvement of 3.5 percentage points. Human evaluations also validate the superiority of our model in generating fluent and relevant responses. This work provides new insights and solutions for building more intelligent and human-like Chinese dialogue systems. Full article

Natural language understanding is a foundational task in medical dialogue systems. However, there are still two key problems to be solved: (1) Multiple meanings of a word lead to ambiguity of intent; (2) character errors make slot entity extraction difficult. To solve the above problems, this paper proposes a character-word information interaction framework (CWIIF) for natural language understanding in the Chinese medical dialogue domain. The CWIIF framework contains an intent information adapter to solve the problem of intent ambiguity caused by multiple meanings of words in the intent detection task and a slot label extractor to solve the problem of difficulty in yellowslot entity extraction due to character errors in the slot filling task. The proposed framework is validated on two publicly available datasets, the Intelligent Medical Consultation System (IMCS-21) and Chinese Artificial Intelligence Speakers (CAIS). Experimental results from both datasets demonstrate that the proposed framework outperforms other baseline methods in handling Chinese medical dialogues. Notably, on the IMCS-21 dataset, precision improved by 2.42%, recall by 3.01%, and the F1 score by 2.4%. Full article

The foveal load hypothesis assumes that the ease (or difficulty) of processing the currently fixated word in a sentence can influence processing of the upcoming word(s), such that parafoveal preview is reduced when foveal load is high. Recent investigations using pseudo-character previews reported an absence of foveal load effects in Chinese reading. Substantial Chinese studies to date provide some evidence to show that parafoveal words may be processed orthographically, phonologically, or semantically. However, it has not yet been established whether parafoveal processing is equivalent in terms of the type of parafoveal information extracted (orthographic, phonological, semantic) under different foveal load conditions. Accordingly, the present study investigated this issue with two experiments. Participants’ eye movements were recorded as they read sentences in which foveal load was manipulated by placing a low- or high-frequency word N preceding a critical word. The preview validity of the upcoming word N + 1 was manipulated in Experiment 1, and word N + 2 in Experiment 2. The parafoveal preview was either identical to word N + 1(or word N + 2); orthographically related; phonologically related; semantically related; or an unrelated pseudo-character. The results showed robust main effects of frequency and preview type on both N + 1 and N + 2. Crucially, however, interactions between foveal load and preview type were absent, indicating that foveal load does not modulate the types of parafoveal information processed during Chinese reading. Full article

The goal of this study was to compare model-generated sounds with the process of sound acquisition in humans. The research utilized two dictionaries of the Chaoshan dialect spanning approximately one century. Identical Chinese characters were selected from each dictionary, and their contemporary pronunciations were documented. Subsequently, inconsistencies in pronunciation were manually rectified, following which three machine learning methods were employed to train the pronunciation of words from one dictionary to another. These methods comprised the attention-based sequence-to-sequence method, DirecTL+, and Sequitur. The accuracy of the model was evaluated using five-fold cross-validation, revealing a maximum accuracy of 68%. Additionally, the study investigated how the probability of a sound’s subsequent unit influences the accuracy of the machine learning methods. The attention-based sequence-to-sequence model is not solely influenced by the frequency of input but also by the probability of the subsequent unit. Full article

The foveal load effect is one of the most fundamental effects in reading psychology, and also one of the most controversial issues in recent years. The foveal load effect refers to the phenomenon that the difficulty of foveal processing affects parafoveal preview. In Chinese reading, whether the foveal load effect exists, as well as whether this effect is modulated by parafoveal word frequency, remains unclear. In this study, the eye-tracking technique was used to track the eye movements of 48 subjects. Utilized the boundary paradigm with single-character words as parafoveal words, the present study manipulated foveal word frequency (high and low), parafoveal word frequency (high and low), and two types of preview (identical preview and pseudocharacter preview) to investigate these questions. The results revealed that the foveal word frequency does not influence preview, suggesting the absence of the foveal load effect when using single-character words as parafoveal words. Furthermore, parafoveal word frequency does not modulate the effect of the foveal load on the preview. This empirical evidence contributes to refining the understanding of the Chinese reading model. Full article

In the field of Chinese-named entity recognition, recent research has sparked new interest by combining lexical features with character-based methods. Although this vocabulary enhancement method provides a new perspective, it faces two main challenges: firstly, using character-by-character matching can easily lead to conflicts during the vocabulary matching process. Although existing solutions attempt to alleviate this problem by obtaining semantic information about words, they still lack sufficient temporal sequential or global information acquisition; secondly, due to the limitations of dictionaries, there may be words in a sentence that do not match the dictionary. In this situation, existing vocabulary enhancement methods cannot effectively play a role. To address these issues, this paper proposes a method based on lexical information and spatial features. This method carefully considers the neighborhood and overlap relationships of characters in vocabulary and establishes global bidirectional semantic and temporal sequential information to effectively address the impact of conflicting vocabulary and character fusion on entity segmentation. Secondly, the attention score matrix extracted by the point-by-point convolutional network captures the local spatial relationship between characters without fused vocabulary information and characters with fused vocabulary information, aiming to compensate for information loss and strengthen spatial connections. The comparison results with the baseline model show that the SISF method proposed in this paper improves the F1 metric by 0.72%, 3.12%, 1.07%, and 0.37% on the Resume, Weibo, Ontonotes 4.0, and MSRA datasets, respectively. Full article

Football is one of the most popular sports in the world, arousing a wide range of research topics related to its off- and on-the-pitch performance. The extraction of football entities from football news helps to construct sports frameworks, integrate sports resources, and timely capture the dynamics of the sports through visual text mining results, including the connections among football players, football clubs, and football competitions, and it is of great convenience to observe and analyze the developmental tendencies of football. Therefore, in this paper, we constructed a 1000,000-word Chinese corpus in the field of football and proposed a BiLSTM-based model for named entity recognition. The ALBERT-BiLSTM combination model of deep learning is used for entity extraction of football textual data. Based on the BiLSTM model, we introduced ALBERT as a pre-training model to extract character and enhance the generalization ability of word embedding vectors. We then compared the results of two different annotation schemes, BIO and BIOE, and two deep learning models, ALBERT-BiLSTM-CRF and ALBERT BiLSTM. It was verified that the BIOE tagging was superior than BIO, and the ALBERT-BiLSTM model was more suitable for football datasets. The precision, recall, and F-Score of the model were 85.4%, 83.47%, and 84.37%, correspondingly. Full article

In view of the fact that entity nested and professional terms are difficult to identify in the field of power dispatch, a multi-task-based few-shot named entity recognition model (FSPD-NER) for power dispatch is proposed. The model consists of four modules: feature enhancement, seed, expansion, and implication. Firstly, the masking strategy of the encoder is improved by adopting whole-word masking, using a RoBERTa (Robustly Optimized BERT Pretraining Approach) encoder as the embedding layer to obtain the text feature representation, and an IDCNN (Iterated Dilated CNN) module to enhance the feature. Then the text is cut into one Chinese character and two Chinese characters as a seed set, the score for each seed is calculated, and if the score is greater than the threshold value ω, they are passed to the expansion module as candidate seeds; next, the candidate seeds need to be expanded left and right according to offset γ to obtain the candidate entities; finally, to construct text implication pairs, the input text is used as a premise sentence, the candidate entity is connected with predefined label templates as hypothesis sentences, and the implication pairs are passed to the RoBERTa encoder for the classification task. The focus loss function is used to alleviate label imbalance during training. The experimental results of the model on the power dispatch dataset show that the precision, recall, and F1 scores of the recognition results in 20-shot samples are 63.39%, 61.97%, and 62.67%, respectively, which is a significant performance improvement compared to existing methods. Full article

Grammar error correction (GEC) is a crucial task in the field of Natural Language Processing (NLP). Its objective is to automatically detect and rectify grammatical mistakes in sentences, which possesses immense application research value. Currently, mainstream grammar-correction methods primarily rely on sequence labeling and text generation, which are two kinds of end-to-end methods. These methods have shown exemplary performance in areas with low error density but often fail to deliver satisfactory results in high-error density situations where multiple errors exist in a single sentence. Consequently, these methods tend to overcorrect correct words, leading to a high rate of false positives. To address this issue, we researched the specific characteristics of the Chinese grammar error correction (CGEC) task in high-error density situations. We proposed a grammar-correction method based on prompt templates. Firstly, we proposed a strategy for constructing prompt templates suitable for CGEC. This strategy transforms the CGEC task into a masked fill-in-the-blank task compatible with the masked language model BERT. Secondly, we proposed a method for dynamically updating templates, which incorporates already corrected errors into the template through dynamic updates to improve the template quality. Moreover, we used the phonetic and graphical resemblance knowledge from the confusion set as guiding information. By combining this with BERT’s prediction results, the model can more accurately select the correct characters, significantly enhancing the accuracy of the model’s prediction correction results. Our methods were validated through experiments on a public grammar-correction dataset. The results indicate that our method achieves higher correction performance and lower false correction rates in high-error density scenarios. Full article

Neural tuning for print refers to differential neural responses (e.g., the N1 component of event-related potentials) to different orthographic forms and other visual stimuli. While impaired neural tuning for print has been well established in dyslexic children who read alphabetic scripts, it remains unclear whether such effects exist in dyslexic children who read Chinese, which dramatically differs in visual and linguistic characteristics from alphabetic words. To fill this gap, we examined two levels of the neural tuning for print: coarse tuning (i.e., false character vs. stroke combination), and fine tuning (i.e., sub-lexical tuning: pseudo character vs. false character; and lexical tuning: real character vs. pseudo character). Using the event-related potential technique, we examined 14 typically developing children and 16 dyslexic children who were screened from 216 nine-year-old children in the third grade. For typically developing children, we observed both coarse and sub-lexical tuning. Critically, for dyslexic children, we found stronger N1 for false character than for stroke combination, suggesting intact coarse tuning, but a reduced N1 difference between false character and pseudo character, suggesting impaired sub-lexical tuning. These results clearly show selective impairments in fine neural tuning at the sub-lexical level in Chinese dyslexic children. Our findings may be associated with unique features of Chinese characters. Full article

Named entity recognition (NER) plays a crucial role in many downstream natural language processing (NLP) tasks. It is challenging for Chinese NER because of certain features of Chinese. Recently, large-scaled pre-training language models have been used in Chinese NER. However, since some of the pre-training language models do not use word information or just employ word information of single granularity, the semantic information in sentences could not be fully captured, which affects these models’ performance. To fully take advantage of word information and obtain richer semantic information, we propose a multi-granularity word fusion method for Chinese NER. We introduce multi-granularity word information into our model. To make full use of the information, we classify the information into three kinds: strong information, moderate information, and weak information. These kinds of information are encoded by encoders and then integrated with each other through the strong-weak feedback attention mechanism. Specifically, we apply two separate attention networks to word embeddings and N-grams embeddings. Then, the outputs are fused into another attention. In these three attentions, character embeddings are used to be the query of attentions. We call the results the multi-granularity word information. To combine character information and multi-granularity word information, we introduce two fusion strategies for better performance. The process makes our model obtain rich semantic information and reduces word segmentation errors and noise in an explicit way. We design experiments to get our model’s best performance by comparing some components. Ablation study is used to verify the effectiveness of each module. The final experiments are conducted on four Chinese NER benchmark datasets and the F1 scores are 81.51% for Ontonotes4.0, 95.47% for MSRA, 95.87% for Resume, and 69.41% for Weibo. The best improvement achieved by the proposed method is 1.37%. Experimental results show that our method outperforms most baselines and achieves the state-of-the-art method in performance. Full article