As a self-supervised deep learning paradigm, contrastive learning has achieved remarkable results in computer vision and natural language processing. Inspired by the success of contrastive learning in these fields, researchers have tried to extend it to graph data and promoted the development of graph contrastive learning. To provide a comprehensive overview of graph contrastive learning, this paper summarizes recent works under a unified framework to highlight the development trends. It also catalogues the popular datasets and evaluation metrics for graph contrastive learning, and concludes with the possible future direction of the field.

Large Language Models (LLMs) have demonstrated exceptional performance in various Natural Language Processing (NLP) tasks, providing a potential for achieving general language intelligence. However, their expanding application necessitates more accurate and comprehensive evaluations. Existing evaluation benchmarks and methods still have many short-comings, such as unreasonable evaluation tasks and uninterpretable evaluation results. With increasing attention to robustness, fairness and so on, the demand for holistic, interpretable evaluations is impressing. This paper delves into the current landscape and challenges of LLM evaluation, summarizes existing evaluation paradigms, analyzes limitations, introduces pertinent evaluation metrics and methodologies for LLMs and discusses the ongoing advancements and future directions in the evaluation of LLMs.

Current humor detection is focused on textual humor recognition rather than carrying out this task on multimodal data. This paper proposes a modal fusion approach to humor detection based on the attention mechanism. Firstly, the model encodes each single-modal context to obtain the feature vector, and then the hierarchical attention mechanism is applied on feature sequences to capture the correlation of multi-modal information in the paragraph context. Tested on the UR-FUNNY public data set, the proposed model achieves an improvement of 1.37% in accuracy compared to the previous best result.

Entity relation extraction aims to extract structured relation triples between entities from unstructured or semi-structured nature language texts. Character relation extraction is a finer-grained branch of entity relation extraction. Focusing on character relation extraction in Chinese literature, we presents a MF-CRC character relation extraction model. We first introduce adversarial learning framework to build the sentence-level noise classifier so as to filter the noise in the dataset. Then BERT and BiLSTM are employed and feature representations of Chinese surnames, gender and relation are designed. The character relation extraction model is finally established by integrating the multi-dimensional features. Experiments on three Chinese classics show that the proposed method outperforms SOTA models by 1.92% and 2.14% in micro-F₁ and macro-F₁ , respectively.

In contrast to the existing relation triple extraction focused on written texts, this paper proposes a GCN(Graph Convolutional Network) based approach to model dialogue scenarios. Compared with the entity relations in written text, those in dialogues emphasizes the relationship among humans and are more colloquial. To address this issue, our method regards dialogue sentences as nodes, and assigns weighted edges between sentences according to sentence distance. With such constructed a dialogue scene graph, we then applies GCN to model the relationship between dialogues. Experimental results on DialogRE show that our model outperforms the existing state-of-the-art baselines.

The data sparsity issue in recommendation can be resolved by including explicit information in the knowledge graph. Most existing knowledge graph-based methods capture user behaviors solely through entity relationships, ignoring the implicit cues between users and items to recommend. To this end, this paper proposes a unique recommendation approach incorporating the knowledge graph and the prompt learning. In particular, the knowledge graph is employed to propagate user preferences and produce corresponding dynamic behaviors. And, the implicit insights absent from the knowledge graph could be absorbed by feeding pre-trained language model (PLM) with static user features under the prompt learning setting. Finally, the template probability within the PLM vocabulary is intuitively selected as the possibility of the recommendation. Experiments on the MovieLens-1M, Book-Crossing, and Last.FM datasets show that our technique outperforms state-of-the-art baselines by 6.4%, 4.0% and 3.6% in AUC, and 6.0%, 1.8%, and 3.2% in F₁ value, respectively.

Lexical substitution (LS) aims at finding an appropriate substitute for a target word in a sentence. In contrast to the BERT-based LS, this paper proposes a method to generate substitution candidates base on paraphrase to utilize the existing large-scale paraphrase corpus which contains a large number of rules of word substitution. Specifically, we first employ a paraphrase dataset to train a neural paraphrase model. Then, we propose a special decoding method to focus only on the variation of the target word to extract substitute candidates. Finally, we rank substitute candidates for choosing the most appropriate substitution without modifying the meaning of the original sentence based on text generation evaluation metrics. Compared with existing state-of-the-art methods, experimental results show that our proposed methods achieve the best results on two widely used benchmarks (LS07 and CoInCo).

Current methods of aspect level sentiment classification are mostly based on cyclic neural network or single-layer attention mechanism while ignore the influence of location information on the emotional polarity of specific aspect words. This paper proposes an aspect level sentiment analysis model based on syntactic structure and mixed attention mechanism. It takes the position vector based on the syntactic structure tree as the auxiliary information, and adopts the mixed attention to extract the affective polarity of a sentence under a given aspect word. Specifically, it constructs positional attention mechanism and interactive multi-head attention mechanism, respectively, to obtain semantic information related to sentence and aspect words. The experiments on Restaurant and Laptop and ACL14 Twitter in Semeval 2014 public dataset show that, in most cases, the model performs better than the related baseline model and can effectively identify different aspects of emotional polarity.

To address the challenging issue of table acquisition in long financlal disclosures, this paper proposes a context feature fusion approach. A table classification dataset is first constructed by preprocessing these long financlal disclosures and extracting tables with their contexts in the document. Then different multiscale Convolution Neural Networks (CNNs) are used for feature extraction according to the characteristics of table information and context information. Comparded with the baseline experiments, the Micro-F1 and Macro-F1 scores have improved by over 0.37% and 1.24% respectively.

The multi-origin, diverse and multimodal nature of educational resources brings up enormous challenges for educational resources recommendation. To address this issue, this paper proposed a method that recommends questions for practicing based on multimodal semantic analysis. First, we extract the multimodal features and the semantic relationships between different modals to construct a representation structure of multimodal educational resources. Then, we model the knowledge map with an algorithm pre-trained on multimodal video features and question features. In the end, fine-tuned by pre-collected video-question features, the model can extract more robust feature representations to recommend practice questions that are highly related to the lecture videos. Experiments show that this method outperforms the current methods.

Compared with western languages, Hindi is a low resource language in Southeast Asia. Due to the lack of corpus, annotation specifications and computational modeling practices, the studies on Hindi natural language processing have not been well addressed. This paper reviews the research progresses in Hindi natural language processing in terms of the resource construction, part of speech tagging, named entity recognition, syntactic analysis, word sense disambiguation, as well as information retrieval, machine translation, sentiment analysis and automatic summarization. This paper also reveals the issues and challenges in Hindi natural language processing, and outlooks the future development trend.

Sentence boundary identification is an essential task in natural language processing. Because of issues such as concurrent ending words and data sparse, the existing Tibetan sentence boundary identification methods based on the dictionary or the statistical model are less efficient. This paper proposes an automatic Tibetan sentence boundary identification method based on Bi-LSTM and Self-Attention. Experiments reveal this method outperforms other method by achieving 97.7%, 98.06% and 97.88% in terms of macro accuracy, macro recall and macro F1, respectively. The experimental results also demonstrate that front-end truncation for fixed sentence length , and the skip-gram syllable word representations are more effective.

The question answering of college entrance examination reading comprehension is an important challenge in reading comprehension task in recent years. This paper proposes a model of answer sentence extraction based on heterogeneous graph neural network. Rich relationships (frame semantics and discourse topic relationships ) between nodes (sentences and words ) are introduced into the graph neural network. Therefore, questions can interact with candidate answer sentences through both words nodes and frame semantics and discourse topic relationships. The results show that the proposed model outperforms the baseline model with 78.08% F₁ value.

Existing machine reading comprehension models are defected in capturing the boundary information of the answer, leading to incomplete long answers and redundant short answers. This paper proposes a strategy to guide the machine reading comprehension through classification of answer length features. With the question and the document encoded by RoBERTa_wwm_ext pre-trained model, the questions are classified according to the predicted length of the answer. The result of the question classification is used to guide the answer prediction module in reading comprehension, where the beginning and end positions of all answers are finally obtained in the way of multi-task learning. Compared with the baseline models, the experimental results on the CMRC2018 dataset, the self-built Chinese bridge inspection question and answer dataset and the traditional Chinese data set DRCD all confirm the superior performance of the proposed method according to either EM value or F₁ value.

By means of ERPs, this paper explore the neural mechanism of semantic processing under information masking condition by comparing the processing of Chinese sentences in quiet condition, white noise condition, Chinese noise condition and English noise condition. It is found that the waveforms of N400, LPC and other ERPs induced by different noise conditions are different, which provide evidences for several conclusions. Firstly, the language information in speech masking occupies the cognitive and psychological resources required by the target sound processing, and the resource competition reduces the listener's ability to identify the target signals, resulting in the information masking in the form of language interference. Secondly, the speech intelligibility of the masker plays a more critical role for difficult semantic processing in the speech masking. The masking effect on semantic processing is smaller when the language is a very familiar or completely unfamiliar language, while the masking effect may be stronger when the masking noise is the non-native language to which the listener has been exposed. Finally, the listener comprehensible semantic content contained in unfamiliar speech noise that appears less frequently is more likely to trigger listener attention transfer if it conflicts with the listener expectations, which, in turn, increases information masking intensity.

Case source clues management is the initial step for industrial and commercial administration and law-enforcement. To deal with the sharp increasing case source clues, this paper explore the deep learning model to realize illegal types automatic recognition. After model selection and empirical research, the overall classification accuracy rate meets actual business needs. The experiment on a first-tier city’s data show that the proposed model can effectively realize the case source clues automatic classification.

Most of the current machine translation systems adopt the autoregressive method for decoding, which leads to low inference efficiency. The non-autoregressive method significantly improves the inference speed through parallel decoding, attracting increasing research interest. We conduct a systematic survey for recent efforts to narrow the translation quality gap between Non-Autoregressive Machine Translation (NART) and Autoregressive Machine Translation (ART). We categorize NART methods by the way to capture the dependencies of target sequences. We also discuss the challenges of NART research.

The rapid development of pre-trained models has made a breakthrough in the task of sentiment classification. However,there is a large number of semantically ambiguous and confusing text in the massive data provided by the Internet, which restricts the effect of most current classification models. To address this issue, a double triplet network for sentiment classification (DTN4SC) is proposed. This method improves the construction method of triplet sample combinations, by extracting and weighing two kinds of triplet samples from straightforward text and ordinary text, respectively, which captures the similarity between texts of the same category and the differences between texts of confusing categories. And during the training process, the confusing text in one batch is added to the next batch for further training. Experimental results on nlpcc2014, waimai_10k and ChnSentiCorp show that the proposed method has better performance in accuracy and F1 value compared with the existing sentiment classification methods of confusing text, by 3.16%, 2.35% and 2.5% improvements, respectively.

论辩（Argumentation）以人的逻辑论证过程作为研究对象，是一个涉及逻辑、哲学、语言、修辞、计算机科学和教育等多学科的研究领域。近年来，论辩研究引起计算语言学学者的关注，并催生了一个新的研究领域，即计算论辩学（Computational Argumentation）。学者们试图将人类关于逻辑论证的认知模型与计算模型结合起来，以提高人工智能自动推理的能力。根据参与论辩过程的人数不同，计算论辩学的研究可以分成两类，即单体式论辩（Monological Argumentation）和对话式论辩（Dialogical Argumentation）。单体式论辩的研究对象是仅有一个参与者的辩论性文本，如议论文和主题演讲等。相关的研究问题包括论辩单元检测、论辩结构预测、论辩策略分类和议论文评分等。对话式论辩的研究对象是针对某一个特定议题进行观点交互的论辩过程, 一般有多个参与者。相关的研究问题包括论辩结果预测、交互式论点对抽取、论辩逻辑链抽取等。

As the firststep in task-oriented dialogue system (TOD), Spoken Language Understanding (SLU) governs the overall system performance. The past few years have witnessed a great progress of SLU due to the huge success of Large Language Model (LLM). This paper investigated the SLU task (in contrast to written language understanding) with a focus on medical field. Specifically, this paper illustrates the difficulties and challenges in medical SLU task. And it summarizes the progress and shortcomings of the existing researches from the perspectives of datasets, algorithms and applications. Besides, combined with the latest progress of generative LLM, this paper outlines the new research direction in this field.

Interpretable sentiment analysis aims to judge the polarity of text, and at the same time, give evidence for judgements or evidence for predictions. Most of the existing sentiment analysis methods are black box models, and interpretability evaluation is still a problem to be solved. This paper proposes a interpretable sentiment analysis method based on UIE. According to the characteristics of sentiment interpretable tasks, this method uses methods such as few-shot and text clustering to improve the rationality and loyalty of the model. The experimental results show that this method has won the first place in the task of “2022 language and intelligent technology competition: sentiment interpretable evaluation”.

Currently, the research on Large Language Models (LLMs), such as InstructGPT, is primarily focused on free-form generation tasks, while the exploration in structured extraction tasks has been overlooked. In order to gain a deep understanding of LLMs on structured extraction tasks, this paper analyzes InstructGPT's performance on named entity recognition (NER), one of the fundamental structured extraction tasks, in both zero-shot and few-shot settings. To ensure the reliability of the findings, the experiments cover common and nested datasets from both biomedical domain and general domain. The results demonstrate that InstructGPT's performance on zero-shot NER achieves 11% to 56% of the performance by a finetuned small-scaled model. To explore why InstructGPT struggles with NER, this paper examines the outputs, finding invalid generation for 50% of them. Besides, the occurrence of both "false-negative" and "false-positive" predictions makes it difficult to improve performance by only addressing the invalid generation. Therefore, in addition to ensuring the validity of generated outputs, further research still should focus on finding effective ways of using InstructGPT in this area.

Code summarization aims to automatically generate the natural language description of source code snippets, which facilitates software maintenance and program understanding. Recent studies have shown that the popular methods utilizing Transformer-ignores the external semantic information such as API documents. Therefore, we propose an automatic code summary generation method based on an improved Transformer integrating multiple semantic features. This method uses three independent encoders to extract multiple semantic features of source code (text, structure and external API documentations information), and the non-parametric Fourier transform is used to replace the self-attention layer in the encoder. The computation time and memory usage of the Transformer structure are reduced by a linear transformation. Experimental results on open datasets prove the effectiveness of the method.

Recent studies show that visual information can help text achieve more accurate named entity recognition. However, most of the exiting work treats an image as a collection of visual objects and attempts to explicitly align visual objects with entities in text, fails to cope with modal bias well when visual objects and the entities are quantitatively and semantically inconsistent. To deal with this problem, we propose a debiased contrastive learning approach (DebiasCL) for multimodal named entity recognition. We utilize the visual objects density to guide visual context-rich sample mining, which enhances debiased contrastive learning to achieve better implicit alignment by optimizing the latent semantic space learning between visual and textual representations. Empirical results shows that the DebiasCL achieves a F₁-value of 75.04% and 86.51%, with 5.23% and 5.2% increased on "PER" and "MISC" entity type data in Twitter-2015 and Twitter-2017, respectively.

Testset for text proofreading evaluation is the basis of spell checking research, including traditional and standard text proofreading testset. The traditional testset for text proofreading is obtained by artificially forging the correct data through subjective experience. The standard testset for text proofreading is obtained from the real dataset with strong reliability. Based on the analysis of the construction methods of English and Chinese text proofreading testsets, combined with the characteristics of Tibetan language, this paper studies the testset construction for Tibetan text proofreading, and completes a standard text proofreading testset with statistical analysis of the types and distribution of errors. The validity and usability of the testset are verified.

Postoperative risk prediction has a positive effect on clinical resource plan, emergency plan preparation and postoperative risk and mortality reduction. To employ the unstructured preoperative diagnosis with rich semantic information, this paper proposes a postoperative risk prediction model via unstructured data representation enhancement. The model utilizes self-attention to fuse the structured data with unstructured preoperative diagnosis. Compared with the baseline methods, the proposed model improves F₁-Score by an average of 9.533% on the tasks of the pulmonary complication risk prediction, the ICU admission risk prediction and the cardiovascular adverse risk prediction.

Concept maps can intuitively display the correlation between concepts and provide teachers with teaching suggestions. Therefore, concept maps have become an important tool for teachers to conduct personalized teaching. However, how to generate a concept map that can reflect students’ learning ability and effectively guide teachers’ teaching is a big challenge in the current concept map research. This paper proposes a new automatic concept map generation model C-IK2. The C-IK2 model considers students’ different learning characteristics and concept understanding levels, and uses Birch algorithm to cluster students’ concept mastery characteristics to obtain student clusters. At the same time, the model considers the hierarchical structure of the concept map and is used to guide teachers’ teaching, combined with the lack of hierarchical structure of the improved LPG algorithm and the effective input sequence of the improved K2 algorithm to generate hierarchical conceptual maps with different learning characteristics of students. The experiment is based on ASIA standard data, and compared with the existing sequence-based latest improved K2 algorithm, the C-IK2 model improves the accuracy of the graph by 7.7%. Compared with existing score-based Bayesian network structure learning methods, the graph structure quality of the C-IK2 model is improved by 3.1%. Experiments show that the C-IK2 model effectively distinguishes different students’ understanding of concepts, and the hierarchical conceptual map generated at the same time has certain effectiveness, thereby helping teachers to carry out personalized teaching.

Named entity recognition is essential to the intelligent analysis of literary works. We annotate over 50 thousands named entities of four types from about 1.8 million words of two Jin Yong’s novels. According to the characteristics of novel text, this paper proposes a document-level named entity recognition model with a dictionary to record the historical state of Chinese characters. We use confidence estimation to fuse BiGRU-CRF and Transformer model. The experimental results show that the proposed method can effectively improve the performance of named entity recognition.

Named entity recognition is a key task in Tibetan processing. This paper proposes a Casaded BiLSTM-CRF method combining three Tibetan pre-training models (Word2Vec, ELMo, ALBERT). The cascade Tibetan named entity recognition refers to treat this task by two sub-tasks, i.e. entity boundary delineation and entity class determination. Experiments show that the proposed model decreases the training time by 28.30% compared with the BiLSTM-CRF model, and combining the pre-training technique achieves better recognition results.

To address such issues as the poor interpretability of current legal intelligence system, the unsatisfactory prediction of less-frequent and confusing legal causes and the insufficient research on civil disputes, an interpretable hierarchical legal causes prediction model (IHLCP) is proposed, taking the hierarchical dependence between legal causes as the source of interpretability. In IHLCP, the fact description is encoded by capturing the semantic differences of cases, and an improved attention-based seq2seq model is used to predict the cause path. Further, the inner text information of the cause is used to filter out the noise information in the fact description. Experiments show that the IHLCP model designed in this paper has achieved the state-of-art performance on three large-scale data sets: CIVIL (ACC-91.0%, Pre-67.5%, Recall-57.9%, F1-62.3%), FSC (ACC-94.9%, PRE-78.8%, RECALL-75.9%, F1-77.3%) and CAIL (ACC-92.3%, Pre-90.9%, Recall-89.7%, F1-90.3%), boosting the ACC and F₁ by 6.6% and 13.4%, respectively. The experimental resuces show that this model can help the system to understand the law causes, make up for the start comings of current legal intelligence system in few-shot and confusing Causes of law prediction, make up for the deficiency of low frequency confusing cause prediction and improve the inter pretability of the model.

Continual relation extraction is used to solve catastrophic forgetting caused by retraining models on new relations. Aiming at task-recency bias issue, this paper proposes a continual relation extraction method based on supervised contrastive replay. Specifically, for each new task, the model first uses the encoder to learn new sample embeddings, and then uses the samples of the same and different relation categories as positive and negative sample pairs to continually learn an embedding space with strong discrimination ability. At the same time, relation prototypes are added to the supervised contrastive loss to prevent the model from overfitting. Finally, the nearest class mean classifier is used for classification. The experimental results show that the proposed method can effectively alleviate the catastrophic forgetting issue in continual relation extraction, and achieve the state-of-the-art performance on FewRel and TACRED datasets.

Sememe is the core component that constitutes the conceptual description of words in HowNet, and the recommendation of sememes for describing new words or concepts is crucial for the automatic or semi-automatic extension of HowNet. Focusing on the sememe recommendation of new words, this paper proposes a sememe attention enhanced pre-training language model named SaBERT. To estimate the similarity between a new word and an in-vocabulary word of HowNet, we employ the existing concepts of the in-vocabulary word to describe the attention distribution of the sememe sequence, and optimize the BERT+CNN model with an objective of similarity isomorphism. Experimental results show that SaBERT achieves achieve 0.831 4, 0.800 7 and 0.815 8 for precision, recall and F₁ value, respectively.

The dialog-level relation extraction is characterized by casual language, low information density and abundant personal pronouns. This paper proposes an end-to-end dialogue relation extraction model via TOD-BERT (Task-Oriented Dialogue BERT) pre-trained language model. It adopts the attention mechanism to capture the interaction between different words and different relations. Besides, the co-reference information related to personal pronouns is applied to enrich the entity features. Validated on DialogRE, a new dialog-level relational extraction dataset, the proposed model reaches 63.77 F₁ score, which is significantly better than the baseline models.

This paper proposes BC-CapsNet model to extract more features to further improve the accuracy of text classification.The BERT model is used to embed words in the text, and the dual channel model and capsule network are used for feature extraction. One channel uses bidirectional threshold cyclic unit (BiGRU) to extract the context text information, and the other channel uses convolutional neural network (CNN) to capture the key features of the text. The features extracted by the two channels are finally fused and sent to the capsule network. Experiments on datasets of THUCNews and Ag_News show that the model can effectively improve the accuracy of text classification.

This paper presents a generative biomedical event extraction model based on the framework of the pre-trained language model T5, which allows the joint modeling of the three subtasks of trigger recognition, relation extraction and argument combination. The model employs a trie-based constrained decoding algorithm, which regulates sequence generation and reduces the search space for argument roles. Finally, curriculum learning algorithm is used in training, which familiarizes T5 with biomedical corpora and events with hierarchical structure. The model obtains 62.40% F₁-score on the Genia 2011 and 54.85% F₁-score on the Genia 2013, respectively, demonstrating the feasibility of using a generative approach to biomedical event extraction.

Visual dialogue is a popular and challenging cross modal task in recent years. It requires robots to fully understand the question being asked, properly reason from the contextual information, and provide meaningful multiple rounds of continuous responses in natural language. This paper proposes a Bert based visual dialogue algorithm via multi-level semantic context. Following the lightweight LTMI model, the algorithm introduces the BERT pre-training model to achieve semantic information fusion on both word and sentence levels. At the same time, the model applies the multitask training process to complete the cross modal fine-tuning in a self supervised manner. Compared with mainstream SOTA algorithms on public dataset of VisDial v0.9 and VisDial v1.0, experimental results show that the proposed model further improves the generalization ability of the algorithm and achieves superior performance.

Humor plays an important role in human communication and is abundant in sitcoms. Punchline is one of a form to achieve humorous effects in sitcoms. The existing punchlines recognition methods only recognize the punchline by modeling the contextual semantic relationship. In contrast, this paper proposes a new method based on multi-task learning model. First, we regard the transfer relationship between two tags as a manifestation of inconsistency in humor theory, and we use the conditional random field to learn this transfer relationship. Secondly, learning the transfer relationship between adjacent tags and the contextual semantic relationship can both capture the inconsistency between the setup and punchline, and we introduce the multi-task learning method to learn the meaning of each sentence, the meaning of all the characters that make up each sentence, the label transfer relationship at the word level and the label transfer relationship at the sentence level. Experiments on the English data set of CCL2020 ”Mavericks Cup” humorous calculation-sitcom punchlines recognition and evaluation task. show that the proposed method is 3.2% higher than the current best method, achieving the best effect on the punchlines recognition task.

Graph contrastive learning, a successful unsupervised node representation method, aims to learn node representations by pulling the augmented versions of the node together (positive examples), while pushing it with other nodes apart (negative examples). One key component of graph contrastive learning is the choice of negative examples, and existing methods fail accurately finding the challengeable negative examples that are critical to the model. We propose to learn a global negative example for all the nodes, through adversarial learning. Extensive experiment results demonstrate both the efficiency and effectiveness of the proposed model.

Frame Identification (FI), which aims to find the proper frame to activate for a target words in a given sentence, is an important prerequisite for labeling frame semantic roles. Generally, FI is regarded as a classifying task, applying the sequence modeling to learn the contextual representation of target words. To further capture the structural information of target words themselves, this paper proposes a model which fuses the contextual and structural information of target words. Specifically, BERT and GCN are utilized to model the contextual information of target words in different parts of speech and the structural information of target words in PropBank roles or dependence syntax, respectively. Also, this paper analyzes the structural differences of the dependency information of target words with different parts of speech, and employs an ensemble learning approach to consider the structural differences. Experiments on FN1.7 and CFN datasets show that our model outperforms the SOTA.

Dialogue state tracking is the core module of task-oriented dialogue system. Currently, multi-domain task-oriented dialogue system is difficult to track the dialogue state due to the complex dialogue scene. This paper proposes a state tracking model named DST-S²C,i.e.dialogue state tracking with slot connection and semantic connection. The model constructs the slots into a multi-relational graph, uses the hierarchical graph attention network to model the slot relationship, and extracts the slot embeddings that fuses multiple related-slot information. Furthermore, the slot-gate mechanism adds the local semantic information between the dialogue context and slots, which is essential to enhance the slot-gate mechanism performance. Experiments on MultiWOZ2.1 datasets show that DST-S²C outperforms the baseline model by 1.12% in joint accuracy and 0.39% in slot accuracy.