Syntactic Structure Features Research Articles

Incorporating knowledge for joint Chinese word segmentation and part-of-speech tagging with SynSemGCN

PurposeRecent trends have shown the integration of Chinese word segmentation (CWS) and part-of-speech (POS) tagging to enhance syntactic and semantic parsing. However, the potential utility of hierarchical and structural information in these tasks remains underexplored. This study aims to leverage multiple external knowledge sources (e.g. syntactic and semantic features, lexicons) through various modules for the joint task.Design/methodology/approachWe introduce a novel learning framework for the joint CWS and POS tagging task, utilizing graph convolutional networks (GCNs) to encode syntactic structure and semantic features. The framework also incorporates a pre-defined lexicon through a lexicon attention module. We evaluate our model on a range of public corpora, including CTB5, PKU and UD, the novel ZX dataset and the comprehensive CTB9 dataset.FindingsExperimental results on these benchmark corpora demonstrate the effectiveness of our model in improving the performance of the joint task. Notably, we find that syntax information significantly enhances performance, while lexicon information helps mitigate the issue of out-of-vocabulary (OOV) words.Originality/valueThis study introduces a comprehensive approach to the joint CWS and POS tagging task by combining multiple features. Moreover, the proposed framework offers potential adaptability to other sequence labeling tasks, such as named entity recognition (NER).

Title Features in Research Articles: A Disciplinary Study of Law

This study brings to the fore trends in title research by investigating title features in law papers extracted by law readers from law-related journals. To this end, 447 articles published in 266 journals from 1946 to 2023 were coded and analyzed statistically. Title length, syntactic structure, and content features were considered. The quantitative results reveal that titles in law articles demonstrated 1) an increase in length 2) a favor of single declarative titles and compound titles with colon 3) an obvious trend of using descriptive titles concerning title content. The current study therefore reflects the full complexity and a comprehensive picture of law articles, demonstrates title features and trends in law paper writing, and thus in light of significant findings, introduces novice writers, especially law students, to disciplinary language use in convention.

Knowledge Graph-Based Hierarchical Text Semantic Representation

Document representation is the basis of language modeling. Its goal is to turn natural language text that flows into a structured form that can be stored and processed by a computer. The bag-of-words model is used by most of the text-representation methods that are currently available. And yet, they do not consider how phrases are used in the text, which hurts the performance of tasks that use natural language processing later on. Representing the meaning of text by phrases is a promising area of future research, but it is hard to do well because phrases are organized in a hierarchy and mining efficiency is low. In this paper, we put forward a method called hierarchical text semantic representation using the knowledge graph (HTSRKG), which uses syntactic structure features to find hierarchical phrases and knowledge graphs to improve how phrases are evaluated. First, we use CKY and PCFG to build the syntax tree sentence by sentence. Second, we walk through the parse tree using the hierarchical routing process to obtain the mixed phrase semantics in passages. Finally, the introduction of the knowledge graph improves the efficiency of text semantic extraction and the accuracy of text representation. This gives us a solid foundation for tasks involving natural language processing that come after. Extensive testing on actual datasets shows that HTSRKG surpasses baseline approaches with respect to text semantic representation, and the results of a recent benchmarking study support this.

Fine-Grained Software Defect Prediction Based on the Method-Call Sequence.

Currently, software defect-prediction technology is being extensively researched in the design of metrics. However, the research objects are mainly limited to coarse-grained entities such as classes, files, and packages, and there is a wide range of defects that are difficult to predict in actual situations. To further explore the information between sequences of method calls and to learn the code semantics and syntactic structure between methods, we generated a method-call sequence that retains the code context structure information and the token sequence representing semantic information. We embedded the token sequence into the method-call sequence and encoded it into a fixed-length real-valued vector. We then built a defect-prediction model based on the transformer, which maps the code-vector representation containing the method-call sequences to a low-dimensional vector space to generate semantic features and syntactic structure features and also predicts the defect density of the method-call sequence. We conducted experiments on 10 open-source projects using the ELFF dataset. The experimental results show that the method-call sequence-level prediction effect is better than the class-level effect, and the prediction results are more stable than those of the method level. The mean absolute error (MAE) value of our approach was 8% lower than that of the other deep-learning methods.

Структура та семантика слоганів (На основі слоганів Міжнародного пісенного конкурсу)

Linguistic research of the of slogans structure and semantics is an increasing trend which helps to understand how a company can shape its image and achieve its communicative goals. The article clarifies the definition of the term “slogan” and presents the findings of the research done into the slogans used in international song contests, namely their syntactic structure, and lexical and semantic features.

Automated defect identification via path analysis-based features with transfer learning

Recently, artificial intelligence techniques have been widely applied to address various specialized tasks in software engineering, such as code generation, defect identification, and bug repair. Despite the diffuse usage of static analysis tools in automatically detecting potential software defects, developers consider the large number of reported alarms and the expensive cost of manual inspection to be a key barrier to using them in practice. To automate the process of defect identification, researchers utilize machine learning algorithms with a set of hand-engineered features to build classification models for identifying alarms as actionable or unactionable. However, traditional features often fail to represent the deep syntactic structure of alarms. To bridge the gap between programs’ syntactic structure and defect identification features, this paper first extracts a set of novel fine-grained features at variable-level, called path-variable characteristic, by applying path analysis techniques in the feature extraction process. We then raise a two-stage transfer learning approach based on our proposed features, called feature ranking-matching based transfer learning, to increase the performance of cross-project defect identification. Our experimental results for eight open-source projects show that the proposed features at variable-level are promising and can yield significant improvement on both within-project and cross-project defect identification.

Transformer Based Multi-Grained Attention Network for Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis aims to predict sentiment polarity for every aspect in a sentence review. Most existing approaches are based on the sequence models, which may superimpose the emotional semantics of different tendencies and lack syntactic structure information. And most models adopt coarse-grained attention mechanism which still face the issues of weakness interaction between aspect and context. In this paper, we propose a transformer based multi-grained attention network (T-MGAN), which utilizes the Transformer module to learn the word-level representations of aspects and context respectively, and further utilizes the Tree Transformer module to obtain the phrase-level representations of contexts. It is capable of extracting the syntactic structure features and syntax information of aspect and context. In addition, we adopt dual-pooling method and multi-grained attention network to extract high quality aspect-context interactive representations. We evaluate the proposed model on three datasets and prove the effectiveness of the proposed model.

Exploiting syntactic and semantics information for chemical-disease relation extraction.

Identifying chemical–disease relations (CDR) from biomedical literature could improve chemical safety and toxicity studies. This article proposes a novel syntactic and semantic information exploitation method for CDR extraction. The proposed method consists of a feature-based model, a tree kernel-based model and a neural network model. The feature-based model exploits lexical features, the tree kernel-based model captures syntactic structure features, and the neural network model generates semantic representations. The motivation of our method is to fully utilize the nice properties of the three models to explore diverse information for CDR extraction. Experiments on the BioCreative V CDR dataset show that the three models are all effective for CDR extraction, and their combination could further improve extraction performance. Database URL: http://www.biocreative.org/resources/corpora/biocreative-v-cdr-corpus/.

Neural bases of syntax-semantics interface processing.

The binding problem-question of how information between the modules of the linguistic system is integrated during language processing-is as yet unresolved. The remarkable speed of language processing and comprehension (Pulvermüller et al. 2009) suggests that at least coarse semantic information (e.g. noun animacy) and syntactically-relevant information (e.g. verbal template) are integrated rapidly to allow for coarse comprehension. This EEG study investigated syntax-semantics interface processing during word-by-word sentence reading. As alpha-band neural activity serves as an inhibition mechanism for local networks, we used topographical distribution of alpha power to help identify the timecourse of the binding process. We manipulated the syntactic parameter of verbal event structure, and semantic parameter of noun animacy in reduced relative clauses (RRCs, e.g. "The witness/mansion seized/protected by the agent was in danger"), to investigate the neural bases of interaction between syntactic and semantic networks during sentence processing. The word-by-word stimulus presentation method in the present experiment required manipulation of both syntactic structure and semantic features in the working memory. The results demonstrated a gradient distribution of early components (biphasic posterior P1-N2 and anterior N1-P2) over function words "by" and "the", and the verb, corresponding to facilitation or conflict resulting from the syntactic (telicity) and semantic (animacy) cues in the preceding portion of the sentence. This was followed by assimilation of power distribution in the α band at the second noun. The flattened distribution of α power during the mental manipulation with high demand on working memory-thematic role re-assignment-demonstrates a state of α equilibrium with strong functional coupling between posterior and anterior regions. These results demonstrate that the processing of semantic and syntactic features during sentence comprehension proceeds in highly integrated fashion using gating of attentional resources to facilitate rapid comprehension, with attentional suppression of global alpha power to facilitate interaction of local networks.

Reflexive choice in Dutch and German

Standard Dutch and German have two reflexive forms: a weak form (zich in Dutch and sich in German) and a strong form (zichzelf in Dutch and sich selbst in German). The choice between the two reflexive forms in Dutch has been explained by the selectional restrictions of the verb, distinguishing between three verb classes: inherently reflexive verbs, accidentally reflexive verbs and transitive verbs. The same three verb classes can be distinguished in German, suggesting that the factors governing reflexive choice in Dutch and German are similar. However, several studies have pointed out that Dutch zich is more restricted in its use than German sich. We used a forced-choice task to test adult Dutch and German participants on their preference for the weak versus strong reflexive form with various verb classes and sentence types. Comparing similar sentences across the two languages, we observe an overall preference for the strong reflexive in Dutch but an overall preference for the weak reflexive in German. Looking at the participants’ reflexive choices within each language, we found effects of verb class, syntactic structure (transitive versus ECM constructions) and semantic features. Whereas the semantic feature habituality did not affect reflexive choice in either language, intentionality did so in Dutch only, and tense and possibly focus affected reflexive choice in both languages. These observations seem problematic for the syntactically motivated dual-entry account of reflexive choice, but are consistent with the likelihood account.

Using a Hybrid Convolution Tree Kernel for Semantic Role Labeling

As a kind of Shallow Semantic Parsing, Semantic Role Labeling (SRL) is gaining more attention as it benefits a wide range of natural language processing applications. Given a sentence, the task of SRL is to recognize semantic arguments (roles) for each predicate (target verb or noun). Feature-based methods have achieved much success in SRL and are regarded as the state-of-the-art methods for SRL. However, these methods are less effective in modeling structured features. As an extension of feature-based methods, kernel-based methods are able to capture structured features more efficiently in a much higher dimension. Application of kernel methods to SRL has been achieved by selecting the tree portion of a predicate and one of its arguments as feature space, which is named as predicate-argument feature (PAF) kernel. The PAF kernel captures the syntactic tree structure features using convolution tree kernel, however, it does not distinguish between the path structure and the constituent structure. In this article, a hybrid convolution tree kernel is proposed to model different linguistic objects. The hybrid convolution tree kernel consists of two individual convolution tree kernels. They are a Path kernel, which captures predicate-argument link features, and a Constituent Structure kernel, which captures the syntactic structure features of arguments. Evaluations on the data sets of the CoNLL-2005 SRL shared task and the Chinese PropBank (CPB) show that our proposed hybrid convolution tree kernel statistically significantly outperforms the previous tree kernels. Moreover, in order to maximize the system performance, we present a composite kernel through combining our hybrid convolution tree kernel method with a feature-based method extended by the polynomial kernel. The experimental results show that the composite kernel achieves better performance than each of the individual methods and outperforms the best reported system on the CoNLL-2005 corpus when only one syntactic parser is used and on the CPB corpus when automated syntactic parse results and correct syntactic parse results are used respectively.

Quantitative assessment of gastric atrophy using the syntactic structure analysis.

AIM: To assess the topographical relation between gastric glands, using the minimum spanning tree (MST), to derive both a model of neighbourhood and quantitative representation of the tissue's architecture, to...

Syntactic structure analysis in uveal melanomas.

Syntactic structure analysis was carried out successfully on 92 paraffin embedded uveal melanomas, taken from patients with a minimum follow up of 5 years. This simple, fast, and reproducible method of describing the tumour architecture has been significantly correlated with malignancy in tumours from several sites. Paraffin sections 5 microns thick, were cut and stained with haematoxylin and eosin. Tumours were classified according to a modification of the Callender classification. A minimum spanning tree (MST), using the centre points of tumour nuclei, was constructed in five randomly chosen fields with an interactive digitising video overlay system. Ten syntactic structure features were derived from each MST; subsequently, the mean and standard deviation of the five fields analysed were calculated for further statistical analysis. Reproducibility was acceptable with a mean correlation coefficient of 0.70. In univariate survival analysis, the percentage of points with three neighbours yielded prognostic significance (p < 0.05). Minimum spanning tree variables were compared (chi 2 test) with classic tumour prognosticators and there was a significant correlation between Callender cell type and the following MST parameters: mean number of points (p < 0.003); MST length (p < 0.003); mean line length (p < 0.01); number of nuclei with one neighbour (p < 0.004); number of nuclei with two neighbours (p < 0.02), and number of nuclei with three neighbours (p < 0.005). Syntactic structure analysis is an evolving technique, but may be able to mathematically (and reproducibly) describe melanoma architecture across the spectrum of the Callender classes. This would also allow architectural grading of tumours within the specific Callender groups, providing more precise prognostic information. Further modifications of this technique are necessary to optimise prognostic potential when applied to uveal melanomas.

Syntactic structure analysis in invasive breast cancer: Analysis of reproducibility, biologic background, and prognostic value

The reproducibility, biologic background, and prognostic value of syntactic structure analysis were studied in a group of 94 patients with invasive primary breast cancer. Using an interactive digitizing video overlay system, the centers of malignant breast cancer nuclei were marked in the five (subjectively) most cellular fields of vision for each case at a final magnification of × 1,200, and the corresponding minimum spanning tree was composed for each field. From each minimum spanning tree, 10 syntactic structure features were derived; subsequently, the mean, standard deviation, minimum, and maximum values of the five fields analyzed were calculated for further statistical analysis. Forty statistics thus were available for each case. The reproducibility of repeatedly measuring the same field (independent of nuclearity) and the same patient twice by the same or different observers was good for most of the syntactic structure features. When comparing the statistics of the syntactic structure features with other established prognosticators, correlations were found with (in this order) standard deviation and mean nuclear area (expressing nuclear differentiation), volume percentage epithelium (expressing architectural differentiation), and mitotic activity index. In univariate survival analysis several syntactic structure statistics yielded prognostic significance, the best being the maximum of the number of nuclei with two neighbors ( P = .002; Mantel-Cox test, 12.4). Multivariate analysis revealed that syntactic structure features did not provide additional prognostic values with regard to each other. However, they did show additional prognostic values with regard to the multivariate prognostic index (currently one of the best prognosticators in breast cancer), which combines the mitotic activity index, lymph node status, and tumor size. Measurement of syntactic structure features could therefore contribute to an improved prediction of prognosis of breast cancer patients. In conclusion, syntactic structure analysis is a simple, fast, and highly reproducible technique that shows prognostic value in invasive breast cancer and also has important prognostic value with regard to the well-established and prognostically strong morphometric features. It seems to be a promising new method of analyzing tissue architecture in breast cancer and perhaps in many other tumors.