Syntax Parsing Research Articles

Text-Vision Relationship Alignment for Referring Image Segmentation

Referring image segmentation aims to segment object in an image based on a referring expression. Its difficulty lies in aligning expression semantics with visual instances. The existing methods based on semantic reasoning are limited by the performance of external syntax parser and do not explicitly explore the relationships between visual instances. This article proposes an end-to-end method for referring image segmentation by aligning ’linguistic relationship’ with ’visual relationships’. This method does not rely on external syntax parser for expression parsing. In this paper, the expression is adaptively and structurally parsed into three components: ’subject’, ’object’, and ’linguistic relationship’ by the Semantic Component Parser (SCP) in a learnable manner. Instances Activation Map Module (IAM) locates multiple visual instances based on the subject and object. In addition, the Relationship Based Visual Localization Module (RBVL) firstly enables each instance of the image to learn global knowledge, then decodes the visual relationships between these visual instances, and finally aligns the visual relationships with the linguistic relationships to further accurately locate the target object. The experimental results show that the proposed method improves performance by 4– 9% compared with baseline method on multiple referring image segmentation datasets.

Confidence-based Syntax encoding network for better ancient Chinese understanding

While neural-based models continue to make rapid strides, syntax remains a foundational element in the domain of Natural Language Processing (NLP), particularly in the context of Chinese language understanding. However, there exists a significant gap in research that integrates syntactic information for the understanding of ancient Chinese, primarily due to the lack of high-quality syntactic annotations. This paper explores the untapped potential of syntax to enhance ancient Chinese understanding, leveraging the “not-so-perfect” noisy syntax trees generated by unsupervised derivations and modern Chinese syntax parsers. To achieve this, we introduce a novel syntax encoding component: the confidence-based syntax encoding network (cSEN). This component is tailored to mitigate the side-effects arising from the noise associated with unsupervised syntax derivations and the incompatibility between ancient and modern Chinese. We validate the importance of syntax information and the efficacy of our cSEN through experimental tasks, specifically ancient poetry theme classification and ancient–modern Chinese translation. Our findings suggest that proper implementation of syntactic information can effectively enhance model understanding of ancient Chinese. The introduced cSEN proves vital in noise-rich environments, potentially revolutionizing the way information professionals approach and utilize ancient Chinese texts.

Research on smart contract vulnerability detection method based on domain features of solidity contracts and attention mechanism

The smart contract, a self-executing program on the blockchain, is key to programmable finance. However, the rise of smart contract use has also led to an increase in vulnerabilities that attract illegal activity from hackers. Traditional manual approaches for vulnerability detection, relying on domain experts, have limitations such as low automation and weak generalization. In this paper, we propose a deep learning approach that leverages domain-specific features and an attention mechanism to accurately detect vulnerabilities in smart contracts. Our approach reduces the reliance on manual input and enhances generalization by continuously learning code patterns of vulnerabilities, specifically detecting various types of vulnerabilities such as reentrancy, integer overflow, forced Ether injection, unchecked return value, denial of service, access control, short address attack, tx.origin, call stack overflow, timestamp dependency, random number dependency, and transaction order dependency vulnerabilities. In order to extract semantic information, we present a semantic distillation approach for detecting smart contract vulnerabilities. This approach involves using a syntax parser, Slither, to segment the code into smaller slices and word embedding to create a matrix for model training and prediction. Our experiments indicate that the BILSTM model is the best deep learning model for smart contract vulnerability detection task. We looked at how domain features and self-attentiveness mechanisms affected the ability to identify 12 different kinds of smart contract vulnerabilities. Our results show that by including domain features, we significantly increased the F1 values for 8 different types of vulnerabilities, with improvements ranging from 7.35% to 48.58%. The methods suggested in this study demonstrate a significant improvement in F1 scores ranging from 4.18% to 38.70% when compared to conventional detection tools like Oyente, Mythril, Osiris, Slither, Smartcheck, and Securify. This study provides developers with a more effective method of detecting smart contract vulnerabilities, assisting in the prevention of potential financial losses. This research provides developers with a more effective means of detecting smart contract vulnerabilities, thereby helping to prevent potential financial losses.

GAN-based data augmentation for transcriptomics: survey and comparative assessment.

Transcriptomics data are becoming more accessible due to high-throughput and less costly sequencing methods. However, data scarcity prevents exploiting deep learning models' full predictive power for phenotypes prediction. Artificially enhancing the training sets, namely data augmentation, is suggested as a regularization strategy. Data augmentation corresponds to label-invariant transformations of the training set (e.g. geometric transformations on images and syntax parsing on text data). Such transformations are, unfortunately, unknown in the transcriptomic field. Therefore, deep generative models such as generative adversarial networks (GANs) have been proposed to generate additional samples. In this article, we analyze GAN-based data augmentation strategies with respect to performance indicators and the classification of cancer phenotypes. This work highlights a significant boost in binary and multiclass classification performances due to augmentation strategies. Without augmentation, training a classifier on only 50 RNA-seq samples yields an accuracy of, respectively, 94% and 70% for binary and tissue classification. In comparison, we achieved 98% and 94% of accuracy when adding 1000 augmented samples. Richer architectures and more expensive training of the GAN return better augmentation performances and generated data quality overall. Further analysis of the generated data shows that several performance indicators are needed to assess its quality correctly. All data used for this research are publicly available and comes from The Cancer Genome Atlas. Reproducible code is available on the GitLab repository: https://forge.ibisc.univ-evry.fr/alacan/GANs-for-transcriptomics.

Block-level dependency syntax based model for end-to-end aspect-based sentiment analysis

End-to-End aspect-based sentiment analysis (E2E-ABSA) aims to jointly extract aspect terms and identify their sentiment polarities. Although previous research has demonstrated that syntax knowledge can be beneficial for E2E-ABSA, standard syntax dependency parsing struggles to capture the block-level relation between aspect and opinion terms, which hinders the role of syntax in E2E-ABSA. To address this issue, this paper proposes a block-level dependency syntax parsing (BDEP) based model to enhance the performance of E2E-ABSA. BDEP is constructed by incorporating routine dependency syntax parsing and part-of-speech tagging, which enables the capture of block-level relations. Subsequently. the BDEP-guided interactive attention module (BDEP-IAM) is used to obtain the aspect-aware representation of each word. Finally the adaptive fusion module is leveraged to combine the semantic-syntactic representation to simultaneously extract the aspect term and identify aspect-orient sentiment polarity. The model is evaluated on five benchmark datasets, including Laptop14, Rest _ALL, Restaurant14, Restaurant15, and TWITTER, with F1 scores of 62.67%, 76.53%, 75.42%, 62.21%, and 58.03%, respectively. The results show that our model outperforms the other compared state-of-the-art (SOTA) methods on all datasets. Additionally, ablation experiments confirm the efficacy of BDEP and IAM in improving aspect-level sentiment analysis.

Query Generation for Answering Complex Questions in Russian Using a Syntax Parser

Query Generation for Answering Complex Questions in Russian Using a Syntax Parser

Learn from structural scope: Improving aspect-level sentiment analysis with hybrid graph convolutional networks

Aspect-level sentiment analysis aims to determine the sentiment polarity towards a specific target in a sentence. The main challenge of this task is to effectively model the relation between targets and sentiments so as to filter out noisy opinion words from irrelevant targets. Most recent efforts capture relations through target-sentiment pairs or opinion spans from a word-level or phrase-level perspective. Based on the observation that targets and sentiments essentially establish relations following the grammatical hierarchy of phrase-clause-sentence structure, it is hopeful to exploit comprehensive syntactic information for better guiding the learning process. Therefore, we introduce the concept of Scope, which outlines a structural text region related to a specific target. To jointly learn structural Scope and predict the sentiment polarity, we propose a hybrid graph convolutional network (HGCN) to synthesize information from constituency tree and dependency tree, exploring the potential of linking two syntax parsing methods to enrich the representation. Experimental results on five public datasets illustrate that our HGCN model outperforms current state-of-the-art baselines. More specifically, the average accuracy/ F1 score improvements of our HGCN compared to baseline models on Restaurant 14, 15 and 16 are 2.46%/5.36%, 2.25%/5.70% and 1.73%/5.50%, while the performance improvements are 3.32%/4.30% and 2.50%/3.08% on the Laptop and Twitter datasets, respectively. Furthermore, when cascaded to five models, our method has significantly improved their performances by simplifying the sentence from multiple targets to a single one.

Collaborative Writing Tools for Predicting Verb Tense Using Syntax Parsing on Learning Networks

Collaborative writing tools and Natural language processing are plays a vital role in learning networks. These tools are involved with the dealings among computer systems and human languages. It processes the data through syntax analysis, parsing and lexical analysis, and etc. Syntax analysis is used for syntactic parsing deals with the syntactic structure of a sentence. The collaborative writing tools and natural language processing applications are used for verb tense prediction and it it encodes the temporal order of activities in a sentence. Recognizing the syntactic structure is beneficial in identifying the means of a sentence. The model in this paper is introduced to predict verb tense based on lexical and syntactic features. This model works on English articles, every article will be split to sentences using the tokenization process. Every token in sentences will be analyzed and model will parse the sentences the use of tenses algorithms that represent grammar rules of the English language. This model is given precise accuracy when it is examined on articles/ stories.

Distinguishing Syntactic Operations in the Brain: Dependency and Phrase-Structure Parsing.

Finding the structure of a sentence-the way its words hold together to convey meaning-is a fundamental step in language comprehension. Several brain regions, including the left inferior frontal gyrus, the left posterior superior temporal gyrus, and the left anterior temporal pole, are supposed to support this operation. The exact role of these areas is nonetheless still debated. In this paper we investigate the hypothesis that different brain regions could be sensitive to different kinds of syntactic computations. We compare the fit of phrase-structure and dependency structure descriptors to activity in brain areas using fMRI. Our results show a division between areas with regard to the type of structure computed, with the left anterior temporal pole and left inferior frontal gyrus favouring dependency structures and left posterior superior temporal gyrus favouring phrase structures.

Manipuri Morphological Analysis

Morphological analysis is the basic foundation in Natural Language Processing applications including Syntax Parsing, Machine Translation (MT), Information Retrieval (IR) and Automatic Indexing. Morphological Analysis can provide valuable information for computer based linguistics task such as Lemmatization and studies of internal structure of the words or the feature values of the word. Computational Morphology is the application of morphological rules in the field of Computational Linguistics, and it is the emerging area in AI, which studies the structure of words, which are formed by combining smaller units of linguistics information, called morphemes: the building blocks of words. It provides about Semantic and Syntactic role in a sentence. It can analyze the Manipuri word forms and produces grammatical information, which is associated with the lexicon. Morphological Analyzer for Manipuri language has been tested on 4500 Manipuri lexicons in Shakti Standard Format (SSF) using Meitei Mayek Unicode as source; thereby an accuracy of 84% has been obtained on a manual check.

A Trajectory Classification Model Using Grammar Parsing

Trajectory classification is a hot topic in the field of spatiotemporal data mining. Existing models exert spatial or temporal computation on trajectory data, which require huge efforts and are often time consuming and lack of efficiency. This article proposes a model to classify unknown ship trajectories through a syntax recognition approach. By using the background semantic information in the rasterized sea chart, the model transforms the ship trajectories into symbolic sentences containing both spatiotemporal and semantic information, and reduces their scale. The class feature is expressed as a context-free grammar and the data classification is implemented through syntax parsing. The parsing requires less computation and is more efficient. Experiments are carried out to verify the model’s practicability, and the results show that it is valid and effective.

Exploring Segment Representations for Neural Semi-Markov Conditional Random Fields

Many problems in natural language processing (NLP) can be cast as the problem of segmenting a sequence. In this article, we combine the semi-Markov conditional random fields (semi-CRF) with neural networks to solve NLP segmentation problems. We focus on the segment representation in neural semi-CRF which is important to the performance. Based on our preliminary work in Liu et al. [1] , we represent a segment by both encoding the subsequence and embedding the segment string. We conduct a systematic study of the utility of various components in subsequence encoding and propose a method of constructing and deriving segment string embeddings. Extensive experiments on three typical segmentation problems, namely, shallow syntax parsing, named entity recognition, and Chinese word segmentation are conducted. The results show that we can achieve equally-performed subsequence encoding with a three times faster concatenation network compared to previous work. The results also show that the segment string embeddings help our neural semi-CRF model to achieve a macro-averaged error reduction of 13.15% over a strong baseline using deep contextualized embeddings and bidirectional long-short-term memory CRF, which also show the usefulness of semi-CRF even with contextualized embeddings. These results are competitive with the state-of-the-art segmentation systems.

Chinese Syntax Parsing Based on Sliding Match of Semantic String

Different from the current syntax parsing based on deep learning, we present a novel Chinese parsing method, which is based on Sliding Match of Semantic String (SMOSS). (1) Training stage: In a treebank, headwords of tree nodes are represented by semantic codes given in the Synonym Dictionary (Tongyici Cilin). N-gram semantic templates are extracted from every layer of a syntax tree by means of sliding window to establish one N-gram semantic template library. (2) Parsing stage: Words of a sentence, including headwords of chunks, are represented by the semantic codes from Tongyici Cilin. With the sliding window method, N-gram semantic code strings are extracted to match with the templates in the N-gram semantic template library; subsequently, the mapping information of the matched templates is employed to guide the chunking of semantic code strings. The Chinese syntax parsing is completed through continuous matching and chunking. On the same training scale, N-gram semantic template can create favorable conditions for flexible matching and improve the syntax parsing performance. With train and test sets from the Tsinghua Chinese Treebank (TCT), the results are F1-score 99.71% (closed test) and F1-score 70.43% (open test), respectively.

Emergence of cognitive priming and structure building from the hierarchical interaction of canonical microcircuit models

The concept of connectionism states that higher cognitive functions emerge from the interaction of many simple elements. Accordingly, research on canonical microcircuits conceptualizes findings on fundamental neuroanatomical circuits as well as recurrent organizational principles of the cerebral cortex and examines the link between architectures and their associated functionality. In this study, we establish minimal canonical microcircuit models as elements of hierarchical processing networks. Based on a combination of descriptive time simulations and explanatory state-space mappings, we show that minimal canonical microcircuits effectively segregate feedforward and feedback information flows and that feedback information conditions basic processing operations in minimal canonical microcircuits. Further, we derive and examine two prototypical meta-circuits of cooperating minimal canonical microcircuits for the neurocognitive problems of priming and structure building. Through the application of these findings to a language network of syntax parsing, this study embodies neurocognitive research on hierarchical communication in light of canonical microcircuits, cell assembly theory, and predictive coding.

A Sequential Neural Encoder With Latent Structured Description for Modeling Sentences

In this paper, we propose a sequential neural encoder with latent structured description (SNELSD) for modeling sentences. This model introduces latent chunk-level representations into conventional sequential neural encoders, i.e., recurrent neural networks (RNNs) with long short-term memory (LSTM) units, to consider the compositionality of languages in semantic modeling. An SNELSD model has a hierarchical structure that includes a detection layer and a description layer. The detection layer predicts the boundaries of latent word chunks in an input sentence and derives a chunk-level vector for each word. The description layer utilizes modified LSTM units to process these chunk-level vectors in a recurrent manner and produces sequential encoding outputs. These output vectors are further concatenated with word vectors or the outputs of a chain LSTM encoder to obtain the final sentence representation. All the model parameters are learned in an end-to-end manner without a dependency on additional text chunking or syntax parsing. A natural language inference (NLI) task and a sentiment analysis (SA) task are adopted to evaluate the performance of our proposed model. The experimental results demonstrate the effectiveness of the proposed SNELSD model on exploring task-dependent chunking patterns during the semantic modeling of sentences. Furthermore, the proposed method achieves better performance than conventional chain LSTMs and tree-structured LSTMs on both tasks.

Chinese-Naxi syntactic statistical machine translation based on tree-to-tree

For the purpose of using Naxi syntax information efficiently, we put forward a method of Chinese-Naxi syntactic statistical machine translation based on the tree-to-tree model. Firstly, for using syntax information of source language and target language, collecting Chinese-Naxi aligned parallel corpus and making a syntax parsing on both side, the method obtains corresponding phrase structure trees of Chinese and Naxi. Then, by using GMKH algorithm to extract a large number of translation rules between Chinese treelets and Naxi treelets, inferring their probabilistic relationship from these rules, it obtains the translation templates. Finally, using these translation templates, through a tree-parsing algorithm, to guide the decoding, translating each Chinese phrase treelet in bottom-up, it obtains the final translation text. In comparison with the tree-to-string model, the experiments show that this method improves 1.2 BLEU value. This proves that both Chinese syntactic information and Naxi syntactic information are very helpful in improving the performance of Chinese-Naxi machine translation.

A model of individualized canonical microcircuits supporting cognitive operations.

Major cognitive functions such as language, memory, and decision-making are thought to rely on distributed networks of a large number of basic elements, called canonical microcircuits. In this theoretical study we propose a novel canonical microcircuit model and find that it supports two basic computational operations: a gating mechanism and working memory. By means of bifurcation analysis we systematically investigate the dynamical behavior of the canonical microcircuit with respect to parameters that govern the local network balance, that is, the relationship between excitation and inhibition, and key intrinsic feedback architectures of canonical microcircuits. We relate the local behavior of the canonical microcircuit to cognitive processing and demonstrate how a network of interacting canonical microcircuits enables the establishment of spatiotemporal sequences in the context of syntax parsing during sentence comprehension. This study provides a framework for using individualized canonical microcircuits for the construction of biologically realistic networks supporting cognitive operations.

Omitting Code Clones Based on Ranking the Called Clones

Code clones represent a stumbling blocking the way of having a more readable, maintainable and less complicated source codes, free of bugs and errors. Many studies had been proposed for detecting and omitting the four types of cloned codes based on pattern matching, syntax parsing, tree parsing and refactoring which is the most commonly used technique to remove the code clones from software, while maintaining its original behavior. In this paper, we propose an automated refactoring technique and its correspondence algorithm to omit code clones of type 1 and type 2. The proposed technique performance was tested and evaluated using four open source Java projects JFreeChart, JRuby, JCommon and Apache ant. The performance of the source codes was indicated based on number of metrics as the lines of code, number of blank lines, method’s count and cyclomatic complexity before and after applying the proposed technique. The experimentation results indicated that the proposed technique had showed superiority over the state-of-the-art through omitting the cloned codes with the possibility of maintaining the stability and correctness of behavior of the source codes under consideration.

Research on feature-based opinion mining using topic maps

Purpose Opinion mining (OM), also known as “sentiment classification”, which aims to discover common patterns of user opinions from their textual statements automatically or semi-automatically, is not only useful for customers, but also for manufacturers. However, because of the complexity of natural language, there are still some problems, such as domain dependence of sentiment words, extraction of implicit features and others. The purpose of this paper is to propose an OM method based on topic maps to solve these problems. Design/methodology/approach Domain-specific knowledge is key to solve problems in feature-based OM. On the one hand, topic maps, as an ontology framework, are composed of topics, associations, occurrences and scopes, and can represent a class of knowledge representation schemes. On the other hand, compared with ontology, topic maps have many advantages. Thus, it is better to integrate domain-specific knowledge into OM based on topic maps. This method can make full use of the semantic relationships among feature words and sentiment words. Findings In feature-level OM, most of the existing research associate product features and opinions by their explicit co-occurrence, or use syntax parsing to judge the modification relationship between opinion words and product features within a review unit. They are mostly based on the structure of language units without considering domain knowledge. Only few methods based on ontology incorporate domain knowledge into feature-based OM, but they only use the “is-a” relation between concepts. Therefore, this paper proposes feature-based OM using topic maps. The experimental results revealed that this method can improve the accuracy of the OM. The findings of this study not only advance the state of OM research but also shed light on future research directions. Research limitations/implications To demonstrate the “feature-based OM using topic maps” applications, this work implements a prototype that helps users to find their new washing machines. Originality/value This paper presents a new method of feature-based OM using topic maps, which can integrate domain-specific knowledge into feature-based OM effectively. This method can improve the accuracy of the OM greatly. The proposed method can be applied across various application domains, such as e-commerce and e-government.

EXTRACTING ACTIONS FROM INSTRUCTION MANUAL AND TESTING THEIR EXECUTION IN A ROBOTIC SIMULATION

Service robots are expected to execute household manipulation tasks on daily basis. These tasks are often related to the operation of home appliances and can be decomposed into specific manipulation actions such as pick up a cup, place a cup, press a button, turn a knob, open or close a cover, etc. This research proposes to use task instructions collected from manuals of household appliances to extract a series of actions that a robot needs to perform in order to accomplish the task. We describe the extraction method of action and object from these task instructions including syntax parsing of sentences and searching the pairs of action and object in each parse tree based on part-of-speech. The extracted actions then will be executed by a robot. We apply a simulation environment with ROS, Gazebo simulator and a virtual robot PR2 for testing their execution. In experiments, we implement the extraction method and evaluate the extracted results of actions and object. In addition, we test the execution of actions pick and place in the proposed simulation environment.