Semantic Context Research Articles

An entity and relation extraction model based on context query and axial attention towards patent texts

Patent Entity and Relation Extraction (PERE) aims to extract entities and entity-relation triples from unstructured patent texts. PERE is one of the fundamental tasks in patent text mining, providing crucial technical support for patent retrieval and technology opportunity discovery. Previous works struggle to capture the implicit semantic information hidden within overlapping triples, especially a large number of overlapping triples existing in patent texts. A Patent Entity and Relation Extraction model based on Context query and Axial attention is proposed, named PERE-CA. As for entity recognition, the text segment is regarded as candidate entity span and entity types are acquired by span classification. Subsequently, the semantic context related to an entity pair is calculated by a context query method. And the semantic context is integrated into entity pair representation. For relation extraction, axial attention is implemented to get the implicit semantic information among overlapping entity pairs. And then, the model outputs all valid entity-relation triples. Experimental results on the patent dataset TFH-2020 and the public dataset SciERC demonstrate that the implementation of context query and axial attention can effectively improve extraction performance.

Testing the role of temporal coherence on speech intelligibility with noise and single-talker maskers.

Temporal coherence, where sounds with aligned timing patterns are perceived as a single source, is considered an essential cue in auditory scene analysis. However, its effects have been studied primarily with simple repeating tones, rather than speech. This study investigated the role of temporal coherence in speech by introducing across-frequency asynchronies. The effect of asynchrony on the intelligibility of target sentences was tested in the presence of background speech-shaped noise or a single-talker interferer. Our hypothesis was that disrupting temporal coherence should not only reduce intelligibility but also impair listeners' ability to segregate the target speech from an interfering talker, leading to greater degradation for speech-in-speech than speech-in-noise tasks. Stimuli were filtered into eight frequency bands, which were then desynchronized with delays of 0-120 ms. As expected, intelligibility declined as asynchrony increased. However, the decline was similar for both noise and single-talker maskers. Primarily target, rather than masker, asynchrony affected performance for both natural (forward) and reversed-speech maskers, and for target sentences with low and high semantic context. The results suggest that temporal coherence may not be as critical a cue for speech segregation as it is for the non-speech stimuli traditionally used in studies of auditory scene analysis.

Vocabulary mapping for archaeological infrastructure

This article reports and reflects on vocabulary mapping techniques, tools and experience from the ARIADNE European archaeological infrastructure projects, where the widely differing terminology of subject indexing in the different partner languages posed significant challenges for effective data integration. The Getty Art & Architecture Thesaurus is employed as a central spine vocabulary for partners to map their native vocabularies and term lists – a hub structure enables a multilingual search capability via vocabulary mapping. Mappings are expressed via SKOS mapping relationships and output as structured JSON for use in the overall data aggregation process and in the ARIADNE portal. The approach followed offers some automatic support for final intellectual judgement. The method can be characterised as providing lexical support in an interactive tool that aims to intuitively visualise semantic context. The experience of partners in producing the vocabulary mappings is discussed in light of previous work in this area. Reflections on lessons learned both for the immediate project and for vocabulary mapping in general contribute to the conclusions. Future search functionality could take account of available vocabulary mappings via a range of search options, such as query expansion including compound mappings and mapping types. Further work on mapping guidelines and metadata is recommended.

GASCOM: Graph-based Attentive Semantic Context Modeling for Online Conversation Understanding

Online conversation understanding is an important yet challenging NLP problem which has many useful applications (e.g., hate speech detection). However, online conversations typically unfold over a series of posts and replies to those posts, forming a tree structure within which individual posts may refer to semantic context from elsewhere in the tree. Such semantic cross-referencing makes it difficult to understand a single post by itself; yet considering the entire conversation tree is not only difficult to scale but can also be misleading as a single conversation may have several distinct threads or points, not all of which are relevant to the post being considered. In this paper, we propose a Graph-based Attentive Semantic COntext Modeling (GASCOM) framework for online conversation understanding. Specifically, we design two novel algorithms that utilize both the graph structure of the online conversation as well as the semantic information from individual posts for retrieving relevant context nodes from the whole conversation. We further design a token-level multi-head graph attention mechanism to pay different attentions to different tokens from different selected context utterances for fine-grained conversation context modelling. Using this semantic conversational context, we re-examine two well-studied problems: polarity prediction and hate speech detection. Our proposed framework significantly outperforms state-of-the-art methods on both tasks, improving macro-F1 scores by 4.5% for polarity prediction and by 5% for hate speech detection. The GASCOM context weights also enhance interpretability.

The Phenomenon of Collective Memory in the Semantic Contexts of Post-Modernity

The article is devoted to the study of the phenomenon of collective memory in the value contexts of post-modernity. During the 20th century, the culture of memory is revealed through the individual-collective polarity, and in the postmodern era attention is focused on the boundary between them, on the culture of memory in the dimension of the modern media, on the contexts of the global information war. While individual memory loses touch with the past in the dimension of simulated identity, collective memory is usually associated with tradition as a reservoir of memory of the past. Collective memory in the age of modern media is in certain danger of targeted negative external influence, falsification, and inflation. The deepest cultural fears of the 20th century are the deformation or loss of memory, as well as the fear of memory substitution. The main value is linking memory with authenticity in the reproduction of the basic narrative in the cultural practices of today, in which the individual intersects with the collective. That is why the article pays special attention to the border between individual and collective memory, the culture of recall in communicative projects, and the reflection of moral dilemmas in different models of historical memory, the confrontation of different memories.

Hierarchical Event-RGB Interaction Network for single-eye expression recognition

The Single-eye Expression Recognition task stands as a crucial vision task, aimed at decoding human emotional states through careful examination of the eye region. Nevertheless, traditional cameras face challenges in detecting and capturing relevant biological information, especially under demanding lighting conditions such as dim environments, high exposure scenarios, or when other radiation sources are present. In this regard, we use a new type of sensor data that can resist extreme lighting conditions, namely event camera data, to improve the performance of single-eye expression recognition. To this end, we propose a novel Hierarchical Event-RGB Interaction Network (HI-Net), to fully integrate RGB and event data to overcome the extreme lighting challenges faced by the single-eye expression recognition task. The HI-Net contains two novel designs: Event-RGB Semantic Interaction Mechanism (ER-SIM) and Hierarchical Semantics Modeling (HSM) Scheme. The former aims to achieve interaction between Event and RGB modality semantics, while the latter aims to obtain high-quality modality semantic representations. In the ER-SIM, we employ an effective cross-attention mechanism to facilitate information fusion, to adaptively integrate and complement multi-scale Event and RGB semantics to cope with extreme lighting conditions. In HSM Scheme, we first explore multi-scale contextual semantics for the event modality and the RGB modality respectively. Then, we perform a semantics interaction strategy for these multi-scale contextual semantics, to enhance each modality's semantic representation. Extensive experiments demonstrate that our HI-Net significantly outperforms many state-of-the-art methods on the single-eye expression recognition task, especially under degraded lighting conditions.

DERCo: A Dataset for Human Behaviour in Reading Comprehension Using EEG

This paper introduces the DERCo (Dublin EEG-based Reading Experiment Corpus), a language resource combining electroencephalography (EEG) and next-word prediction data obtained from participants reading narrative texts. The dataset comprises behavioral data collected from 500 participants recruited through the Amazon Mechanical Turk online crowd-sourcing platform, along with EEG recordings from 22 healthy adult native English speakers. The online experiment was designed to examine the context-based word prediction by a large sample of participants, while the EEG-based experiment was developed to extend the validation of behavioral next-word predictability. Online participants were instructed to predict upcoming words and complete entire stories. Cloze probabilities were then calculated for each word so that this predictability measure could be used to support various analyses pertaining to semantic context effects in the EEG recordings. EEG-based analyses revealed significant differences between high and low predictable words, demonstrating one important type of potential analysis that necessitates close integration of these two datasets. This material is a valuable resource for researchers in neurolinguistics due to the word-level EEG recordings in context.

Chinese Named Entity Recognition Based on Multi-Level Representation Learning

Named Entity Recognition (NER) is a crucial component of Natural Language Processing (NLP). When dealing with the high diversity and complexity of the Chinese language, existing Chinese NER models face challenges in addressing word sense ambiguity, capturing long-range dependencies, and maintaining robustness, which hinders the accuracy of entity recognition. To this end, a Chinese NER model based on multi-level representation learning is proposed. The model leverages a pre-trained word-based embedding to capture contextual information. A linear layer adjusts dimensions to fit an Extended Long Short-Term Memory (XLSTM) network, enabling the capture of long-range dependencies and contextual information, and providing deeper representations. An adaptive multi-head attention mechanism is proposed to enhance the ability to capture global dependencies and comprehend deep semantic context. Additionally, GlobalPointer with rotational position encoding integrates global information for entity category prediction. Projected Gradient Descent (PGD) is incorporated, introducing perturbations in the embedding layer of the pre-trained model to enhance stability in noisy environments. The proposed model achieves F1-scores of 96.89%, 74.89%, 72.19%, and 80.96% on the Resume, Weibo, CMeEE, and CLUENER2020 datasets, respectively, demonstrating improvements over baseline and comparison models.

Semantic Context Effects in Picture and Sound Naming: Evidence from Event-related Potentials and Pupillometric Data.

When a picture is repeatedly named in the context of semantically related pictures, (homogeneous context) responses are slower than when the picture is repeatedly named in the context of unrelated pictures (heterogeneous context). This semantic interference effect in blocked-cyclic naming plays an important role in devising theories of word production. Wöhner, Mädebach, and Jescheniak [2021; Wöhner, S., Mädebach, A., & Jescheniak, J. D. Naming pictures and sounds: Stimulus type affects semantic context effects. Journal of Experimental Psychology: Human Perception and Performance, 47, 716-730, 2021] have shown that the effect is substantially larger when participants name environmental sounds than when they name pictures. We investigated possible reasons for this difference, using EEG and pupillometry. The behavioral data replicated Wöhner and colleagues. ERPs were more positive in the homogeneous compared with the heterogeneous context over central electrode locations between 140-180 msec and 250-350 msec for picture naming and between 250 and 350 msec for sound naming, presumably reflecting semantic interference during semantic and lexical processing. The later component was of similar size for pictures and sounds. ERPs were more negative in the homogeneous compared with the heterogeneous context over frontal electrode locations between 400 and 600 msec only for sounds. The pupillometric data showed a stronger pupil dilation in the homogeneous compared with the heterogeneous context only for sounds. The amplitudes of the late ERP negativity and pupil dilation predicted naming latencies for sounds in the homogeneous context. The latency of the effects indicates that the difference in semantic interference between picture and sound naming arises at later, presumably postlexical processing stages closer to articulation. We suggest that the processing of the auditory stimuli interferes with phonological response preparation and self-monitoring, leading to enhanced semantic interference.

Using query semantic and feature transfer fusion to enhance cardinality estimating of property graph queries

With the increasing complexity and diversity of query tasks, cardinality estimation has become one of the most challenging problems in query optimization. In this study, we propose an efficient and accurate cardinality estimation method to address the cardinality estimation problem in property graph queries, particularly in response to the current research gap regarding the neglect of contextual semantic features. We first propose formal representations of the property graph query and define its cardinality estimation problem. Then, through the query featurization, we transform the query into a vector representation that can be learned by the estimation model, and enrich the feature vector representation by the context semantic information of the query. We finally propose an estimation model for property graph queries, specifically introducing a feature information transfer module to dynamically control the information flow meanwhile achieving the model’s feature fusion and inference. Experimental results on three datasets show that the estimation model can accurately and efficiently estimate the cardinality of property graph queries, the mean Q_error and RMSE are reduced by about 30% and 25% than the state-of-art estimation models. The context semantics features of queries can improve the model’s estimation accuracy, the mean Q_error result is reduced by about 20% and the RMSE result is about 5%.

Revisiting Conversation Discourse for Dialogue Disentanglement

Dialogue disentanglement aims to detach the chronologically ordered utterances into several independent sessions. Conversation utterances are essentially organized and described by the underlying discourse, and thus dialogue disentanglement requires the full understanding and harnessing of the intrinsic discourse attribute. In this paper, we propose enhancing dialogue disentanglement by taking full advantage of the dialogue discourse characteristics. First of all, in feature encoding stage , we construct the heterogeneous graph representations to model the various dialogue-specific discourse structural features, including the static speaker-role structures (i.e., speaker-utterance and speaker-mentioning structure) and the dynamic contextual structures (i.e., the utterance-distance and partial-replying structure). We then develop a structure-aware framework to integrate the rich structural features for better modeling the conversational semantic context. Second, in model learning stage , we perform optimization with a hierarchical ranking loss mechanism, which groups dialogue utterances into different discourse levels and carries training covering pair-wise and session-wise levels hierarchically. Third, in inference stage , we devise an easy-first decoding algorithm, which performs utterance pairing under the easy-to-hard manner with a global context, breaking the constraint of traditional sequential decoding order. On two benchmark datasets, our overall system achieves new state-of-the-art performances on all evaluations. In-depth analyses further demonstrate the efficacy of each proposed idea and also reveal how our methods help advance the task. Our work has great potential to facilitate broader multi-party multi-thread dialogue applications.

Weakly‐supervised structural component segmentation via scribble annotations

AbstractSegmentation of structural components in infrastructure inspection images is crucial for automated and accurate condition assessment. While deep neural networks hold great potential for this task, existing methods typically require fully annotated ground truth masks, which are time‐consuming and labor‐intensive to create. This paper introduces Scribble‐supervised Structural Component Segmentation Network (ScribCompNet), the first weakly‐supervised method requiring only scribble annotations for multiclass structural component segmentation. ScribCompNet features a dual‐branch architecture with higher‐resolution refinement to enhance fine detail detection. It extends supervision from labeled to unlabeled pixels through a combined objective function, incorporating scribble annotation, dynamic pseudo label, semantic context enhancement, and scale‐adaptive harmony losses. Experimental results show that ScribCompNet outperforms other scribble‐supervised methods and most fully‐supervised counterparts, achieving 90.19% mean intersection over union (mIoU) with an 80% reduction in labeling time. Further evaluations confirm the effectiveness of the novel designs and robust performance, even with lower‐quality scribble annotations.

Transition Words and Phrases: Logical Fallacy in Saudi Premedical English as a Foreign Language Learners’ Written English

This study investigates the use of transition words and phrases in the writing samples of premedical EFL learners enrolled in a preparatory English course at a university in Saudi Arabia. The study employed an empirical research design and mixed-methods research methodology to investigate the factors behind learners’ perplexity about the semantic contexts for using transition words in written English. Thirty male premedical EFL learners with B1 proficiency levels participated as subjects in the study. Learners’ comprehension of the context of the use of transition words was checked using tests. The test responses were cross-checked through a survey questionnaire. The results show that, in general, these learners are perplexed about the exact semantic connotations of transition words and the complexity in the transition of ideas from one sentence or paragraph to another. This may at times result in a loss of meaning, or a mismatch in the transition word and the context sentence the word is used in. The study’s findings suggest that Saudi pre-university EFL learners use transition words and phrases incorrectly or unnecessarily, and therefore, need intensive training in the use of transition words focused on semantic contexts to enhance their writing skills.

Exploring multi-granularity contextual semantics for fully inductive knowledge graph completion

Fully inductive knowledge graph completion (KGC) aims to predict triplets involving both unseen entities and relations. Recent several approaches transform paths between entities into descriptions and modeling semantic correlations between paths using pre-trained language models (PLMs), have emerged as a promising solution for fully inductive reasoning. However, these methods often adopt a simplistic concatenation strategy for path-to-sentence transformation, which impedes PLMs’ ability to capture subtle nuances in context, resulting in sub-optimal path context embeddings. Furthermore, they ignore the high-order semantics underlying the complete context, which can provide richer information for inductive reasoning. To address these issues, we propose a Multi-Granularity Contextual Semantic (MGCS) modeling framework, utilizing a Path Modeling Network (PMN) and a Subgraph Modeling Network (SMN) to extract two granularity levels of contextual semantics from single paths and complete subgraphs, for fully inductive KGC. The PMN extracts paths between head and tail entities and employs reasoning patterns from similar cases to filter out unreliable paths. Then two innovative path conversion strategies are designed to significantly enhance the pre-trained language model’s understanding of specific path contexts. The SMN employs a neighbor interactive graph neural network to extract high-order semantics from the complete subgraph context with a concept-enhanced relation encoding, and optimizes it through a contrastive learning method. Finally, the confidence of the triples is evaluated from the perspective of global complete context by comparing the semantics between the subgraphs surrounding the target triplet and the subgraphs surrounding similar cases. Experimental results on benchmark datasets demonstrate the effectiveness of MGCS.

M2Tames: Interaction and Semantic Context Enhanced Pedestrian Trajectory Prediction

Autonomous driving pays considerable attention to pedestrian trajectory prediction as a crucial task. Constructing effective pedestrian trajectory prediction models depends heavily on utilizing the motion characteristics of pedestrians, along with their interactions among themselves and between themselves and their environment. However, traditional trajectory prediction models often fall short of capturing complex real-world scenarios. To address these challenges, this paper proposes an enhanced pedestrian trajectory prediction model, M2Tames, which incorporates comprehensive motion, interaction, and semantic context factors. M2Tames provides an interaction module (IM), which consists of an improved multi-head mask temporal attention mechanism (M2Tea) and an Interaction Inference Module (I2). M2Tea thoroughly characterizes the historical trajectories and potential interactions, while I2 determines the precise interaction types. Then, IM adaptively aggregates useful neighbor features to generate a more accurate interactive feature map and feeds it into the final layer of the U-Net encoder to fuse with the encoder’s output. Furthermore, by adopting the U-Net architecture, M2Tames can learn and interpret scene semantic information, enhancing its understanding of the spatial relationships between pedestrians and their surroundings. These innovations improve the accuracy and adaptability of the model for predicting pedestrian trajectories. Finally, M2Tames is evaluated on the ETH/UCY and SDD datasets for short- and long-term settings, respectively. The results demonstrate that M2Tames outperforms the state-of-the-art model MSRL by 2.49% (ADE) and 8.77% (FDE) in the short-term setting and surpasses the optimum Y-Net by 6.89% (ADE) and 1.12% (FDE) in the long-term prediction. Excellent performance is also shown on the ETH/UCY datasets.

The Most Beautiful Names of Allah “Ghafir, Ghaffar, and Ghafoor” in the Holy Qur’an (Morphological and Semantic Study)

Morphological forms are used to refer to the root of a word and its material with which its letters are built, and to its functions, derivations, and morphological structures that characterize it in addition to its semantic and lexical functions. The Arabic language includes many morphological structures with a single root, such as (the Most Merciful and the Most Merciful) and (Hafez and Hafeez). and (Shakour and Shaker) (Ghafara, Ghafer, and Ghafoor). These morphological connotations of the same root, despite the closeness in their meanings, differ in their semantic contexts depending on the root of the word, its structure, and its derivation. Hence, the study of the beautiful names according to the meter (Ghafoor, Ghafir, and Ghafar) came to determine their morphological functions, their linguistic connotations, and the contexts in which they appeared in the Qur’anic text.

A revisit to interactions of stimulus quality and semantic context on N400 in visual word recognition.

Much behavioral research has revealed interactive effects between stimulus quality and semantic priming in visual word recognition, practically in favor of the interactive activation model. However, the limited number of event-related brain potential (ERP) studies have yielded inconsistent results considering this interaction's impact on N400 amplitude. The current ERP study aimed to examine whether the joint effects of stimulus quality and semantic priming were specific to the lexical decision task. We used both behavioral measures and ERP recordings to evaluate the joint effects of stimulus degradation (i.e. highly vs. slightly degraded) and semantic priming (i.e. semantically related vs. unrelated) in a lexical decision task involving visual recognition of Chinese characters. The results showed significant degradation-by-priming interactions on response times and N400 amplitude ( P < 0.05), with larger semantic priming effects on slightly degraded targets. These converging behavioral and electrophysiological findings provide evidence in accordance with the interactive activation models of visual word recognition, in which the early-stage visual processing (i.e. degradation) cascades into the later-stage semantic processing (i.e. priming), thus yielding interactions observed in N400 amplitude.

Taking the Extra Listening Mile: Processing Spoken Semantic Context Is More Effortful for Older Than Young Adults.

Older adults use semantic context to generate predictions in speech processing, compensating for aging-related sensory and cognitive changes. This study aimed to gauge aging-related changes in effort exertion related to context use. The study revisited data from Harel-Arbeli et al. (2023) that used a "visual-world" eye-tracking paradigm. Data on efficiency of context use (response latency and the probability to gaze at the target before hearing it) and effort exertion (pupil dilation) were extracted from a subset of 14 young adults (21 to 27 years old) and 13 older adults (65 to 79 years old). Both age groups showed a similar pattern of context benefits for response latency and target word predictions, however only the older adults group showed overall increased pupil dilation when listening to context sentences. Older adults' efficient use of spoken semantic context appears to come at a cost of increased effort exertion.

CSMDC: Exploring consistently context semantics for multi-view document clustering

Multi-view document clustering, which aims to discover clustering partitions based on multiple document views, has attracted increasing research interest. However, the potential advantages of incorporating context semantics to enhance multi-view document clustering are yet to be fully explored. To address the above limitation, we propose a deep multi-view document clustering model that explores consistent context semantics called CSMDC which consists of three modules. Specifically, a novel view-translator is designed to convert non-contextual document views into contextual views. With its help, all document views can be processed to obtain their semantic representations within the view-translator representation learning module. Then the data-based view consistency self-supervising module is developed to fine-tune the semantic representations of document views by jointly incorporating view-wise representation relevance and consistent clustering assignments. Additionally, the task-based document clustering module is employed to simultaneously improve the view semantic representations and document clustering results. To the best of our knowledge, this is the first study to explicitly apply consistent context semantics under the guidance of data-based and task-based objectives in multi-view document clustering. Comprehensive experimental results demonstrated the effectiveness of the proposed model.

법의 세계화와 한국법의 위상

This article deals with the status of Korean law in the semantic context of the globalization of law. In today’s situation where conflicts between countries are intensifying, questions may be raised about whether it is meaningful to discuss globalization, especially the globalization of law. However, as Kant’s theory of perpetual peace suggests, the world society pursued by globalization could contain the normative ideal of realizing a peaceful human community. Considering this, it is meaningful to handle the globalization of law and the current status of Korean law at this point. In those contexts, this article examines the globalization of law and the status of Korean law. However, since the topic itself is very broad, discussion may be limited in this article. This article deals with globalization in three meanings: unification, pluralization, and conflict. In connection with this, the globalization of law is also examined in terms of unification, pluralization, and conflict of law. Based upon this, the author deals with the status of Korean law. To this end, this article applies a three-stage model to the developing process of Korean law. According to that working, Korean law is currently in a third-stage of its developing process. At this stage, Korean law is not only developing independently, but in some cases is also receiving global attention. However, this article raises questions about whether the independent legal system we have achieved can really become one of the global standards. For that reason, this article mentions the limit of our country’s scale. In addition, this article argues that the current crisis Korean legal science is facing could be a significant obstacle to the development of Korean law.