Semantics - Interfaces Claudia Maienborn, Klaus Heusinger, Paul Portner / Claudia Maienborn, Klaus Heusinger, Paul Portner
2019, 2019-02-19
eBook
Explore the exciting research where semantics meets morphology, syntax and pragmatics. In this book, leading researchers use in-depth articles to explain a wide range of topics at these interfaces, ...including the semantics of intonation, inflection, compounding, argument structure, type shifting, compositionality, implicature, context dependence, deixis and presupposition. Now in paperback for the first time since its original publication, the highly cited material in this book is an ideal starting point for anyone interested in semantics where it crosses over with other dimensions of grammar.
Now available in paperback for the first time since its original publication, the material in this book provides a broad, accessible guide to semantic typology, crosslinguistic semantics and ...diachronic semantics. Coming from a world-leading team of authors, the book also deals with the concept of meaning in psycholinguistics and neurolinguistics, and the understanding of semantics in computer science. It is packed with highly cited, expert guidance on the key topics in the field, making it a bookshelf essential for linguists, cognitive scientists, philosophers, and computer scientists working on natural language.
Abstract
Psychological constructs, such as emotions, thoughts, and attitudes are often measured by asking individuals to reply to questions using closed-ended numerical rating scales. However, when ...asking people about their state of mind in a natural context ("How are you?"), we receive open-ended answers using words ("Fine and happy!") and not closed-ended answers using numbers ("7") or categories ("A lot"). Nevertheless, to date it has been difficult to objectively quantify responses to open-ended questions. We develop an approach using open-ended questions in which the responses are analyzed using natural language processing (Latent Semantic Analyses). This approach of using open-ended, semantic questions is compared with traditional rating scales in nine studies (N = 92-854), including two different study paradigms. The first paradigm requires participants to describe psychological aspects of external stimuli (facial expressions) and the second paradigm involves asking participants to report their subjective well-being and mental health problems. The results demonstrate that the approach using semantic questions yields good statistical properties with competitive, or higher, validity and reliability compared with corresponding numerical rating scales. As these semantic measures are based on natural language and measure, differentiate, and describe psychological constructs, they have the potential of complementing and extending traditional rating scales.
Translational Abstract
We develop tools called semantic measures to statistically measure, differentiate and describe subjective psychological states. In this new method, natural language processing is used for objectively quantifying words from open-ended questions, rather than the closed-ended numerical rating scales traditionally used today. Importantly, the results suggest that these semantic measures have competitive, or higher, validity and reliability compared with traditional rating scales. Using semantic measures also brings along advantages, including an empirical description/definition of the measured construct and better differentiation between similar constructs. This method encompasses a great potential in terms of improving the way we quantify and understand individuals' states of mind. Semantic measures may end up becoming a widespread alternative applied in scientific research (e.g., psychology and medicine) as well as in various professional contexts (e.g., political polls and job recruitment).
Agricultural robots rely on semantic segmentation for distinguishing between crops and weeds to perform selective treatments and increase yield and crop health while reducing the amount of chemicals ...used. Deep‐learning approaches have recently achieved both excellent classification performance and real‐time execution. However, these techniques also rely on a large amount of training data, requiring a substantial labeling effort, both of which are scarce in precision agriculture. Additional design efforts are required to achieve commercially viable performance levels under varying environmental conditions and crop growth stages. In this paper, we explore the role of knowledge transfer between deep‐learning‐based classifiers for different crop types, with the goal of reducing the retraining time and labeling efforts required for a new crop. We examine the classification performance on three datasets with different crop types and containing a variety of weeds and compare the performance and retraining efforts required when using data labeled at pixel level with partially labeled data obtained through a less time‐consuming procedure of annotating the segmentation output. We show that transfer learning between different crop types is possible and reduces training times for up to 80%. Furthermore, we show that even when the data used for retraining are imperfectly annotated, the classification performance is within 2% of that of networks trained with laboriously annotated pixel‐precision data.
Domain invariance and discrimination of learned features as two crucial factors affect the performance of unsupervised domain adaptation (UDA) person re-identification (Re-ID). Person attributes ...(such as "backpack", "boots", "handbag", etc) remaining unchanged across multiple domains have been used as mid-level visual-semantic information in UDA person Re-ID. As two main challenges, both misalignment of attribute-related regions across multiple images and domain shift between source and target domains affect the learning of domain-invariant features (DIF). To address the above two challenges, this article proposes to take advantage of the stability of person attributes and the complementarity of person attributes and the corresponding low-level visual features to guide the learning of discriminative DIF. Specifically, the proposed solution contains the generation of latent attribute-correlated visual features (GLAVF), DIF learning under the guidance of person attributes, and the alignment of person attributes corresponding to the local regions of pedestrian images. Due to the gap between person attributes and visual features, person attributes are first converted into latent attribute-correlated visual features (LAVF) without any specific domain information in GLAVF, and then LAVF are used as the substitutions of person attributes to guide the learning of DIF. To enhance the discrimination of learned features, the proposed solution mainly explores the alignment between person attributes and corresponding local regions, and the alignment of the same person attributes across multiple pedestrian images. A fully connected layer is used to achieve the above two types of alignment in the proposed framework, which reduces the adverse impacts of inference information and ensures the semantic consistency between person attributes and corresponding local regions across multiple pedestrian images. The effectiveness of the proposed solution is confirmed on four existing datasets by comparative experiments.
A Survey on Ethereum Systems Security Chen, Huashan; Pendleton, Marcus; Njilla, Laurent ...
ACM computing surveys,
06/2020, Letnik:
53, Številka:
3
Journal Article
Recenzirano
Odprti dostop
Blockchain technology is believed by many to be a game changer in many application domains. While the first generation of blockchain technology (i.e., Blockchain 1.0) is almost exclusively used for ...cryptocurrency, the second generation (i.e., Blockchain 2.0), as represented by Ethereum, is an open and decentralized platform enabling a new paradigm of computing—Decentralized Applications (DApps) running on top of blockchains. The rich applications and semantics of DApps inevitably introduce many security vulnerabilities, which have no counterparts in pure cryptocurrency systems like Bitcoin. Since Ethereum is a new, yet complex, system, it is imperative to have a systematic and comprehensive understanding on its security from a holistic perspective, which was previously unavailable in the literature. To the best of our knowledge, the present survey, which can also be used as a tutorial, fills this void. We systematize three aspects of Ethereum systems security: vulnerabilities, attacks, and defenses. We draw insights into vulnerability root causes, attack consequences, and defense capabilities, which shed light on future research directions.
The understanding of web images has been a hot research topic in both artificial intelligence and multimedia content analysis domains. The web images are composed of various complex foregrounds and ...backgrounds, which makes the design of an accurate and robust learning algorithm a challenging task. To solve the above significant problem, first, we learn a cross-modality bridging dictionary for the deep and complete understanding of a vast quantity of web images. The proposed algorithm leverages the visual features into the semantic concept probability distribution, which can construct a global semantic description for images while preserving the local geometric structure. To discover and model the occurrence patterns between intra- and inter-categories, multi-task learning is introduced for formulating the objective formulation with Capped-ℓ 1 penalty, which can obtain the optimal solution with a higher probability and outperform the traditional convex function-based methods. Second, we propose a knowledge-based concept transferring algorithm to discover the underlying relations of different categories. This distribution probability transferring among categories can bring the more robust global feature representation, and enable the image semantic representation to generalize better as the scenario becomes larger. Experimental comparisons and performance discussion with classical methods on the ImageNet, Caltech-256, SUN397, and Scene15 datasets show the effectiveness of our proposed method at three traditional image understanding tasks.
Semantic communication has sparked great interest, due to the rising demands of emerging applications on high communication capacity and low latency. The majority of existing semantic communication ...methods are task-oriented, which transmit task-related semantic information via synchronous trained deep learning-based (DL-based) encoders and decoders. However, these methods have limitations in handling multi-task communications. Moreover, the synchronous training paradigm also leads to significant communication overhead in the establishing phase. In this article, we propose an asynchronous multi-task semantic communication method. In the proposed method, the DL-based encoder is trained independently using a contrastive learning method to extract task-independent semantic knowledge. Then, the receiver trains different DL-based decoders to perform various communication tasks based on the pre-trained encoder. Our method enables the accomplishment of multiple communication tasks in a single transmission. Moreover, the asynchronous training paradigm can reduce the communication overhead during the training phase of our system. The experimental results demonstrate that the proposed method achieves state-of-the-art performance in image classification and reconstruction tasks while requiring less than 10% of the training communication time compared to existing semantic communication systems.
While pre-training large-scale video-language models (VLMs) has shown remarkable potential for various downstream video-language tasks, existing VLMs can still suffer from certain commonly seen ...limitations, e.g., coarse-grained cross-modal aligning , under-modeling of temporal dynamics , detached video-language view . In this work, we target enhancing VLMs with a fine-grained structural spatio-temporal alignment learning method (namely Finsta). First of all, we represent the input texts and videos with fine-grained scene graph (SG) structures, both of which are further unified into a holistic SG (HSG) for bridging two modalities. Then, an SG-based framework is built, where the textual SG (TSG) is encoded with a graph Transformer, while the video dynamic SG (DSG) and the HSG are modeled with a novel recurrent graph Transformer for spatial and temporal feature propagation. A spatial-temporal Gaussian differential graph Transformer is further devised to strengthen the sense of the changes in objects across spatial and temporal dimensions. Next, based on the fine-grained structural features of TSG and DSG, we perform object-centered spatial alignment and predicate-centered temporal alignment respectively, enhancing the video-language grounding in both the spatiality and temporality. We design our method as a plug&play system, which can be integrated into existing well-trained VLMs for further representation augmentation, without training from scratch or relying on SG annotations in downstream applications. On 6 representative VL modeling tasks over 12 datasets in both standard and long-form video scenarios, Finsta consistently improves the existing 13 strong-performing VLMs persistently, and refreshes the current state-of-the-art end task performance significantly in both the fine-tuning and zero-shot settings.