Explore the vast range of titles available.

Models that represent meaning as high-dimensional numerical vectors—such as latent semantic analysis (LSA), hyperspace analogue to language (HAL), bound encoding of the aggregate language environment (BEAGLE), topic models, global vectors (GloVe), and word2vec—have been introduced as extremely powerful machine-learning proxies for human semantic representations and have seen an explosive rise in popularity over the past 2 decades. However, despite their considerable advancements and spread in the cognitive sciences, one can observe problems associated with the adequate presentation and understanding of some of their features. Indeed, when these models are examined from a cognitive perspective, a number of unfounded arguments tend to appear in the psychological literature. In this article, we review the most common of these arguments and discuss (a) what exactly these models represent at the implementational level and their plausibility as a cognitive theory, (b) how they deal with various aspects of meaning such as polysemy or compositionality, and (c) how they relate to the debate on embodied and grounded cognition. We identify common misconceptions that arise as a result of incomplete descriptions, outdated arguments, and unclear distinctions between theory and implementation of the models. We clarify and amend these points to provide a theoretical basis for future research and discussions on vector models of semantic representation.

Adult semantic memory has been traditionally conceptualized as a relatively static memory system that consists of knowledge about the world, concepts, and symbols. Considerable work in the past few decades has challenged this static view of semantic memory, and instead proposed a more fluid and flexible system that is sensitive to context, task demands, and perceptual and sensorimotor information from the environment. This paper (1) reviews traditional and modern computational models of semantic memory, within the umbrella of network (free association-based), feature (property generation norms-based), and distributional semantic (natural language corpora-based) models, (2) discusses the contribution of these models to important debates in the literature regarding knowledge representation (localist vs. distributed representations) and learning (error-free/Hebbian learning vs. error-driven/predictive learning), and (3) evaluates how modern computational models (neural network, retrieval-based, and topic models) are revisiting the traditional “static” conceptualization of semantic memory and tackling important challenges in semantic modeling such as addressing temporal, contextual, and attentional influences, as well as incorporating grounding and compositionality into semantic representations. The review also identifies new challenges regarding the abundance and availability of data, the generalization of semantic models to other languages, and the role of social interaction and collaboration in language learning and development. The concluding section advocates the need for integrating representational accounts of semantic memory with process-based accounts of cognitive behavior, as well as the need for explicit comparisons of computational models to human baselines in semantic tasks to adequately assess their psychological plausibility as models of human semantic memory.

This paper is an extended description of SemEval-2014 Task 1, the task on the evaluation of Compositional Distributional Semantics Models on full sentences. Systems participating in the task were presented with pairs of sentences and were evaluated on their ability to predict human judgments on (1) semantic relatedness and (2) entailment. Training and testing data were subsets of the SICK (Sentences Involving Compositional Knowledge) data set. SICK was developed with the aim of providing a proper benchmark to evaluate compositional semantic systems, though task participation was open to systems based on any approach. Taking advantage of the SemEval experience, in this paper we analyze the SICK data set, in order to evaluate the extent to which it meets its design goal and to shed light on the linguistic phenomena that are still challenging for state-of-the-art computational semantic systems. Qualitative and quantitative error analyses show that many systems are quite sensitive to changes in the proportion of sentence pair types, and degrade in the presence of additional lexico-syntactic complexities which do not affect human judgements. More compositional systems seem to perform better when the task proportions are changed, but the effect needs further confirmation.

With the advances of technology, the banking industry faces the challenge of processing large-scale, heterogeneous human resource data. Traditional methods have difficulties in providing efficient and accurate analysis and prediction. This paper proposes an optimized human resource allocation algorithm based on deep latent Semantic Model (DLSM), which improves the accuracy and efficiency of data analysis by integrating deep neural network (DNN) and transfer learning technology. The experimental results show that the DLSM model performs well in text classification and information retrieval tasks, with the accuracy, accuracy, recall and F1 scores improving by 7.5%, 5.5%, 6.0% and 5.8%, respectively. This study confirms the excellent performance of DLSM model in HR data processing, provides an efficient and scientifically based solution for recruitment optimization in the banking industry, and enhances the competitiveness of enterprises.

Many changes in our digital corpus have been brought about by the interplay between rapid advances in digital communication and the current environment characterized by pandemics, political polarization, and social unrest. One such change is the pace with which new words enter the mass vocabulary and the frequency at which meanings, perceptions, and interpretations of existing expressions change. The current state-of-the-art algorithms do not allow for an intuitive and rigorous detection of these changes in word meanings over time. We propose a dynamic graph-theoretic approach to inferring the semantics of words and phrases (“terms”) and detecting temporal shifts. Our approach represents each term as a stochastic time-evolving set of contextual words and is a count-based distributional semantic model in nature. We use local clustering techniques to assess the structural changes in a given word’s contextual words. We demonstrate the efficacy of our method by investigating the changes in the semantics of the phrase “Chinavirus”. We conclude that the term took on a much more pejorative meaning when the White House used the term in the second half of March 2020, although the effect appears to have been temporary. We make both the dataset and the code used to generate this paper’s results available.

Collection and especially analysis of open-ended survey responses are relatively rare in the discipline and when conducted are almost exclusively done through human coding. We present an alternative, semiautomated approach, the structural topic model (STM) (Roberts, Stewart, and Airoldi 2013; Roberts et al. 2013), that draws on recent developments in machine learning based analysis of textual data. A crucial contribution of the method is that it incorporates information about the document, such as the authors gender, political affiliation, and treatment assignment (if an experimental study). This article focuses on how the STM is helpful for survey researchers and experimentalists. The STM makes analyzing open-ended responses easier, more revealing, and capable of being used to estimate treatment effects. We illustrate these innovations with analysis of text from surveys and experiments.

PurposeThis paper reviews the state-of-the art research in life cycle assessment (LCA) applied to buildings. It focuses on current research trends, and elaborates on gaps and directions for future research.MethodsA systematic literature review was conducted to identify current research and applications of LCA in buildings. The proposed review methodology includes (i) identifying recent authoritative research publications using established search engines, (ii) screening and retaining relevant publications, and (iii) extracting relevant LCA applications for buildings and analyzing their underpinning research. Subsequently, several research gaps and limitations were identified, which have informed our proposed future research directions.Results and discussionsThis paper argues that humans can attenuate and positively control the impact of their buildings on the environment, and as such mitigate the effects of climate change. This can be achieved by a new generation of LCA methods and tools that are model based and continuously learn from real-time data, while informing effective operation and management strategies of buildings and districts. Therefore, the consideration of the time dimension in product system modeling is becoming essential to understand the resulting pollutant emissions and resource consumption. This time dimension is currently missing in life cycle inventory databases. A further combination of life cycle impact assessment (LCIA) models using time-dependent characterization factors can lead to more comprehensive and reliable LCA results.Conclusions and recommendationsThis paper promotes the concept of semantic-based dynamic (real-time) LCA, which addresses temporal and spatial variations in the local built and environmental ecosystem, and thus more effectively promotes a “cradle-to-grave-to-reincarnation” environmental sustainability capability. Furthermore, it is critical to leverage digital building resources (e.g., connected objects, semantic models, and artificial intelligence) to deliver accurate and reliable environmental assessments.

It is now part and parcel of the official philosophical wisdom that models are essential to the acquisition and organisation of scientific knowledge. It is also generally accepted that most models represent their target systems in one way or another. But what does it mean for a model to represent its target system? I begin by introducing three conundrums that a theory of scientific representation has to come to terms with and then address the question of whether the semantic view of theories, which is the currently most widely accepted account of theories and models, provides us with adequate answers to these questions. After having argued in some detail that it does not, I conclude by pointing out in what direction a tenable account of scientific representation might be sought.

Human memory is reconstructive and thus fundamentally imperfect. One of its critical flaws is false recall—the erroneous recollection of unstudied items. Despite its significant implications, false recall poses a challenge for existing computational models of serial recall, which struggle to provide item-specific predictions. Across six experiments, each involving 100 young adults, we address this issue using the Embedded Computational Framework of Memory (eCFM) that integrates existing accounts of semantic and episodic memory. While the framework provides a comprehensive account of memory processing, its innovation lies in the inclusion of a comprehensive lexicon of word knowledge derived from distributional semantic models. By integrating a lexicon that captures orthographic, phonological, and semantic relationships within an episodic memory model, the eCFM successfully accounts for patterns of veridical serial recall (e.g., proportion correct, intralist errors, omissions) while also capturing false recall (e.g., extralist errors including both critical lures and non-critical lures). We demonstrate the model’s capabilities through simulations applied to six experiments, with lists of words (Experiments 1 A, 1 B, 2 A, and 2 B) and non-words (Experiments 3 A and 3 B) that are either related or unrelated semantically (Experiments 1 A and 1 B), phonologically (Experiments 2 A and 2 B), or orthographically (Experiments 3 A and 3 B). This approach fills a computational gap in modelling serial recall and underscores the importance of integrating traditionally separate areas of semantic and episodic memory to provide more precise predictions and holistic memory models.

I provide a truthmaker semantics for Angell's system of analytic implication and establish completeness.