Sentence Length Research Articles

A Pre-Silicon Detection Based on Deep Learning Model for Hardware Trojans

Several hardware Trojan (HT) detection techniques are available today to ensure the security of hardware systems. However, the existing pre-silicon HT detection techniques have problems such as difficulties in capturing HT path features and poor applicability. To address these challenges, this paper proposes a gate-level HT detection scheme based on a deep learning model. We parse the circuit gate-level netlist and develop an algorithm to extract circuit path sentences based on the signal propagation rule. Path sentences consisting of gate names are extracted as experimental datasets. We apply the theory of natural language processing (NLP) to the task of HT detection and use three neural networks to filter the length of path sentences. Then, based on the deep learning model text convolutional neural network (TextCNN), we propose PS-TextCNN for HT detection. Our approach is verified on seven benchmark circuits of the RS232-series and eight benchmark circuits of the s-series. We achieve an average true positive rate (TPR) of 88.9%. The TPR of the RS232-series reaches a high score of 99.5%. The TPR of the s-series is 79.5%, which is significantly higher than that of the existing gate-level HT detection techniques.

Screening through a broad pool: Towards better diversity for lexically constrained text generation

Lexically constrained text generation (CTG) is to generate text that contains given constrained keywords. However, the text diversity of existing models is still unsatisfactory. In this paper, we propose a lightweight dynamic refinement strategy that aims at increasing the randomness of inference to improve generation richness and diversity while maintaining a high level of fluidity and integrity. Our basic idea is to enlarge the number and length of candidate sentences in each iteration, and choose the best for subsequent refinement. On the one hand, different from previous works, which carefully insert one token between two words per action, we insert an uncertain number of tokens following a well-designed distribution. To ensure high-quality decoding, the insertion number increases as more words are generated. On the other hand, we randomly mask an increasing number of generated words to force Pre-trained Language Models (PLMs) to examine the whole sentence via reconstruction. We have conducted extensive experiments and designed four dimensions for human evaluation. Compared with important baseline (CBART (He, 2021)), our method improves the 1.3% (B-2), 0.1% (B-4), 0.016 (N-2), 0.016 (N-4), 5.7% (M), 1.9% (SB-4), 0.6% (D-2), 0.5% (D-4) on One-Billion-Word dataset (Chelba et al., 2014) and 1.6% (B-2), 0.1% (B-4), 0.121 (N-2), 0.120 (N-4), 0.0% (M), 6.7% (SB-4), 2.7% (D-2), 3.8% (D-4) on Yelp dataset (Cho et al., 2018). The results demonstrate that our method is more diverse and plausible.

The Relationship Between Sentence Length, Time Served, and State Prison Population Levels

The Relationship Between Sentence Length, Time Served, and State Prison Population Levels

The development of sentence and clause lengths in Czech L2 texts

The development of sentence and clause lengths in Czech L2 texts

Examining Automatic Generated Language Features of Chinese Spontaneous Speech for Early Detection of Cognitive Decline

AbstractBackgroundConnected speech is sensitive on detecting cognitive decline in early Alzheimer disease. In this study, we apply artificial intelligence to develop an automatic assessment for analyzing speech data.Method79 samples of picture description speech data were collected. All participants were native Chinese speakers including 31 normal controls (59‐88 yrs) and 49 patients (amnestic mild cognitive impairment and early Alzheimer’s disease) (58‐88 yrs). We extracted 16 linguistic features from the manually transcribed text. These linguistic features were generated by well‐trained linguists or automatically processed by the machine. We also trained decision tree models with those two sets of linguistic features. Seventy percent of the data was used for training and the remainder was used for testing. We also applied a cross‐validation method to avoid overfitting.ResultTotal words, unique words, and content words generated from linguists or machines were highly correlated (about r = 0.99, p < .001). However, the correlations between verb ratio, mean length of sentences, and filler ratio were relatively low (about r = 0.75, p < .001). With manually corrected features, the model could achieve 91.67% accuracy. Among them, the pronoun ratio and MLU (mean length of utterance) appeared to be equally crucial for model prediction. By contrast, with automatically generated features, the model achieved 83.33% accuracy only. MLU and MLS (mean length of sentences) were essential features for prediction.ConclusionAutomatic assessment could also achieve a good accuracy rate compared to humans (83.33% v.s. 91.67%). Some linguistic features such as fillers or sentences were still highly dependent on the expert’s judgment. Interestingly, MLU was critical in the prediction model of automatic or experts.

Strahler number of natural language sentences in comparison with random trees

The Strahler number was originally proposed to characterize the complexity of river bifurcation and has found various applications. This article proposes a computation of the Strahler number’s upper and lower limits for natural language sentence tree structures. Through empirical measurements across grammatically annotated data, the Strahler number of natural language sentences is shown to be almost 3 or 4, similar to the case of river bifurcation as reported by Strahler (1957 Eos Trans. Am. Geophys. Union 38 913–20). Based on the theory behind this number, we show that there is a kind of lower limit on the amount of memory required to process sentences. We consider the Strahler number to provide reasoning that explains reports showing that the number of required memory areas to process sentences is 3–4 for parsing (Schuler et al 2010 Comput. Linguist. 36 1–30), and reports indicating a psychological ‘magical number’ of 3–5 (Cowan 2001 Behav. Brain Sci. 24 87–114). An analytical and empirical analysis shows that the Strahler number is not constant but grows logarithmically. Therefore, the Strahler number of sentences is derived from the range of sentence lengths. Furthermore, the Strahler number is not different for random trees, which could suggest that its origin is not specific to natural language.

Evaluation of Interpretable Speech Biomarkers for Monitoring Alzheimer’s Disease and Mild Cognitive Impairment Progression

AbstractBackgroundAlzheimer’s disease (AD) is a progressive neurodegenerative disease. Like for other dementias, biomarkers may help characterize distinct aspects of the underlying pathology, predict decline, and monitor disease progression. We extracted a composite array of 24 speech‐based biomarkers using machine learning and signal processing techniques. We then determined which of the given biomarkers was predictive of MCI and AD progression from baseline by conducting a correlation analysis.MethodSpoken responses to a Cookie Theft Picture description task were recorded from 2 subjects with AD, 4 subjects with Mild Cognitive Impairment (MCI) due to AD (biomarker confirmed AD), and 4 subjects with MCI. We automatically extracted acoustic, linguistic, and cognitive biomarkers using speech recognition, acoustic, and language modeling techniques. We later computed Kendall’s tau‐b (tb) correlation between the biomarker values and Montreal Cognitive Assessment (MoCA) scores. Recordings and MoCA scores were collected at baseline, at 6 months after baseline, and at 12 months for a subgroup of the subjects. To perform the correlation analysis, we used scipy.stats.kendalltau library in Python.ResultWith respect to the acoustic biomarkers, a strong negative correlation (tb = ‐0.50) was observed between the MoCA scores and features such as pause time, pause percentage, and pause speech ratio, while a moderate positive correlation (tb = 0.2) was found for rhythm standard deviation. With respect to the linguistic biomarkers a strong positive correlation(tb = 0.50) for the features of corrected type‐token ratio, average sentence length in words, and noun count was reported, while a moderate positive correlation (tb = 0.27) was found for the features of word type count, word token count, and moving average type‐token ratio. The other acoustic, linguistic, and cognitive biomarkers showed a very weak (tb = 0.00 ‐ 0.10) or weak correlation (tb = 0.10 ‐ 0.20).ConclusionAltogether, these results suggest that speech‐based interpretable biomarkers may help clinicians to diagnose AD at earlier stages and monitor disease progression. Our preliminary data suggest that AD patients encounter more problems delivering longer and linguistically elaborated narratives as the disease progresses.

Evaluation of Interpretable Speech Biomarkers for Monitoring Alzheimer’s Disease and Mild Cognitive Impairment Progression

AbstractBackgroundAlzheimer’s disease (AD) is a progressive neurodegenerative disease. Like for other dementias, biomarkers may help characterize distinct aspects of the underlying pathology, predict decline, and monitor disease progression. We extracted a composite array of 24 speech‐based biomarkers using machine learning and signal processing techniques. We then determined which of the given biomarkers was predictive of MCI and AD progression from baseline by conducting a correlation analysis.MethodSpoken responses to a Cookie Theft Picture description task were recorded from 2 subjects with AD, 4 subjects with Mild Cognitive Impairment (MCI) due to AD (biomarker confirmed AD), and 4 subjects with MCI. We automatically extracted acoustic, linguistic, and cognitive biomarkers using speech recognition, acoustic, and language modeling techniques. We later computed Kendall’s tau‐b (τb ) correlation between the biomarker values and Montreal Cognitive Assessment (MoCA) scores. Recordings and MoCA scores were collected at baseline, at 6 months after baseline, and at 12 months for a subgroup of the subjects. To perform the correlation analysis, we used scipy.stats.kendalltau library in Python.ResultWith respect to the acoustic biomarkers, a strong negative correlation (τb= ‐0.50) was observed between the MoCA scores and features such as pause time, pause percentage, and pause speech ratio, while a moderate positive correlation (τb= 0.2) was found for rhythm standard deviation. With respect to the linguistic biomarkers a strong positive correlation(τb= 0.50) for the features of corrected type‐token ratio, average sentence length in words, and noun count was reported, while a moderate positive correlation (τb= 0.27) was found for the features of word type count, word token count, and moving average type‐token ratio. The other acoustic, linguistic, and cognitive biomarkers showed a very weak (τb= 0.00 ‐ 0.10) or weak correlation (τb= 0.10 ‐ 0.20).ConclusionAltogether, these results suggest that speech‐based interpretable biomarkers may help clinicians to diagnose AD at earlier stages and monitor disease progression. Our preliminary data suggest that AD patients encounter more problems delivering longer and linguistically elaborated narratives as the disease progresses.

Retranslated Chinese classical canon Journey to the West: a stylometric comparison between Julia Lovell’s retranslation and Arthur Waley’s translation

Abstract Journey to the West (西游记; Xi You Ji) is one of the best-known classic novels in Chinese literature, and it has been translated into English by various notable translators. This study compares the retranslation of the novel by Julia Lovell published in “Penguin Classics” in 2021 with Arthur Waley’s translation in “Penguin Classics” in 1973. Employing a stylometric approach to compare the styles of the two translations, it uses the corpus tools of word lists, keyword analysis, and function word analysis. The results reveal distinct stylistic differences in the translators’ styles, including lexical density, sentence length, and function words, which point to different translation strategies employed by the two translations of this classic Chinese novel. The book reviews published so far indicate that Lovell’s version has been well received by contemporary Anglophone readers and that the changes in this retranslation may have helped to explain the recanonization of the original classic. This study provides new insights into the understanding of the differences between translation and retranslation, and thus has implications for the fields of translator style studies and stylometry research.

Mandatory minimum sentencing and its effect on sentencing distributions: Evidence from Canada

AbstractWhether judges and prosecutors should be given full discretionary power in sentencing or mandatory minimum sentences be imposed remains a fiercely debated topic. In this paper, we examine the impact of Canada's 2005 introduction of minimum sentences on sexual offences against children and child pornography on the distribution of sentence lengths using administrative data containing the universe of these offences that occurred between 2003 and 2007. We find that the average sentence length for affected crimes at times increased by substantially more than the newly imposed minimum, and effects of the policy appear even in the middle and upper portions of the sentencing distribution. These increases occur immediately following the policy change, signalling that judges and prosecutors quickly change their sentencing behaviour after the implementation of mandatory minimum sentences. These lengthier sentences have significant implications for the estimation of the fiscal costs of minimum sentencing policies.

Probing the cognitive load of consecutive interpreters

Abstract This study employs four purpose-built corpora to assess the frequency of the disfluency marker uh (emm) in Chinese-English consecutive interpreting (CI) renditions as a proxy measure of interpreters’ cognitive load. Based on Plevoets and Defrancq (2016, 2018), the frequencies are compared across four informational load indicators: delivery rate, lexical density, proportion of numbers, and sentence length. The analysis also probes the potential influence of interpreting directionality on disfluencies. Results reveal differential effects of the four informational load indicators on disfluencies and, by extension, interpreters’ cognitive load, while Chinese-to-English CI is associated with an increase in disfluencies compared to English-to-Chinese for interpreters with Chinese as their A language.

Evaluating the performance of Generative Pre-trained Transformer-4 (GPT-4) in standardizing radiology reports.

Radiology reporting is an essential component of clinical diagnosis and decision-making. With the advent of advanced artificial intelligence (AI) models like GPT-4 (Generative Pre-trained Transformer 4), there is growing interest in evaluating their potential for optimizing or generating radiology reports. This study aimed to compare the quality and content of radiologist-generated and GPT-4 AI-generated radiology reports. A comparative study design was employed in the study, where a total of 100 anonymized radiology reports were randomly selected and analyzed. Each report was processed by GPT-4, resulting in the generation of a corresponding AI-generated report. Quantitative and qualitative analysis techniques were utilized to assess similarities and differences between the two sets of reports. The AI-generated reports showed comparable quality to radiologist-generated reports in most categories. Significant differences were observed in clarity (p = 0.027), ease of understanding (p = 0.023), and structure (p = 0.050), favoring the AI-generated reports. AI-generated reports were more concise, with 34.53 fewer words and 174.22 fewer characters on average, but had greater variability in sentence length. Content similarity was high, with an average Cosine Similarity of 0.85, Sequence Matcher Similarity of 0.52, BLEU Score of 0.5008, and BERTScore F1 of 0.8775. The results of this proof-of-concept study suggest that GPT-4 can be a reliable tool for generating standardized radiology reports, offering potential benefits such as improved efficiency, better communication, and simplified data extraction and analysis. However, limitations and ethical implications must be addressed to ensure the safe and effective implementation of this technology in clinical practice. The findings of this study suggest that GPT-4 (Generative Pre-trained Transformer 4), an advanced AI model, has the potential to significantly contribute to the standardization and optimization of radiology reporting, offering improved efficiency and communication in clinical practice. • Large language model-generated radiology reports exhibited high content similarity and moderate structural resemblance to radiologist-generated reports. • Performance metrics highlighted the strong matching of word selection and order, as well as high semantic similarity between AI and radiologist-generated reports. • Large language model demonstrated potential for generating standardized radiology reports, improving efficiency and communication in clinical settings.

A hierarchical convolutional model for biomedical relation extraction

Biomedical relation extraction aims to extract the interactive relations between biomedical entities in a sentence. In biomedical literature, the sentence lengths are longer compared to general domain. Because all entity pairs in a sentence share the same contextual features and each of them should be evaluated, the biomedical relation extract task suffers from more serious semantic overlapping and data imbalance problems. In this study, a hierarchical convolutional model is proposed to address these problems. This model organizes the convolution operation in a hierarchical structure. First, after a sentence is divided into several channels by using the semantic structure of a relation instance, a token-level convolution is used to encodes local contextual features of different channels. Then, a channel-level convolution is designed to encode global semantic dependencies of a sentence. The hierarchical convolution is effective to learn contextual features and semantic dependencies relevant to ordered named entities, which enhance the discriminability of a neural network for biomedical relation extraction. The proposed method was evaluated on seven public datasets for three tasks: including protein-protein, drug-drug, and chemical-protein interactions. It outperformed state-of-the-art performance about 3.7% in the F1 score.

Speech Rate and Sentence Length’s Influence on Perception of Mandarin Tone Sandhi

Speech Rate and Sentence Length’s Influence on Perception of Mandarin Tone Sandhi

Application of Criminal Procedures to Perpetrators of Corruption Crimes Based on Perma No. 1 of 2020 concerning Sentencing Guidelines Article 2 Article 3 of the Corruption Eradication Law

The Jambi Corruption Crime Court (Tipikor) in handing down crimes is more dominant in applying Article 3 compared to Article 2 against perpetrators who cause harm to state finances and handing down decisions in the light category, namely an average of 1 year and 11 months. Regarding this issue, the aim of the research is to carry out an analysis of the judge's decision in relation to the implementation of Perma No. 1 of 2020 concerning Sentencing Guidelines for Article 2 and Article 3 of the Corruption Law. By conducting a study of the Jambi Corruption Court's decision, the judge's decision will be evaluated in the light, medium and heavy categories, so that a clear picture of the judge's rationale in implementing PERMA No.1 of 2020 is obtained. The type of research is normative juridical, namely examining materials law, both primary, secondary and tertiary legal materials. The approach is to use a statutory approach and a case approach by analyzing cases related to the legal issues discussed. From the results of the research on the Jambi District Court's decision 1) The decision handed down by the Judge regarding the implementation of PERMA Number 1 of 2020 has not been used as a guideline in handing down the decision. This can be assessed from the verdict handed down by the judge. The length of the prison sentence imposed is not in accordance with the categories as formulated, namely the categories of state losses are the most severe, heavy, medium, light and lightest, where in each category there is a classification, namely the range of prison sentences imposed is adjusted to that category. 2) The aim of punishment in corruption cases is to recover state losses, but in the imposition of a substitute sentence imposed by the judge the aim of the sentence has not been realized, because in PERMA there is no regulation regarding guidelines for imposing additional punishment as replacement money.

Syntactic complexity differentially affects auditory sentence comprehension performance for individuals with age-related hearing loss.

This study examined whether older adults with hearing loss (HL) experience greater difficulties in auditory sentence comprehension compared to those with typical-hearing (TH) when the linguistic burdens of syntactic complexity were systematically manipulated by varying either the sentence type (active vs. passive) or sentence length (3- vs. 4-phrases). A total of 22 individuals with HL and 24 controls participated in the study, completing sentence comprehension test (SCT), standardized memory assessments, and pure-tone audiometry tests. Generalized linear mixed effects models were employed to compare the effects of sentence type and length on SCT accuracy, while Pearson correlation coefficients were conducted to explore the relationships between SCT accuracy and other factors. Additionally, stepwise regression analyses were employed to identify memory-related predictors of sentence comprehension ability. Older adults with HL exhibited poorer performance on passive sentences than on active sentences compared to controls, while the sentence length was controlled. Greater difficulties on passive sentences were linked to working memory capacity, emerging as the most significant predictor for the comprehension of passive sentences among participants with HL. Our findings contribute to the understanding of the linguistic-cognitive deficits linked to age-related hearing loss by demonstrating its detrimental impact on the processing of passive sentences. Cognitively healthy adults with hearing difficulties may face challenges in comprehending syntactically more complex sentences that require higher computational demands, particularly in working memory allocation.

Groups of experts often differ in their decisions: What are the implications for AI and machine learning? A commentary on Noise: A Flaw in Human Judgment, by Kahneman, Sibony, and Sunstein (2021)

AbstractMachine Learning systems rely heavily on annotated instances. Such annotations are frequently done by human experts, or by tools developed by experts, and so the central message of this book, Noise: A Flaw in Human Judgment (Kahneman, Sibony, and Sunstein 2021) is of considerable importance to AI/Machine Learning community. The core message is that if a number of experts are asked to annotate tasks that involve judgments, these responses will frequently differ. This observation poses a problem for how analysts choose a particular annotated dataset (from the group), or process the set of responses to give a “balanced” response, or whether to reject all the annotated datasets. A further important aspect of this book is the case studies which demonstrate that differences in judgments between fellow experts have been reported in a significant number of disciplines including, business, the law, government, and medicine. Kahneman, Sibony and Sunstein (2021), referred to as KSS subsequently, discuss how Expert Biases can be reduced, but the main focus of this book is a discussion of Noise, that is, differences that often occur between fellow experts, and how Noise can often be reduced. To address the last point KSS have formulated a set of six decision hygiene principles which include the recommendation that complex tasks should be subdivided, and then each subtask should be solved separately. A further principle is that each task should be solved by individual experts before the various judgments are discussed with fellow experts. Effectively, the book being reviewed covers three main topics: First, it reports several motivating studies that show how judgments of fellow experts varied significantly in the pricing of insurance premiums, and in setting the lengths of custodial sentences. These motivating studies very effectively illustrate the central concepts of Judgment, Noise, and Bias; that section also provides definitions of these core concepts and discusses how Noise is often amplified in group meetings. Secondly, the authors provide detailed discussion of further studies, in a variety of domains, which report the levels of disagreement between experts. Thirdly, KSS discusses how to reduce the levels of Noise between experts, as noted above, the authors refer to these as Principles of Noise Hygiene. These three parts are interwoven in a complex way throughout the book; in our view, the best overview of the book is given in the section Review and Conclusions: Taking Noise Seriously (KSS, p. 361).

Assessment of sentence sophistication in L2 spoken production: Expansion of verbs and argument structure constructions

Despite the vast body of literature concerning automatic analyses of L2 production, there is limited research on L2 spoken production. Furthermore, investigations into L2 sentence production abilities have predominantly been centered around sentence length. To provide more sophisticated descriptions of L2 syntactic sophistication, this study examines the validity of using the expansion of verbs and constructions as an index of L2 oral production abilities, drawing upon the principles of usage-based approaches to language development. Employing natural language processing tools, we analyzed 790 speech samples produced by L2 English learners using frequency-based and construction-focused indices to assess their predictive validity in relation to the learners’ speaking proficiency. Our findings revealed that advanced L2 learners tend to exhibit an increased use of diverse construction types and a wider range of verb types within each construction. Notably, among the individual construction types observed, the transitive and there-expletive constructions exerted the most substantial influence on the variance in speaking proficiency. These findings suggest a close relationship between the development of verbs and constructions in the spoken domain and factors related to language usage. The results provide an opportunity to evaluate L2 sentence production skills in speaking within the theoretical framework of usage-based approaches.

Ecological validity in corpus-based and experimental translation research

This study provides insights into the ecological validity of experimental results in translation process research (TPR) by comparing translation products under three different conditions: produced in a translation research lab, in the translators' usual working environment, and included as part of a corpus. The results will test the ecological validity of experimental results in TPR and shed light on some of the discrepancies between findings based on corpus data and lab experiments. Data collected in rigorous translation process experiments outside the translators’ usual working environment may not represent authentic translation behaviour. For example, in the experimental setting, translators will not have access to the tools and resources they usually work with, they will be immediately aware of their participation in a scientific study (which may affect their choices), and the stimuli under investigation will often be artificially constructed. These caveats call into question the meaningfulness of conclusions about translation and the translation process based on target texts produced in such artificial settings. This is furthermore reinforced by the differences found between experimental and corpus-based results. In order to test the comparability of different translation settings, 20 translators were commissioned to translate texts according to their usual workflow, in their usual working environment and at their own pace with access to resources of their preference. The source texts were previously used in experiments (Heilmann et al., 2021; Heilmann et al., 2022) and they contain stimuli that may represent a contrastive or cognitive challenge to the translators. The translators were also asked to provide information about the resources they used and the time and breaks they took to finish the translations. Their translations were compared to the target texts collected in the lab experiments and to translations obtained from a corpus with regard to the linguistic stimuli as well as linguistic characteristics such as average sentence length and lexical density. The results highlight the effect of the experimental setting on the translation product and illuminate the differences between experimental data and corpus data.

Deep Learning Applied on Arabic language for punctuation marks prediction

In the absence of explicit punctuation, the Arabic language's semantic and contextual nature poses a unique challenge, necessitating the reintroduction of punctuation marks for elucidating sentence structure and meaning. We investigate the impact of sentence length on punctuation prediction in the context of Arabic language processing. Leveraging Deep Neural Networks (DNNs), specifically Bi-Directional Long Short-Term Memory (Bi-LSTM) models. Our study goes beyond restoration, aiming to accurately predict punctuation marks in unprocessed text. The investigation focuses on five primary punctuation marks (.?,: and !), contributing to a more comprehensive understanding of predicting diverse punctuation marks in Arabic texts and we have achieved 85 % in accuracy . This research not only advances our understanding of Arabic language processing but also serves as a broader exploration of the relationship between sentence length and punctuation prediction.