Papers reviewed and determined not to be word norm studies. Use the flag icon to report errors or suggest re-inclusion.
18625 papers
The paper illustrates a case study aimed at identifying cross-lingual quantitative trends in the distribution of dependency relations in treebanks for typologically different languages. Preliminary results show interesting differences rooted either in language-specific peculiarities or cross-lingual annotation inconsistencies, with a potential impact on different application scenarios.1
In this study, Bakay et. al [1] and Yıldız et. al.'s [2] work on Turkish constituency treebanks were developed further. Compared to the previous work, the most prominent feature of this study is the fact that every annotation and refinement process is held manually. In addition, constituency treebank created as a result of this study abides by the syntactic rules and typologic features of Turkish while the trees created by previous studies convey only the translated and simply inverted trees that completely ignore the syntactic properties of Turkish. The methodology followed in this study resulted in a significantly more accurate representation of Turkish language and simpler, relatively flatter trees. The straightforward style of trees in this study reduces the complexity and offers a better training dataset for learning algorithms.
We outline the issues and decisions involved in creating a Penn-style treebank of Middle Low German (MLG, 1200-1650), which will form part of the Corpus of Historical Low German (CHLG). The attestation for MLG is rich, but the syntax of the language remains relatively understudied. The development of a syntactically annotated corpus for the language will facilitate future studies with a strong empirical basis, building on recent work which indicates that, syntactically, MLG occupies a position in its own right within West Germanic. In this paper, we describe the background for the corpus and the process by which texts were selected to be included. In particular, we focus on the decisions involved in the syntactic annotation of the corpus, specifically, the practical and linguistic reasons for adopting the Penn annotation scheme, the stages of the annotation process itself, and how we have adapted the Penn scheme for syntactic features specific to MLG. We also discuss the issue of data uncertainty, which is a major issue when building a corpus of an under-researched language stage like MLG, and some novel ways in which we capture this uncertainty in the annotation.
We show how a diachronic analysis based on an annotated corpus that includes texts from various Postclassical stages of Greek can open new perspectives in the examination of syntactic phenomena, such as backward control, as well as in the construction of a linguistic and philological profile of earlier texts. Sphrantzes’ Chronicle (15th ct. AD) demonstrates an example of a text that reflects “parallel” grammars of a transitional period (Kroch 2001). We support this view through a diachronic examination of backward control in Sphrantzes as well as in Herodotus and the Gospels. The starting point of this case study is related to an apparent asymmetry: though there is a tendency for continuous constructions to increase from Herodotus to the New Testament, discontinuous conjunct participles, with the subject interfering in the participle clause, increase from Herodotus to the New Testament. This apparent asymmetry concerns examples of backward control. We connect the characteristics of backward control in Sphrantzes to general properties of the text, which presents evidence of an essentially modern syntax that is archaized in various ways (Horrocks 2010: 272). We use evidence from the presence of NPs in the dative case (an archaizing element) and the absence of verbs that show the middle-passive voice alternation (a modern element of the text) to argue in favor of this claim.
Abstract This article analyses the linguistic norms found within legal and legislative language and their implementation. It attempts to answer the following questions: is there a common scope for the use of linguistic norms in general language and legislative language, what can form the basis for resolving issues of correctness in legal and legislative language and is a codification of the linguistic norms for legislative language necessary? The discrepancies observed between normative standards and linguistic practise raise the issue of the need to codify linguistic norms within legal and legislative language. In this article, I hypothesise the need to elaborate a source for codifying the norms of legal and legislative language.
Cross-language differences in dependency parsing performance are mostly attributed to treebank size, average sentence length, average dependency length, morphological complexity, and domain differences. In this paper I point to a factor not previously discussed: If we abstract away from words and dependency labels, how many graphs in the test data were seen in the training data? I discuss how to compute graph isomorphisms, and show that, treebank size aside, overlap between training and test graphs explains more of the observed variation than standard explanations such as the above.
We introduce Sta n z a, an open-source Python natural language processing toolkit supporting 66 human languages. Compared to existing widely used toolkits, Sta n z a features a language-agnostic fully neural pipeline for text analysis, including tokenization, multiword token expansion, lemmatization, part-ofspeech and morphological feature tagging, dependency parsing, and named entity recognition. We have trained Sta n z a on a total of 112 datasets, including the Universal Dependencies treebanks and other multilingual corpora, and show that the same neural architecture generalizes well and achieves competitive performance on all languages tested. Additionally, Sta n z a includes a native Python interface to the widely used Java Stanford CoreNLP software, which further extends its functionality to cover other tasks such as coreference resolution and relation extraction. Source code, documentation, and pretrained models for 66 languages are available at https:// stanfordnlp.github.io/stanza/.
Dependency relations are needed for the development of a dependency treebank and a dependency parser. The guidelines 1 for the development of treebank for Sanskrit proposed a set of dependency relations. Use of these relations for the development of a sentence generator and a dependency parser for Sanskrit demanded a need for an enhancement as well as a revision of these relations. In this paper, we discuss the revised version of these relations and discuss the cases where there is a possibility of multiple tagging either due to the ellipsis of certain arguments or due to the possible derivational morphological analysis. This led us to arrive at specific instructions for handling such cases during the tagging. A treebank with around 4000 sentences has been developed following these guidelines. Finally we evaluate a grammar based dependency parser for Sanskrit on this treebank and report its performance.
obtained from the automated conversion of the Late Latin Charter Treebank 2 (LLCT2), originally in the Prague Dependency Treebank (PDT) style. As this treebank consists of Early Medieval legal documents, its language variety differs considerably from both the Classical and Medieval learned varieties prevalent in the other currently available UD Latin treebanks. Consequently, besides significant phenomena from the perspective of diachronic linguistics, this treebank also poses several challenging technical issues for the current and future syntactic annotation of Latin in the UD framework. Some of the most relevant cases are discussed in depth, with comparisons between the original PDT and the resulting UD annotations. Additionally, an overview of the UD-style structure of the treebank is given, and some diachronic aspects of the transition from Latin to Romance languages are highlighted.
The lack of large and diverse discourse treebanks hinders the application of data-driven approaches, such as deep-learning, to RSTstyle discourse parsing. In this work, we present a novel scalable methodology to automatically generate discourse treebanks using distant supervision from sentiment-annotated datasets, creating and publishing MEGA-DT, a new large-scale discourse-annotated corpus. Our approach generates discourse trees incorporating structure and nuclearity for documents of arbitrary length by relying on an efficient heuristic beam-search strategy, extended with a stochastic component. Experiments on multiple datasets indicate that a discourse parser trained on our MEGA-DT treebank delivers promising inter-domain performance gains when compared to parsers trained on human-annotated discourse corpora.
Treebanks are linguistically annotated corpus of natural language texts represented as a database. It is vital in natural language processing (NLP), which allows the interaction and communication between computers and the human language. It is behind the recent technological innovations of automated and smart assistants. This paper intends to create an English treebank for the usage of Mapua University in their future endeavors to develop Interactive Voice Response (IVR) systems. This study is accomplished by providing students with a connection to a communication server through their phones. Calls are made to the Asterisk server set up in a Raspberry Pi. When the intended audio message is forwarded to the system, it is converted to a text input using a Speech-to-Text algorithm. It then undergoes process and analysis divided into five parts: preprocessing, segmentation, tagging, creation of the grammar tree, and computation for the Probabilistic Context-Free Grammar (PCFG). Based on the testing results for this study, the system yielded a word error rate of 7.36%, a NER F1 score of 71.7%, and a PCFG calculation accuracy of 64.44%.
The question whether a constitutive linguistic norm can be prescriptive is central to the debate on the normativity of meaning. Recently, the author has attempted to defend an affirmative answer, pointing to how speakers sporadically invoke constitutive linguistic norms in the service of linguistic calibration. Such invocations are clearly prescriptive. However, they are only appropriate if the invoked norms are applicable to the addressed speaker. But that can only be the case if the speaker herself generally accepts them. This qualification has led critics to argue that if an addressed speaker’s acceptance is a necessary condition for legitimate prescriptions (and reproach for failure to adhere to them), then the account becomes unable to underwrite actual normativity. Moreover, critics argue, a danger of vicious circularity arises from the calibration account. This paper shows that once a vantage point within the calibration practice is accepted, the criticisms lose their force. It then explores why a theorist might reject such a perspective and suggests, as a plausible candidate, implicit Humean assumptions about the proper explanation of (linguistic) action. The paper ends by sketching a way forward for the debate on the normativity of meaning in light of this diagnosis.
Multiword Expression (MWE) has been a pain in the neck, especially in determining its word-classes in syntactic treebank. Previous work had proposed annotation guidelines for Indonesian MWEs that align to the Penn Treebank (PTB) format. However, we think that their proposed annotation still needs improvements. Therefore, this study proposes a new annotation guideline in labeling Indonesian MWE that conforms to PTB format. Moreover, we also revised the MWE annotation of an existing Indonesian constituency treebank consisting of 1030 sentences to conform to the new guidelines. To evaluate the revised treebank's quality, we built an Indonesian constituency parser model using the revised treebank and Stanford parser. The experiments show that the resulting parser has an F1-score of 69.97%.
International audience
Abstract Despite the remarkable advances made in recent years to facilitate the lexicographer’s work of interpreting and synthesizing the complexity of language uncovered by corpora, an uncritical use of cutting-edge corpus tools and resources can instill a false sense of assurance. In this paper, authentic examples pertaining to wordlist use, collocation research and example selection that arose when compiling a real-world lexical database are discussed through the lens of problems that can easily slip through the cracks in e-lexicography. In doing so, we emphasize the importance of solid training and sound lexicographic judgment when using corpora, corpus tools and corpus-derived resources, and provide an opportunity to reflect on how e-lexicography can be further refined in the future.
A recent advance in monolingual dependency parsing is the idea of a treebank embedding vector, which allows all treebanks for a particular language to be used as training data while at the same time allowing the model to prefer training data from one treebank over others and to select the preferred treebank at test time. We build on this idea by 1) introducing a method to predict a treebank vector for sentences that do not come from a treebank used in training, and 2) exploring what happens when we move away from predefined treebank embedding vectors during test time and instead devise tailored interpolations. We show that 1) there are interpolated vectors that are superior to the predefined ones, and 2) treebank vectors can be predicted with sufficient accuracy, for nine out of ten test languages, to match the performance of an oracle approach that knows the most suitable predefined treebank embedding for the test set.
Abstract In this paper, we present a novel lemmatization method based on a sequence-to-sequence neural network architecture and morphosyntactic context representation. In the proposed method, our context-sensitive lemmatizer generates the lemma one character at a time based on the surface form characters and its morphosyntactic features obtained from a morphological tagger. We argue that a sliding window context representation suffers from sparseness, while in majority of cases the morphosyntactic features of a word bring enough information to resolve lemma ambiguities while keeping the context representation dense and more practical for machine learning systems. Additionally, we study two different data augmentation methods utilizing autoencoder training and morphological transducers especially beneficial for low-resource languages. We evaluate our lemmatizer on 52 different languages and 76 different treebanks, showing that our system outperforms all latest baseline systems. Compared to the best overall baseline, UDPipe Future, our system outperforms it on 62 out of 76 treebanks reducing errors on average by 19% relative. The lemmatizer together with all trained models is made available as a part of the Turku-neural-parsing-pipeline under the Apache 2.0 license.
Text structuring is a fundamental step in NLG, especially when generating multi-sentential text. With the goal of fostering more general and data-driven approaches to text structuring, we propose the new and domain-independent NLG task of structuring and ordering a (possibly large) set of EDUs. We then present a solution for this task that combines neural dependency tree induction with pointer networks and can be trained on large discourse treebanks that have only recently become available. Further, we propose a new evaluation metric that is arguably more suitable for our new task compared to existing content ordering metrics. Finally, we empirically show that our approach outperforms competitive alternatives on the proposed measure and is equivalent in performance with respect to previously established measures.
Pretrained multilingual contextual representations have shown great success, but due to the limits of their pretraining data, their benefits do not apply equally to all language varieties. This presents a challenge for language varieties unfamiliar to these models, whose labeled and unlabeled data is too limited to train a monolingual model effectively. We propose the use of additional language-specific pretraining and vocabulary augmentation to adapt multilingual models to low-resource settings. Using dependency parsing of four diverse low-resource language varieties as a case study, we show that these methods significantly improve performance over baselines, especially in the lowestresource cases, and demonstrate the importance of the relationship between such models' pretraining data and target language varieties.
We introduce a new symmetric measure (called pos ) that utilises the non-symmetric KL cpos 3 measure We can set a threshold for this new measure so that a pair of treebanks can be considered harmonious in their annotation if pos does not surpass the threshold. For the calculation of the threshold, we estimate the effects of (i) the size variation, and (ii) the genre variation in the considered pair of treebanks. The estimations are based on data from treebanks of distinct language families, making the threshold less dependent on the properties of individual languages. We demonstrate the utility of the proposed measure by listing the treebanks in Universal Dependencies version 2.5 (UDv2.5) (Zeman et al., 2019) data that are annotated consistently with other treebanks of the same language. However, the measure could be used to assess inter-treebank annotation consistency under other (non-UD) annotation guidelines as well.
Tae Hwan Oh, Ji Yoon Han, Hyonsu Choe, Seokwon Park, Han He, Jinho D. Choi, Na-Rae Han, Jena D. Hwang, Hansaem Kim. Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies. 2020.
This paper reports on the analysis and annotation of Multiword Expressions in the Irish Universal Dependency Treebank. We provide a linguistic discussion around decisions on how to appropri- ately label Irish MWEs using the compound, flat and fixed dependency relation labels within the framework of the Universal Dependencies annotation guidelines. We discuss some nuances of the Irish language that pose challenges for assigning these UD labels and provide this report in support of the Irish UD annotation guidelines. With this we hope to ensure consistency in annotation across the dataset and provide a basis for future MWE annotation for Irish.
Historical linguistics, whether synchronic or diachronic, is by definition based on corpora.Since we do not have access to the intuitions of native speakers we can only test linguistic hypotheses about historical languages by systematically collating information from our corpus of texts.For questions that typically concern linguists, this often means identifying every occurrence of a particular phenomenon in the corpus, analysing, classifying and counting the occurrences and then using this for testing hypotheses about the structure of the language.This can be done manually, but this is time-consuming and error-prone.As Haug (2015) points out, while reading the text and manually collating information from it is essential for hypothesis formation it is much less useful for hypothesis testing.Even if the text is in electronic form, it is easy to overlook an example, record it incorrectly or fail to apply test criteria consistently over time.This paper focuses on treebanks, which are corpora that have been annotated with morphosyntactic information so that we can extract linguistic structures like 'verb with an accusative noun'.High-quality treebanks for a range of historical languages now exist and are widely used in historical linguistic research.This includes treebanks that follow the Penn-style of annotation, e.g. the Penn-Helsinki
The present article presents some challenges posed by lemmatization and PoS tagging of Latin, with reference to the ongoing work to revise the Latin Dependency Treebank. Current options available for lemmatization and morphological analysis of Latin are reviewed and discussed. The pipeline to annotate the morphological layer of the Latin Dependency Treebank is shown to consist of three main steps: (i) tokenization/sentence split, which is performed via a documented rule-based algorithm, (ii) pre-population by means of COMBO, a state-of-the-art joint lemmatizer, PoS tagger, and parser trained on the data of the Latin Dependency Treebank 2.1, and (iii) manual error correction informed by the attempt to identify and document lemmatization and morphology annotation rules.
We present scalable Universal Dependency (UD) treebank synthesis techniques that exploit advances in language representation modeling which leverage vast amounts of unlabeled generalpurpose multilingual text. We introduce a data augmentation technique that uses synthetic treebanks to improve production-grade parsers. The synthetic treebanks are generated using a state-of-the-art biaffine parser adapted with pretrained Transformer models, such as Multilingual BERT (M-BERT). The new parser improves LAS by up to two points on seven languages. The production models' LAS performance improves as the augmented treebanks scale in size, surpassing performance of production models trained on originally annotated UD treebanks.
Most syntactic dependency parsing models may fall into one of two categories: transition- and graph-based models. The former models enjoy high inference efficiency with linear time complexity, but they rely on the stacking or re-ranking of partially-built parse trees to build a complete parse tree and are stuck with slower training for the necessity of dynamic oracle training. The latter, graph-based models, may boast better performance but are unfortunately marred by polynomial time inference. In this paper, we propose a novel parsing order objective, resulting in a novel dependency parsing model capable of both global (in sentence scope) feature extraction as in graph models and linear time inference as in transitional models. The proposed global greedy parser only uses two arc-building actions, left and right arcs, for projective parsing. When equipped with two extra non-projective arc-building actions, the proposed parser may also smoothly support non-projective parsing. Using multiple benchmark treebanks, including the Penn Treebank (PTB), the CoNLL-X treebanks, and the Universal Dependency Treebanks, we evaluate our parser and demonstrate that the proposed novel parser achieves good performance with faster training and decoding.
Emotion research typically searches for consistency and specificity in physiological activity across instances of an emotion category, such as anger or fear, yet studies to date have observed more variation than expected. In the present study, we adopt an alternative approach, searching inductively for structure within variation, both within and across participants. Following a novel, physiologically-triggered experience sampling procedure, participants' self-reports and peripheral physiological activity were recorded when substantial changes in cardiac activity occurred in the absence of movement. Unsupervised clustering analyses revealed variability in the number and nature of patterns of physiological activity that recurred within individuals, as well as in the affect ratings and emotion labels associated with each pattern. There were also broad patterns that recurred across individuals. These findings support a constructionist account of emotion which, drawing on Darwin, proposes that emotion categories are populations of variable instances tied to situation-specific needs.
It is now a common practice to compare models of human language processing by comparing how well they predict behavioral and neural measures of processing difficulty, such as reading times, on corpora of rich naturalistic linguistic materials. However, many of these corpora, which are based on naturally-occurring text, do not contain many of the low-frequency syntactic constructions that are often required to distinguish between processing theories. Here we describe a new corpus consisting of English texts edited to contain many low-frequency syntactic constructions while still sounding fluent to native speakers. The corpus is annotated with hand-corrected Penn Treebank-style parse trees and includes self-paced reading time data and aligned audio recordings. We give an overview of the content of the corpus, review recent work using the corpus, and release the data.
BACKGROUND: When the COVID-19 pandemic restricted visitation between intensive care unit patients and their families, the virtual intensive care unit (vICU) in our large tertiary hospital was adapted to facilitate virtual family visitation. The objective of this paper is to document findings from interviews conducted with family members on three categories: (1) feelings experienced during the visit, (2) barriers, challenges or concerns faced using this service, and (3) opportunities for improvements. METHODS: Family members were interviewed postvisit via phone. For category 1 (feelings), automated analysis in Python using the Valence Aware Dictionary for sentiment Reasoner package produced weighted valence (extent of positive, negative or neutral emotive connotations) of the interviewees' word choices. Outputs were compared with a manual coder's valence ratings to assess reliability. Two raters conducted inductive thematic analysis on the notes from these interviews to analyse categories 2 (barriers) and 3 (opportunities). RESULTS: Valence-based and manual sentiment analysis of 230 comments received on feelings showed over 86% positive sentiments (88.2% and 86.8%, respectively) with some neutral (7.3% and 6.8%) and negative (4.5% and 6.4%) sentiments. The qualitative analysis of data from 57 participants who commented on barriers showed four primary concerns: inability to communicate due to patient status (44% of respondents); technical difficulties (35%); lack of touch and physical presence (11%); and frequency and clarity of communications with the care team (11%). Suggested improvements from 59 participants included: on demand access (51%); improved communication with the care team (17%); improved scheduling processes (10%); and improved system feedback and technical capabilities (17%). CONCLUSIONS: Use of vICU for remote family visitations evoked happiness, joy, gratitude and relief and a sense of closure for those who lost loved ones. Identified areas for concern and improvement should be addressed in future implementations of telecritical care for this purpose.
Machine learning (ML) has progressed rapidly during the past decade and ML models have been deployed in various real-world applications. Meanwhile, machine learning models have been shown to be vulnerable to various security and privacy attacks. One attack that has attracted a great deal of attention recently is the backdoor attack. Specifically, the adversary poisons the target model training set, to mislead any input with an added secret trigger to a target class, while keeping the accuracy for original inputs unchanged. Previous backdoor attacks mainly focus on computer vision tasks. In this paper, we present the first systematic investigation of the backdoor attack against models designed for natural language processing (NLP) tasks. Specifically, we propose three methods to construct triggers in the NLP setting, including Char-level, Word-level, and Sentence-level triggers. Our Attacks achieve an almost perfect success rate without jeopardizing the original model utility. For instance, using the word-level triggers, our backdoor attack achieves 100% backdoor accuracy with only a drop of 0.18%, 1.26%, and 0.19% in the models utility, for the IMDB, Amazon, and Stanford Sentiment Treebank datasets, respectively.
Lexical simplification (LS) aims to replace complex words in a given sentence with their simpler alternatives of equivalent meaning. Recently unsupervised lexical simplification approaches only rely on the complex word itself regardless of the given sentence to generate candidate substitutions, which will inevitably produce a large number of spurious candidates. We present a simple LS approach that makes use of the Bidirectional Encoder Representations from Transformers (BERT) which can consider both the given sentence and the complex word during generating candidate substitutions for the complex word. Specifically, we mask the complex word of the original sentence for feeding into the BERT to predict the masked token. The predicted results will be used as candidate substitutions. Despite being entirely unsupervised, experimental results show that our approach obtains obvious improvement compared with these baselines leveraging linguistic databases and parallel corpus, outperforming the state-of-the-art by more than 12 Accuracy points on three well-known benchmarks.
In this study we evaluate the convergent validity of a new graphical self-report tool (the EmojiGrid) for the affective appraisal of perceived touch events. The EmojiGrid is a square grid labeled with facial icons (emoji) showing different levels of valence and arousal. The EmojiGrid is language independent and efficient (a single click suffices to report both valence and arousal), making it a practical instrument for studies on affective appraisal. We previously showed that participants can intuitively and reliably report their affective appraisal (valence and arousal) of visual, auditory and olfactory stimuli using the EmojiGrid, even without additional (verbal) instructions. However, because touch events can be bidirectional and dynamic, these previous results cannot be generalized to the touch domain. In this study, participants reported their affective appraisal of video clips showing different interpersonal (social) and object-based touch events, using either the validated 9-point SAM (Self-Assessment Mannikin) scale or the EmojiGrid. The valence ratings obtained with the EmojiGrid and the SAM are in excellent agreement. The arousal ratings show good agreement for object-based touch and moderate agreement for social touch. For social touch and at more extreme levels of valence, the EmojiGrid appears more sensitive to arousal than the SAM. We conclude that the EmojiGrid can also serve as a valid and efficient graphical self-report instrument to measure human affective response to a wide range of tactile signals.
Abstract The rise of world Englishes has challenged the emphasis on native-speaker accents and cultures in English language teaching. This study aimed to investigate the representation of world Englishes and cultures in three global language teaching textbooks, namely Interchange, English Result, and American English File. The textbooks were subjected to content analysis regarding their reference to Inner, Outer, and Expanding Circles’ varieties and their associated cultural contents. Kachru ( The alchemy of English: The spread functions and models of non-native Englishes. Oxford: Pergamon, 1986) notion of Concentric Circles, and the categorization proposed by Pfister and Borzelli ( Unterrichtspraxis 10:102–108, 1977) functioned as a framework to see which aspects of each culture (social, personal, religion/arts/humanities, political systems and institutions, and environmental concerns) were addressed in these textbooks. Findings revealed that most of the references to the three circles and cultural elements embodied in the textbooks were toward Inner Circle countries in American English File. Furthermore, in Interchange and English Result series, reference to Outer and Expanding Circles’ varieties and cultural elements were comparatively more evident. However, all the three textbook series mostly represented Inner-Circle accents. These findings have implications for materials developers to adopt an EIL-aware approach and to avoid the sole representation of native speakers’ linguistic norms and cultures in ELT textbooks.
Federated learning (FL) is a privacy-preserving technique for training a vast amount of decentralized data and making inferences on mobile devices. As a typical language modeling problem, mobile keyboard prediction aims at suggesting a probable next word or phrase and facilitating the human-machine interaction in a virtual keyboard of the smartphone or laptop. Mobile keyboard prediction with FL hopes to satisfy the growing demand that high-level data privacy be preserved in artificial intelligence applications even with the distributed models training. However, there are two major problems in the federated optimization for the prediction: (1) aggregating model parameters on the server-side and (2) reducing communication costs caused by model weights collection. To address the above issues, traditional FL methods simply use averaging aggregation or ignore communication costs. We propose a novel Federated Mediation (FedMed) framework with the adaptive aggregation, mediation incentive scheme, and topK strategy to address the model aggregation and communication costs. The performance is evaluated in terms of perplexity and communication rounds. Experiments are conducted on three datasets (i.e., Penn Treebank, WikiText-2, and Yelp) and the results demonstrate that our FedMed framework achieves robust performance and outperforms baseline approaches.
The training of Deep Neural Networks (DNNs) brings enormous memory requirements and computational complexity, which makes it a challenge to train DNN models on resource-constrained devices. Training DNNs with reduced-precision data representation is crucial to mitigate this problem. In this article, we conduct a thorough investigation on training DNNs with low-bit posit numbers, a Type-III universal number (Unum). Through a comprehensive analysis of quantization with various data formats, it is demonstrated that the posit format shows great potential to be employed in the training of DNNs. Moreover, a DNN training framework using 8-bit posit is proposed with a novel tensor-wise scaling scheme. The experiments show the same performance as the state-of-the-art (SOTA) across multiple datasets (MNIST, CIFAR-10, ImageNet, and Penn Treebank) and model architectures (LeNet-5, AlexNet, ResNet, MobileNet-V2, and LSTM). We further design an energy-efficient hardware prototype for our framework. Compared to the standard floating-point counterpart, our design achieves a reduction of 68, 51, and 75 percent in terms of area, power, and memory capacity, respectively.
As different genres are known to differ in their communicative properties and as previously, for Chinese, discourse relations have only been annotated over news text, we have created the TED-CDB dataset. TED-CDB comprises a large set of TED talks in Chinese that have been manually annotated according to the goals and principles of Penn Discourse Treebank, but adapted to features that are not present in English. It serves as a unique Chinese corpus of spoken discourse. Benchmark experiments show that TED-CDB poses a challenge for state-of-the-art discourse relation classifiers, whose F1 performance on 4way classification is <60%. This is a dramatic drop of 35% from performance on the news text in the Chinese Discourse Treebank. Transfer learning experiments have been carried out with the TED-CDB for both same-language cross-domain transfer and same-domain crosslanguage transfer. Both demonstrate that the TED-CDB can improve the performance of systems being developed for languages other than Chinese and would be helpful for insufficient or unbalanced data in other corpora. The dataset and our Chinese annotation guidelines has been made freely available. 1
This paper describes the development of Turkic Morpheme web portal, a toolkit that takes into account core features of Turkic languages and meets the requirements for research activities in computational linguistics and typology. This portal was created on the basis of the structural-parametric functional model of the Turkic morpheme and contains special linguistic databases that describe the categories of Turkic languages at different levels: morphological, syntactic, and semantic. The portal can also be used in educational process as a reference system for Turkic languages.
Several studies have suggested that females and males differ in reward behaviors and their underlying neural circuitry. Whether human sex differences extend across neural and behavioral levels for both rewards and punishments remains unclear. We studied a community sample of 221 young women and men who performed a monetary incentive task known to engage the mesoaccumbal pathway and salience network. Both stimulus salience (behavioral relevance) and valence (win vs loss) varied during the task. In response to high- vs low-salience stimuli presented during the monetary incentive task, men showed greater subjective arousal ratings, behavioral accuracy and skin conductance responses (P < 0.006, Hedges' effect size g = 0.38 to 0.46). In a subsample studied with functional magnetic resonance imaging (n = 44), men exhibited greater responsiveness to stimulus salience in the nucleus accumbens, midbrain, anterior insula and dorsal anterior cingulate cortex (P < 0.02, g = 0.86 to 1.7). Behavioral, autonomic and neural sensitivity to the valence of stimuli did not differ by sex, indicating that responses to rewards vs punishments were similar in women and men. These results reveal novel and robust sex differences in reward- and punishment-related traits, behavior, autonomic activity and neural responses. These convergent results suggest a neurobehavioral basis for sexual dimorphism observed in the reward system, including reward-related disorders.
In this paper we propose a novel data augmentation approach where guided outputs of a language generation model, e.g. GPT-2, when labeled, can improve the performance of text classifiers through an active learning process. We transform the data generation task into an optimization problem which maximizes the usefulness of the generated output, using Monte Carlo Tree Search (MCTS) as the optimization strategy and incorporating entropy as one of the optimization criteria. We test our approach against a Non-Guided Data Generation (NGDG) process that does not optimize for a reward function. Starting with a small set of data, our results show an increased performance with MCTS of 26% on the TREC-6 Questions dataset, and 10% on the Stanford Sentiment Treebank SST-2 dataset. Compared with NGDG, we are able to achieve increases of 3% and 5% on TREC-6 and SST-2.
Cross-lingual dependency parsing approaches have been employed to develop dependency parsers for the languages for which little or no treebanks are available using the treebanks of other languages. A language for which the cross-lingual parser is developed is usually referred to as the target language and the language whose treebank is used to train the cross-lingual parser model is referred to as the source language. The cross-lingual parsing approaches for dependency parsing may be broadly classified into three categories: model transfer, annotation projection, and treebank translation. This survey provides an overview of the various aspects of the model transfer approach of cross-lingual dependency parsing. In this survey, we present a classification of the model transfer approaches based on the different aspects of the method. We discuss some of the challenges associated with cross-lingual parsing and the techniques used to address these challenges. In order to address the difference in vocabulary between two languages, some approaches use only non-lexical features of the words to train the models while others use shared representations of the words. Some approaches address the morphological differences by chunk-level transfer rather than word-level transfer. The syntactic differences between the source and target languages are sometimes addressed by transforming the source language treebanks or by combining the resources of multiple source languages. Besides cross-lingual transfer parser models may be developed for a specific target language or it may be trained to parse sentences of multiple languages. With respect to the above-mentioned aspects, we look at the different ways in which the methods can be classified. We further classify and discuss the different approaches from the perspective of the corresponding aspects. We also demonstrate the performance of the transferred models under different settings corresponding to the classification aspects on a common dataset.
Despite achieving prominent performance on many important tasks, it has been reported that neural networks are vulnerable to adversarial examples. Previously studies along this line mainly focused on semantic tasks such as sentiment analysis, question answering and reading comprehension. In this study, we show that adversarial examples also exist in dependency parsing: we propose two approaches to study where and how parsers make mistakes by searching over perturbations to existing texts at sentence and phrase levels, and design algorithms to construct such examples in both of the black-box and white-box settings. Our experiments with one of state-of-the-art parsers on the English Penn Treebank (PTB) show that up to 77% of input examples admit adversarial perturbations, and we also show that the robustness of parsing models can be improved by crafting high-quality adversaries and including them in the training stage, while suffering little to no performance drop on the clean input data.
We present the first Universal Dependencies treebank for Hittite. This paper expands on earlier efforts at Hittite corpus creation (Molina and Molin, 2016; Molina, 2016) and discussions of annotation guidelines for Hittite within the UD framework (Inglese, 2015; Inglese et al., 2018). We build on the expertise of the above works to create a small corpus which we hope will serve as a stepping-stone to more expansive UD treebanking for Hittite.
The Icelandic Contemporary Corpus (IceConTree) is a machine-parsed treebank parsed according to the IcePaHC annotation scheme. It consists of texts from the Icelandic Gigaword Corpus, parsed using the IceNeuralParsingPipeline. It contains 524,601,329 words in 29,929,132 clauses. The treebank consists of 14 texts which are mainly media, law and parliamentary text. Within each text, files are divided according to years. This division was done after the text was parsed and is therefore not completely correct. The texts are labelled according to the following genres: • par: parliamentary text • spe: speech • law: law text • med: text from media • rad: text from radio • onl: text from the Internet • tel: text from television • enc: encyclopedia
This is the first prerelease of PapyGreek annotations. The full release is located at https://doi.org/10.5281/zenodo.5062996.
Abnormalities in olfactory function have been identified in a number of neurological and psychiatric disorders, including Parkinson's disease and schizophrenia. However, little is known about olfactory function in autism spectrum disorder (ASD). The present study aims to assess the olfactory profiles of children with ASD, compared to an age- and sex-matched comparison group of typically developing children and a second clinical control group consisting of non-ASD children with sensory processing dysfunction (SPD). Participants completed a battery of sensory and behavioral assessments including olfactory tasks (Sniffin' Sticks Threshold Test and self-reported valence ratings for two target odorants (phenylethyl alcohol and vanillin) and the University of Pennsylvania Smell Identification Test), and an autism evaluation (Autism Diagnostic Observation Schedule-2). Children with ASD showed intact odor detection with reduced odor identification ability. Poor odor identification was significantly correlated with autism symptom severity. Children with SPD demonstrated reduced odor detection and identification ability. These findings provide evidence for differential patterns of smell processing among ASD and non-ASD neurodevelopmental disorders. Future studies are needed to determine whether the association of impaired olfaction and increased autism symptoms is due to shared etiology.
The aim of this study is to present a robot-assisted therapy protocol for children with ASD based on the current state-of-the-art in both ASD intervention research and robotics research, and critically evaluate its adherence and acceptability based on child as well as parent ratings. The robot-assisted therapy was designed based on motivational components of Pivotal Response Treatment (PRT), a highly promising and feasible intervention focused at training "pivotal" (key) areas such as motivation for social interaction and self-initiations, with the goal of establishing collateral gains in untargeted areas of functioning and development, affected by autism spectrum disorders. Overall, children (3-8 y) could adhere to the robot-assisted therapy protocol (Mean percentage of treatment adherence 85.5%), showed positive affect ratings after therapy sessions (positive in 86.6% of sessions) and high robot likability scores (high in 79.4% of sessions). Positive likability ratings were mainly given by school-aged children (H(1) = 7.91, p =.005) and related to the movements, speech and game scenarios of the robot. Parent ratings on the added value of the robot were mainly positive (Mean of 84.8 on 0-100 scale), while lower parent ratings were related to inflexibility of robot behaviour.
It is commonly believed that knowledge of syntactic structure should improve language modeling. However, effectively and computationally efficiently incorporating syntactic structure into neural language models has been a challenging topic. In this paper, we make use of a multi-task objective, i.e., the models simultaneously predict words as well as ground truth parse trees in a form called "syntactic distances", where information between these two separate objectives shares the same intermediate representation. Experimental results on the Penn Treebank and Chinese Treebank datasets show that when ground truth parse trees are provided as additional training signals, the model is able to achieve lower perplexity and induce trees with better quality. * Equal contribution.