Papers reviewed and determined not to be word norm studies. Use the flag icon to report errors or suggest re-inclusion.
18625 papers
Earlier work in parsing Arabic has speculated that attachment to construct state constructions decreases parsing performance. We make this speculation precise and define the problem of attachment to construct state constructions in the Arabic Treebank. We present the first statistics that quantify the problem. We provide a baseline and the results from a first attempt at a discriminative learning procedure for this task, achieving 80% accuracy.
We present a simple and effective semisupervised method for training dependency parsers. We focus on the problem of lexical representation, introducing features that incorporate word clusters derived from a large unannotated corpus. We demonstrate the effectiveness of the approach in a series of dependency parsing experiments on the Penn Treebank and Prague Dependency Treebank, and we show that the cluster-based features yield substantial gains in performance across a wide range of conditions. For example, in the case of English unlabeled second-order parsing, we improve from a baseline accuracy of 92:02% to 93:16%, and in the case of Czech unlabeled second-order parsing, we improve from a baseline accuracy of 86:13% to 87:13%. In addition, we demonstrate that our method also improves performance when small amounts of training data are available, and can roughly halve the amount of supervised data required to reach a desired level of performance.
This paper discusses the role of annotated corpora as works of reference for grammatical translation problems. Within this context, the English-German CroCo Corpus and its multi-layer alignment and annotation are introduced. It is described how the corpus is exploited as interactive resource to display translation solutions for typologically problematic constructions. Additionally, the Penn and TiGer Treebanks are used as comparable corpora for English and German. The linguistic enrichment of the treebanks, i.e. their syntactic annotation, is described and corpus query techniques relevant for translation problems are shown. Relevant structures are extracted from the treebanks and translation candidates are displayed and discussed. The advantage of this technique is that translation solutions are extracted from published translations, i.e. language in use. Consequently, they are more comprehensive and inventive than dictionary entries or descriptions in grammars are. Treebanks could thus be used as an interactive reference grammar in translation education and practice.
Although punctuation is pervasive in written text, their treatment in parsers and corpora is often second-class. We examine the treatment of commas in CCGbank, a wide-coverage corpus for Combinatory Categorial Grammar (CCG), reanalysing its comma structures in order to eliminate a class of redundant rules, obtaining a more consistent treebank. We then eliminate these rules from C&C, a wide-coverage statistical CCG parser, obtaining a 37 % increase in parsing speed on the standard CCGbank test set and a considerable reduction in memory consumed, without affecting parser accuracy. 1
In the framework of meaning representation in Natural Language Processing (NLP), we aim to develop a system that can be used for heterogeneous applications such as Machine Translation, Information Retrieval or Lexical Access. This system is based on six hypotheses which concern meaning representation and acquisition. In this paper, we discuss the related hypotheses that motivate the construction of a such system and how these hypotheses, together with NLP software engineering concerns, led us to conceive a distributed multi-agent system for our goals. We present Blexisma2, a distributed multi-agent system for NLP, its conceptual properties, and an example of inter-agent collaboration. The system is currently being tested on a Grid computing environment.
Social relations between humans critically depend on our affective experiences of others. Oxytocin enhances prosocial behavior, but its effect on humans' affective experience of others is not known. We tested whether oxytocin influences affective ratings, and underlying brain activity, of faces that have been aversively conditioned. Using a standard conditioning procedure, we induced differential negative affective ratings in faces exposed to an aversive conditioning compared with nonconditioning manipulation. This differential negative evaluative effect was abolished by treatment with oxytocin, an effect associated with an attenuation of activity in anterior medial temporal and anterior cingulate cortices. In amygdala and fusiform gyrus, this modulation was stronger for faces with direct gaze, relative to averted gaze, consistent with a relative specificity for socially relevant cues. The data suggest that oxytocin modulates the expression of evaluative conditioning for socially relevant faces via influences on amygdala and fusiform gyrus, an effect that may explain its prosocial effects.
Two Languages - One Annotation Scenario? Experience from the Prague Dependency Treebank This paper compares the two FGD-based annotation scenarios for Czech and for English, with the Czech as the basis. We discuss the secondary predication expressed by infinitive and its functions in Czech and English, respectively. We give a few examples of English constructions that do not have direct counterparts in Czech (e.g., tough movement and causative constructions with make, get, and have ), as well as some phenomena central in English but much less employed in Czech (object raising or control in adjectives as nominal predicates), and, last, structures more or less parallel both in their function and distribution, whose respective annotation differs due to significant differences in the respective linguistic traditions (verbs of perception).
The paper describes an approach to automati-cally annotate a Hindi Treebank using Pan-inian dependency framework. The annotator is a rule based system and the rules use certain syntactic cues available in a sentence. This automated annotation scheme aims at facilitat-ing manual annotation by reducing time and effort of manual annotators. Also, the aim of automatic annotation, among other things, is to increase the efficiency of a broad coverage constraint based Hindi parser. We also evalu-ate this tool and show its accuracy and cover-age. 1
In this paper, we will give an overview of the reconstruction process of the Swedish treebank Talbanken, created in the first half of the 70’s. Talbanken contains both written and spoken material, both encoded in the MAMBA-format. The goal has been to construct two new versions of the original data, one based on phrase structure and one on dependency structure. The outcome of the reconstruction, i.e. different versions of Talbanken, is available for non-commercial research and educational purposes. 1
I EMOTION ELICITATION 1. Emotion Elicitation Using Films 2. The International Affective Picture System (IAPS) in the Study of Emotion and Attention 3. The Directed Facial Action Task: Emotional Responses without Appraisal 4. Emotional Behaviors As Emotional Stimuli 5. Probing Unconscious Emotional Processes: On Becoming a Successful Masketeer 6. Social Psychological Methods of Emotion Elicitation 7. Emotion Elicitation Using Dyadic Interaction Tasks 8. Combining Music with Thought to Change Mood 9. Emotion Elicited by Primary Reinforcers, and Following Stimulus-Reinforcement Association Learning 10. Emotion Elicitation with Neurological Patients II EMOTION ASSESSMENT 11. Assessing Positive and Negative via Self-Report 12. The Information-Processing Approach to Emotion Research 13. Observer-Based Measurement of Facial Expression with the Facial Action Coding System 14. Use of Automated Facial Image Analysis for Measurement of Emotion Expression 15. Measuring Emotion-Related Vocal Acoustics 16. The Specific Affect Coding System (SPAFF) 17. Continuous Measurement of Emotion: The Affect Rating Dial 18. Assessing Understanding and Appraisals During Emotional Experience in Everyday Life Situations 19. The Time Sampling Diary (TSD) of Emotional Experience in Everyday Life Situations 20. Methodological Considerations in the Study of Emotion Across Cultures 21. Considerations in Studying Emotion in Infants and Children 22. Conceptual, Theoretical, and Methodological Issues in Inferring Subjective Emotion Experience: Recommendations for Researchers III METHODS FOR UNDERSTANDING THE BIOLOGICAL BASES OF EMOTION 23. Studying Emotion in Animals: Methods, Materials, and Training 24. The Psychophysiological Laboratory 25. Investigating Human Emotion With Lesions and Intracranial Recording 26. Functional Magnetic Resonance Imaging and the Study of Emotion
This article examines the role of subjective familiarity in the implicit and explicit learning of artificial grammars. Experiment 1 found that objective measures of similarity (including fragment frequency and repetition structure) predicted ratings of familiarity, that familiarity ratings predicted grammaticality judgments, and that the extremity of familiarity ratings predicted confidence. Familiarity was further shown to predict judgments in the absence of confidence, hence contributing to above-chance guessing. Experiment 2 found that confidence developed as participants refined their knowledge of the distribution of familiarity and that differences in familiarity could be exploited prior to confidence developing. Experiment 3 found that familiarity was consciously exploited to make grammaticality judgments including those made without confidence and that familiarity could in some instances influence participants' grammaticality judgments apparently without their awareness. All 3 experiments found that knowledge distinct from familiarity was derived only under deliberate learning conditions. The results provide decisive evidence that familiarity is the essential source of knowledge in artificial grammar learning while also supporting a dual-process model of implicit and explicit learning.
Although different in terms of purpose, word-selection procedures, and rating scales, both the ANEW (n = 1034) and DAL (n = 8742) lists, which have 633 words in common, provide normative emotional ratings for English words. This research compared the lists and cross-validated the two main lexical dimensions of affect. Parallel representatives of the two dimensions (Valence and Pleasantness, Arousal and Activation) were correlated across lists (rs =.86,.63). In tune with their separate purposes, the ANEW list, which was designed to describe emotional words, included more rare words, while the DAL, which was designed for natural language applications, included more common ones. The Valence-Activation scatterplot for ANEW was C-shaped and included fewer Arousing words of medium Valence, such as "awake," "debate," and "proves," while the DAL included fewer less common words descriptive of emotion such as "maniac," "corrupt," and "lavish." In view of these differences, list similarities strongly support the generalizability of the two main lexical dimensions of affect.
By ‘treebank-aligned lexical resources ’ we mean ones where there is a systematic correspondence between the lexical resource and treebank syntactic resources. For instance, the lexicon resource contains features representing the subcategorization frames of verbs, which correspond to structural configurations that the verb occurs in, in a treebank. Given such an alignment, a treebank can be
Although current theories suggest that affective empathy (perceivers' experience of social targets' emotions) should contribute to empathic accuracy (perceivers' ability to accurately assess targets' emotions), extant research has failed to consistently demonstrate a correspondence between them. We reasoned that prior null findings may be attributable to a failure to account for the fundamentally interpersonal nature of empathy, and tested the prediction that empathic accuracy may depend on both targets' tendency to express emotion and perceivers' tendency to empathically share that emotion. Using a continuous affect-rating paradigm, we found that perceivers' trait affective empathy was unrelated to empathic accuracy unless targets' trait expressivity was taken into account: Perceivers' trait affective empathy predicted accuracy only for expressive targets. These data suggest that perceivers' self-reported affective empathy can indeed predict their empathic accuracy, but only when targets' expressivity allows their thoughts and feelings to be read.
Periods in the development of the lexical database in the Czech Language Institute, programmes.
Purpose Customer satisfaction is seen to be one of the main determinants of loyalty. However, the relationship between customer satisfaction and loyalty does not seem to be linear, many researchers have reported doubts about the predictability of loyalty solely due to customer satisfaction ratings which ignore image as predictor of loyalty. This paper aims to address the issues. Design/methodology/approach The authors report a study of ski resorts where they first established a causal model of customer satisfaction and image predicting customer loyalty, and then map the scores in a four‐fields‐grid. Additionally the authors conducted a moderator analysis to assess the relative importance of image and satisfaction for loyalty intentions between two different groups (first‐time‐visitors, and regular guests). Findings The results show that those ski resorts with the highest satisfaction ratings and the highest image ratings have the highest loyalty scores. Among first‐time‐visitors overall satisfaction is more important than image, with increasing number of repeat visits the importance of overall satisfaction declines and that of image relatively augments. Practical implications Besides measuring customer satisfaction, managers must assess also image ratings in order to get a realistic view of the loyalty intentions of their customer base. The scores can than be mapped together with the ratings of other ski resorts, and serve as a benchmark study. Originality/value Second order analysis of image (comprising three different dimensions), the image‐satisfaction‐grid, moderating effect of experience to relative importance of satisfaction and image on loyalty.
We present a new English→Czech machine translation system combining linguistically motivated layers of language description (as defined in the Prague Dependency Treebank annotation scenario) with statistical NLP approaches.
Parsing algorithms that process the input from left to right and construct a single derivation have often been considered inadequate for natural language parsing because of the massive ambiguity typically found in natural language grammars. Nevertheless, it has been shown that such algorithms, combined with treebank-induced classifiers, can be used to build highly accurate disambiguating parsers, in particular for dependency-based syntactic representations. In this article, we first present a general framework for describing and analyzing algorithms for deterministic incremental dependency parsing, formalized as transition systems. We then describe and analyze two families of such algorithms: stack-based and list-based algorithms. In the former family, which is restricted to projective dependency structures, we describe an arc-eager and an arc-standard variant; in the latter family, we present a projective and a non-projective variant. For each of the four algorithms, we give proofs of correctness and complexity. In addition, we perform an experimental evaluation of all algorithms in combination with SVM classifiers for predicting the next parsing action, using data from thirteen languages. We show that all four algorithms give competitive accuracy, although the non-projective list-based algorithm generally outperforms the projective algorithms for languages with a non-negligible proportion of non-projective constructions. However, the projective algorithms often produce comparable results when combined with the technique known as pseudo-projective parsing. The linear time complexity of the stack-based algorithms gives them an advantage with respect to efficiency both in learning and in parsing, but the projective list-based algorithm turns out to be equally efficient in practice. Moreover, when the projective algorithms are used to implement pseudo-projective parsing, they sometimes become less efficient in parsing (but not in learning) than the non-projective list-based algorithm. Although most of the algorithms have been partially described in the literature before, this is the first comprehensive analysis and evaluation of the algorithms within a unified framework.
Disordered gambling stigma was examined. University students (117 male, 132 female) rated vignettes describing males with five health conditions (schizophrenia, alcohol dependence, disordered gambling, cancer, and a no diagnosis control with subclinical problems) on a measure of attitudinal social distance. A mixed ANOVA revealed that, in keeping with hypotheses, disordered gambling was more stigmatized than the cancer and control conditions. Interactions suggested that stigma may be influenced by context (i.e., order of vignette appearance) and participant characteristics (i.e., sex and ethnicity), although follow–up analyses revealed this was not the case for disordered gambling. Perceived dangerousness attributions and familiarity (previous experience with a disordered gambler) were also examined. As predicted, perceived dangerousness was positively correlated with social distance scores. Familiarity ratings were unrelated to social distance.
CONTEXT: Cognitive decline, mood, behavioral and sleep disturbances, and limitations of activities of daily living commonly burden elderly patients with dementia and their caregivers. Circadian rhythm disturbances have been associated with these symptoms. OBJECTIVE: To determine whether the progression of cognitive and noncognitive symptoms may be ameliorated by individual or combined long-term application of the 2 major synchronizers of the circadian timing system: bright light and melatonin. DESIGN, SETTING, AND PARTICIPANTS: A long-term, double-blind, placebo-controlled, 2 x 2 factorial randomized trial performed from 1999 to 2004 with 189 residents of 12 group care facilities in the Netherlands; mean (SD) age, 85.8 (5.5) years; 90% were female and 87% had dementia. INTERVENTIONS: Random assignment by facility to long-term daily treatment with whole-day bright (+/- 1000 lux) or dim (+/- 300 lux) light and by participant to evening melatonin (2.5 mg) or placebo for a mean (SD) of 15 (12) months (maximum period of 3.5 years). MAIN OUTCOME MEASURES: Standardized scales for cognitive and noncognitive symptoms, limitations of activities of daily living, and adverse effects assessed every 6 months. RESULTS: Light attenuated cognitive deterioration by a mean of 0.9 points (95% confidence interval [CI], 0.04-1.71) on the Mini-Mental State Examination or a relative 5%. Light also ameliorated depressive symptoms by 1.5 points (95% CI, 0.24-2.70) on the Cornell Scale for Depression in Dementia or a relative 19%, and attenuated the increase in functional limitations over time by 1.8 points per year (95% CI, 0.61-2.92) on the nurse-informant activities of daily living scale or a relative 53% difference. Melatonin shortened sleep onset latency by 8.2 minutes (95% CI, 1.08-15.38) or 19% and increased sleep duration by 27 minutes (95% CI, 9-46) or 6%. However, melatonin adversely affected scores on the Philadelphia Geriatric Centre Affect Rating Scale, both for positive affect (-0.5 points; 95% CI, -0.10 to -1.00) and negative affect (0.8 points; 95% CI, 0.20-1.44). Melatonin also increased withdrawn behavior by 1.02 points (95% CI, 0.18-1.86) on the Multi Observational Scale for Elderly Subjects scale, although this effect was not seen if given in combination with light. Combined treatment also attenuated aggressive behavior by 3.9 points (95% CI, 0.88-6.92) on the Cohen-Mansfield Agitation Index or 9%, increased sleep efficiency by 3.5% (95% CI, 0.8%-6.1%), and improved nocturnal restlessness by 1.00 minute per hour each year (95% CI, 0.26-1.78) or 9% (treatment x time effect). CONCLUSIONS: Light has a modest benefit in improving some cognitive and noncognitive symptoms of dementia. To counteract the adverse effect of melatonin on mood, it is recommended only in combination with light. TRIAL REGISTRATION: controlled-trials.com/isrctn Identifier: ISRCTN93133646.
Parser self-training is the technique of taking an existing parser, parsing extra data and then creating a second parser by treating the extra data as further training data. Here we apply this technique to parser adaptation. In particular, we self-train the standard Charniak/Johnson Penn-Treebank parser using unlabeled biomedical abstracts. This achieves an f-score of 84.3% on a standard test set of biomedical abstracts from the Genia corpus. This is a 20% error reduction over the best previous result on biomedical data (80.2% on the same test set).
We propose a cascaded linear model for joint Chinese word segmentation and partof-speech tagging. With a character-based perceptron as the core, combined with realvalued features such as language models, the cascaded model is able to efficiently utilize knowledge sources that are inconvenient to incorporate into the perceptron directly. Experiments show that the cascaded model achieves improved accuracies on both segmentation only and joint segmentation and part-of-speech tagging. On the Penn Chinese Treebank 5.0, we obtain an error reduction of 18.5 % on segmentation and 12 % on joint segmentation and part-of-speech tagging over the perceptron-only baseline. 1
Drawing on motivational approaches to emotion, the authors propose that the perceived change in spatial distance to pictures that arouse negative emotions exerts an influence on the significance of these pictures. Two experiments induced the illusion that affective pictures approach toward the observer, recede from the observer, or remain static. To determine the motivational significance of the pictures, emotional valence and arousal ratings as well as startle responses were assessed. Approaching unpleasant pictures were found to exert an influence on both the valence and the arousal elicited by the pictures. Furthermore, movement of pleasant or neutral pictures did not influence startle responses, while the second experiment showed that approaching unpleasant pictures elicited enhanced startle responses compared to receding unpleasant pictures. These findings support the view that a change of spatial distance influences motivational significance and thereby shapes emotional responses.
In this paper, we describe the TeP 2.0 -- Electronic Thesaurus for Brazilian Portuguese -- which stores sets of synonym and antonym word forms. Specifically, we present the lexical database and the Web interface of TeP 2.0.
Probabilistic modeling of lexicalized grammars is difficult because these grammars exploit complicated data structures, such as typed feature structures. This prevents us from applying common methods of probabilistic modeling in which a complete structure is divided into sub-structures under the assumption of statistical independence among sub-structures. For example, part-of-speech tagging of a sentence is decomposed into tagging of each word, and CFG parsing is split into applications of CFG rules. These methods have relied on the structure of the target problem, namely lattices or trees, and cannot be applied to graph structures including typed feature structures. This article proposes the feature forest model as a solution to the problem of probabilistic modeling of complex data structures including typed feature structures. The feature forest model provides a method for probabilistic modeling without the independence assumption when probabilistic events are represented with feature forests. Feature forests are generic data structures that represent ambiguous trees in a packed forest structure. Feature forest models are maximum entropy models defined over feature forests. A dynamic programming algorithm is proposed for maximum entropy estimation without unpacking feature forests. Thus probabilistic modeling of any data structures is possible when they are represented by feature forests. This article also describes methods for representing HPSG syntactic structures and predicate-argument structures with feature forests. Hence, we describe a complete strategy for developing probabilistic models for HPSG parsing. The effectiveness of the proposed methods is empirically evaluated through parsing experiments on the Penn Treebank, and the promise of applicability to parsing of real-world sentences is discussed.
In the age of communication, new technological advances are made everyday in the field of information and linguistics. Deriv@ is a system that makes the most of linguistic data. All data managed by this application are connected with derivational morphology, since derived words constitute the starting point from which relationships with other linguistic elements are established. Deriv@ is a linguistic database with two models of representation: one for all Spanish words created by means of derivation; the other for the corresponding Latin words. We offer a grammatically-analysed corpus, both synchronically and diachronically, to make customised queries according to the user.s interests, and also to create a dictionary of derived words. Deriv@ allows and facilitates non-restricted access to all the information available in the two databases. This model is valid for any form derived from Spanish or from other Romance languages. It offers users the possibility of using it real time, thus letting them interact with the system and contribute to its improvement.
We show that jointly parsing a bitext can substantially improve parse quality on both sides. In a maximum entropy bitext parsing model, we define a distribution over source trees, target trees, and node-to-node alignments between them. Features include monolingual parse scores and various measures of syntactic divergence. Using the translated portion of the Chinese treebank, our model is trained iteratively to maximize the marginal likelihood of training tree pairs, with alignments treated as latent variables. The resulting bitext parser outperforms state-of-the-art monolingual parser baselines by 2.5 F1 at predicting English side trees and 1.8 F1 at predicting Chinese side trees (the highest published numbers on these corpora). Moreover, these improved trees yield a 2.4 BLEU increase when used in a downstream MT evaluation.
Broad-coverage parsing has come to a point where distinct approaches can offer (seemingly) comparable performance: statistical parsers acquired from the Penn Treebank (PTB); data-driven dependency parsers; deep parsers trained off enriched treebanks (in linguistic frameworks like CCG, HPSG, or LFG); and hybrid deep parsers, employing hand-built grammars in, for example, HPSG, LFG, or LTAG. Evaluation against trees in the Wall Street Journal (WSJ) section of the PTB has helped advance parsing research over the course of the past decade. Despite some skepticism, the crisp and, over time, stable task of maximizing ParsEval metrics (i.e. constituent labeling precision and recall) over PTB trees has served as a dominating benchmark. However, modern treebank parsers still restrict themselves to only a subset of PTB annotation; there is reason to worry about the idiosyncrasies of this particular corpus; it remains unknown how much the ParsEval metric (or any intrinsic evaluation) can inform NLP application developers; and PTB-style analyses leave a lot to be desired in terms of linguistic information.
A nonhuman primate model was used to evaluate the value of the dexamethasone suppression test as an index of hypothalamic-pituitary-adrenal responsiveness to arousal. In 8 rhesus monkeys plasma cortisol was suppressed by dexamethasone in a dose-dependent fashion at doses between 0.75 and 33 microgram/kg. A replication study was performed 5 months later using a single dexamethasone dose (17 microgram/kg) known to produce maximal plasma cortisol suppression. This yielded highly correlated results (r = 0.91, p less than 0.005) suggesting that dexamethasone suppressibility may be a stable characteristic of individual animals. In 9 other animals whose arousal responses to a stressful procedure (nasogastric tube insertion) had been rated daily over a previous 3-month period, baseline plasma cortisol levels and the percent suppression of plasma cortisol by dexamethasone were evaluated. Baseline plasma cortisol levels did not significantly correlate with the degree of dexamethasone-suppression and the mean arousal ratings within animals. However, the postdexamethasone percent of baseline cortisol did correlate significantly (r = 0.75, p less than 0.025) with individual mean arousal ratings. These preliminary results suggest that assessment of the sensitivity of an individual's hypothalamic-pituitary glucocorticoid feedback system may be a better predictor than its baseline cortisol concentrations of its degree of behavioral arousal to stress.
The Reading Span Test (RST) is a verbal working-memory test. The original RST ( Daneman & Carpenter, 1980 ), and derivatives of it, are being used increasingly as assessments of central executive functioning and for research on aging-associated cognitive decline ( Whitney, Arnett, Driver, & Budd, 2001 ). Several versions have been made in order to further improve the test or to develop a version in a different language. However, all versions changed different things, making direct comparisons of the results with the RST between different research groups and across different languages impossible. This paper presents the results of testing a new standard computerized version of the RST in four languages (Dutch, English, German, and Norwegian). The new RST meets strict methodological criteria that are the same for all four language versions. A plausibility test, an abstract-concrete rating scale, and a pilot-study were conducted on native speakers to test the new RST. In addition, the internal and external reliability and the ecological validity of the new RST were tested. The results showed that the new RST is a suitable test to investigate verbal working memory. Finally, an important advantage of the new RST is that the different language versions make cross-linguistic comparisons of RST results possible.
This article examines the attitudes of a group of middle-class African Americans toward varieties that are available to them for helping to project the attitudes, stances, and affiliations that they perceive as effective in negotiating social and professional environments where vastly distinct linguistic norms may prevail. The research uses subjective reaction tests, interviews, and an online survey to ask questions about the significance of “sounding black” in judgments the participants make about standardness, social class, and appropriateness of speech styles for various environments. The research also examines linguistic features that contribute to the social judgments. Results show a correlation between the perception of African American identity and judgments that occur in other areas; the consultants value AAVE as their heritage language, but see standard African American English as the one variety that can meet the demands of all environments.
The ACL 2008 Workshop on Parsing German features a shared task on parsing German. The goal of the shared task was to find reasons for the radically different behavior of parsers on the different treebanks and between constituent and dependency representations. In this paper, we describe the task and the data sets. In addition, we provide an overview of the test results and a first analysis.
We describe experiments on learning latent variable grammars for various German tree-banks, using a language-agnostic statistical approach. In our method, a minimal initial grammar is hierarchically refined using an adaptive split-and-merge EM procedure, giving compact, accurate grammars. The learning procedure directly maximizes the likelihood of the training treebank, without the use of any language specific or linguistically constrained features. Nonetheless, the resulting grammars encode many linguistically interpretable patterns and give the best published parsing accuracies on three German treebanks.
International audience
The suitability of different parsing methods for different languages is an important topic in syntactic parsing. Especially lesser-studied languages, typologically different from the languages for which methods have originally been developed, pose interesting challenges in this respect. This article presents an investigation of data-driven dependency parsing of Turkish, an agglutinative, free constituent order language that can be seen as the representative of a wider class of languages of similar type. Our investigations show that morphological structure plays an essential role in finding syntactic relations in such a language. In particular, we show that employing sublexical units called inflectional groups, rather than word forms, as the basic parsing units improves parsing accuracy. We test our claim on two different parsing methods, one based on a probabilistic model with beam search and the other based on discriminative classifiers and a deterministic parsing strategy, and show that the usefulness of sublexical units holds regardless of the parsing method. We examine the impact of morphological and lexical information in detail and show that, properly used, this kind of information can improve parsing accuracy substantially. Applying the techniques presented in this article, we achieve the highest reported accuracy for parsing the Turkish Treebank.
A number of researchers have recently conducted experiments comparing “deep” hand-crafted wide-coverage with “shallow” treebank- and machine-learning-based parsers at the level of dependencies, using simple and automatic methods to convert tree output generated by the shallow parsers into dependencies. In this article, we revisit such experiments, this time using sophisticated automatic LFG f-structure annotation methodologies with surprising results. We compare various PCFG and history-based parsers to find a baseline parsing system that fits best into our automatic dependency structure annotation technique. This combined system of syntactic parser and dependency structure annotation is compared to two hand-crafted, deep constraint-based parsers, RASP and XLE. We evaluate using dependency-based gold standards and use the Approximate Randomization Test to test the statistical significance of the results. Our experiments show that machine-learning-based shallow grammars augmented with sophisticated automatic dependency annotation technology outperform hand-crafted, deep, wide-coverage constraint grammars. Currently our best system achieves an f-score of 82.73% against the PARC 700 Dependency Bank, a statistically significant improvement of 2.18% over the most recent results of 80.55% for the hand-crafted LFG grammar and XLE parsing system and an f-score of 80.23% against the CBS 500 Dependency Bank, a statistically significant 3.66% improvement over the 76.57% achieved by the hand-crafted RASP grammar and parsing system.
We present a dependency-driven parser that parses both dependency structures and constituent structures. Constituency representations are automatically transformed into dependency representations with complex arc labels, which makes it possible to recover the constituent structure with both constituent labels and grammatical functions. We report a labeled attachment score close to 90% for dependency versions of the TIGER and TúBa-D/Z treebanks. Moreover, the parser is able to recover both constituent labels and grammatical functions with an F-Score over 75% for TüBa-D/Z and over 65% for TIGER.
In this paper we present the methodology for Word Sense Disambiguation based on domain information. Domain is a set of words in which there is a strong semantic relation among the words. The words in the sentence contribute to determine the domain of the sentence. The availability of WordNet domains makes the domain-oriented text analysis possible. The domain of the target word can be fixed based on the domains of the content words in the local context. This approach can be effectively used to disambiguate nouns. We present the unsupervised approach to Word Sense Disambiguation using the WordNet domains. The model determines the domain of the target word and the sense corresponding to this domain is taken as the correct sense. We have used the WordNet domains 3.1.as lexical database.
Possession in some Austronesian languages shows levels of elaboration far in excess of cross-linguistic norms, while in others it is strikingly unelaborated. The appearance of alienable/inalienable contrasts has been assumed to result from contact with Papuan languages, and the existence of a paradigm of indirect possessive classifiers is cited as one of the pieces of evidence for the Oceanic subgroup, while acknowledging that indirect possession constructions can be found in Malayo-Polynesian languages further west. We argue that the appearance of possessive classifiers in these languages is also the result of contact with Papuan languages west of New Guinea.
This paper describes a method of accurately projecting Propbank roles onto constituents in the CCGbank with near perfect accuracy and automatically annotating verbal categories with the semantic roles of their arguments. The current version of the CCGbank annotates arguments and adjuncts in a suboptimal way – it relies heavily on the Penn Treebank CLR tag, which is widely considered unreliable. By incorporating Propbank roles we are able to modify the derivation to better reflect linguistic reality. Tagging of nodes in the CCG derivation also permits us to annotate verbal categories with semantic roles corresponding to their syntactic arguments, which has strong implications for many NLP tasks.
The Berkeley FrameNet Project (BFN) is making an English lexical database called FrameNet, which describes syntactic and semantic properties of an English lexicon extracted from large electronic text corpora (Baker et al., 1998). Other projects dealing with Spanish, German and Japanese follow a similar approach and annotate large corpora. FrameSQL is a web-based application developed by the author, and it allows the user to search the BFN database in a variety of ways (Sato, 2003). FrameSQL shows a clear view of the headword’s grammar and combinatorial properties offered by the FrameNet database. FrameSQL has been developing and new functions were implemented for processing the Spanish FrameNet data (Subirats and Sato, 2004). FrameSQL is also in the process of incorporating the data of the Japanese FrameNet Project (Ohara et al., 2003) and that of the Saarbrücken Lexical Semantics Acquisition Project (Erk et al., 2003) into the database and will offer the same user-interface for searching these lexical data. This paper describes new functions of FrameSQL, showing how FrameSQL deals with the lexical data of English, Spanish, Japanese and German seamlessly. 1.
OBJECTIVE: This experimental, repeated-measures, crossover design study with nursing home residents examined the efficacy of reflexology in individuals with mild-to-moderate stage dementia. Specifically, the study tested whether a weekly reflexology intervention contributed to the resident outcomes of reduced physiologic distress, reduced pain, and improved affect. SETTING: The study was conducted at a large nursing home in suburban Philadelphia. SAMPLE: The sample included 21 nursing home residents with mild-to-moderate stage dementia randomly assigned to two groups. INTERVENTIONS: The first group received 4 weeks of weekly reflexology treatments followed by 4 weeks of a control condition of friendly visits. The second group received 4 weeks of friendly visits followed by 4 weeks of weekly reflexology. OUTCOME MEASURES: The primary efficacy endpoint was reduction of physiologic distress as measured by salivary alpha-amylase. The secondary outcomes were observed pain (Checklist of Nonverbal Pain Indicators) and observed affect (Apparent Affect Rating Scale). RESULTS: The findings demonstrate that when receiving the reflexology treatment condition, as compared to the control condition, the residents demonstrated significant reduction in observed pain and salivary alpha-amylase. No adverse events were recorded during the study period. CONCLUSIONS: This study provides preliminary support for the efficacy of reflexology as a treatment of stress in nursing home residents with mild-to-moderate stage dementia.
Recent parsing research has started addressing the questions a) how parsers trained on different syntactic resources differ in their performance and b) how to conduct a meaningful evaluation of the parsing results across such a range of syntactic representations. Two German treebanks, Negra and TüBa-D/Z, constitute an interesting testing ground for such research given that the two treebanks make very different representational choices for this language, which also is of general interest given that German is situated between the extremes of fixed and free word order. We show that previous work comparing PCFG parsing with these two treebanks employed PARSEVAL and grammatical function comparisons which were skewed by differences between the two corpus annotation schemes. Focusing on the grammatical dependency triples as an essential dimension of comparison, we show that the two very distinct corpora result in comparable parsing performance.
High doses of ibuprofen have been shown to inhibit muscle protein synthesis after a bout of resistance exercise. We determined the effect of a moderate dose of ibuprofen (400 mg x d(-1)) consumed on a daily basis after resistance training on muscle hypertrophy and strength. Twelve males and 6 females (approximately 24 years of age) trained their right and left biceps on alternate days (6 sets of 4-10 repetitions), 5 d x week(-1), for 6 weeks. In a counter-balanced, double-blind design, they were randomized to receive 400 mg x d(-1) ibuprofen immediately after training their left or right arm, and a placebo after training the opposite arm the following day. Before- and after-training muscle thickness of both biceps was measured using ultrasound and 1 repetition maximum (1 RM) arm curl strength was determined on both arms. Subjects rated their muscle soreness daily. There were time main effects for muscle thickness and strength (p < 0.01). Ibuprofen consumption had no effect on muscle hypertrophy (muscle thickness of biceps for arm receiving ibuprofen: pre 3.63 +/- 0.14, post 3.92 +/- 0.15 cm; and placebo: pre 3.62 +/- 0.15, post 3.90 +/- 0.15 cm) and strength (1 RM of arm receiving ibuprofen: pre 18.6 +/- 2.8, post 23.4 +/- 3.5 kg; and placebo: pre 18.8 +/- 2.8, post 22.8 +/- 3.4 kg). Muscle soreness was elevated during the first week of training only, but was not different between the ibuprofen and placebo arm. We conclude that a moderate dose of ibuprofen ingested after repeated resistance training sessions does not impair muscle hypertrophy or strength and does not affect ratings of muscle soreness.
German genitive attributes are usually tagged as such in treebanks. However, it is well known that this information is not sufficient for determining the type of relation between head nouns and attributes, as genitive attributes can express many different semantic relations. Various linguistic classifications have been worked out, but to my knowledge, nobody has so far proposed to apply this linguistic knowledge to a corpus. The challenge here is to come up with a classification that is both easy to verify and sufficiently fine-grained. Using earlier linguistic approaches as guidelines, I propose in this paper a detailed annotation scheme for German genitive attributes based on readily identifiable noun features. First insights from its application to the Smultron Treebank show that it is easy to distinguish between the proposed classes and that my classification of genitive attributes can be related to a more general semantic annotation level.