Papers reviewed and determined not to be word norm studies. Use the flag icon to report errors or suggest re-inclusion.
16504 papers
Contrasting linguistic and nonlinguistic processing has been of interest to many researchers with different scientific, theoretical, or clinical questions. However, previous work on this type of comparative analysis and experimentation has been limited. In particular, little is known about the differences and similarities between the perceptual, cognitive, and neural processing of nonverbal environmental sounds and that of speech sounds. With the aim of contrasting verbal and nonverbal processing in the auditory modality, we developed a new on-line measure that can be administered to subjects from different clinical, neurological, or sociocultural groups. This is an on-line task of sound to picture matching, in which the sounds are either environmental sounds or their linguistic equivalents and which is controlled for potential task and item confounds across the two sound types. Here, we describe the design and development of our measure and report norming data for healthy subjects from two different adult age groups: younger adults (18–24 years of age) and older adults (54–78 years of age). We also outline other populations to which the test has been or is being administered. In addition to the results reported here, the test can be useful to other researchers who are interested in systematically contrasting verbal and nonverbal auditory processing in other populations.
This study compared four common methods for scoring a popular working memory span task, Daneman and Carpenter’s (1980) reading span test. More continuous measures, such as the total number of words recalled or the proportion of words per set averaged across all sets, were more normally distributed, had higher reliability, and had higher correlations with criterion measures (reading comprehension and Verbal SAT) than did traditional span scores that quantified the highest set size completed or the number of words in correct sets. Furthermore, creation of arbitrary groups (e.g., high-span and low-span groups) led to poor reliability and greatly reduced predictive power. It is recommended that researchers score span tasks with continuous measures and avoid post hoc dichotomization of working memory span groups.
Many of the available image databases have keyword annotations associated with the images. In spite of the availability of good quality low-level visual features that reflect well the physical content, image retrieval based on visual features alone is subject to semantic gap. Text annotations are related to image context or semantic interpretation of the visual content and are not necessarely directly linked to the visual appearance of the images. Keywords and visual features thus provide complementary information. Using both sources of information is an advantage in many applications and recent work in this area reflects this interest. In this paper, we address the challenge of semantic gap reduction using a hybrid visual and conceptual representation of the content within an active relevance feedback context. We introduce a new feature vector, based on the keyword annotations available for the images, which makes use of conceptual information extracted from an external lexical database, information represented by a set of "core concepts". Our experiments show that the use of the proposed hybrid conceptual and visual feature vector dramatically improves the quality of the relevance feedback results.
During the past few years, the information representation and retrieval sector in the area of Documentation and Biblioteconomy has had to assume the important repercussions of the Internet and its associated technologies, and in particular, the World Wide Web (WWW). Technological modifications arising from these important changes are leading to the gradual digitalisation of the information representation and retrieval sector, affecting information artefacts, representation and retrieval tools and user requirements.\nIn the light of this growing context of digitalisation, diverse information representation and retrieval tools exist, which must be studied in addition to diverse fields of knowledge in which these tools have originated: Linguistics, Artificial Intelligence, Documentation, Linguistic Engineering... Hence, in specialised literature, analyses are performed on information representation and retrieval tools, taxonomies, classification systems, computational lexicons, lexical databases, thesauruses, titles lists, knowledge bases, conceptual maps, ontologies, synonym rings and semantic networks, among others. Among this wide spectrum of information representation and retrieval tools are thesauruses and ontologies, which are most often linked in bibliography, even though they come from completely different disciplinary areas. However, the conceptualisation applied by authors to the terms "thesaurus" and "ontology" is quite diverse, and sometimes authors confuse, oppose, complement or overlap both these concepts.\nThe overall objective of the present article [1] is to establish the relationship between the concepts of thesaurus and ontology in the Documentation and Biblioteconomy field. Two specific objectives have been established for this purpose. Firstly, to make an analysis of the thesaurus-based concept with a view to defining its most important characteristics and to verify the similarities and differences it shares with ontologies. And secondly, to establish a definition for the ontology concept, also for the purpose of verifying its characteristics and analysing the similarities and differences it has with thesauruses.
Incremental parsing gains its importance in natural language processing and psycholinguistics because of its cognitive plausibility. Modeling the associated cognitive data structures, and their dynamics, can lead to a better understanding of the human parser. In earlier work, we have introduced a recursive neural network (RNN) capable of performing syntactic ambiguity resolution in incremental parsing. In this paper, we report a systematic analysis of the behavior of the network that allows us to gain important insights about the kind of information that is exploited to resolve different forms of ambiguity. In attachment ambiguities, in which a new phrase can be attached at more than one point in the syntactic left context, we found that learning from examples allows us to predict the location of the attachment point with high accuracy, while the discrimination amongst alternative syntactic structures with the same attachment point is slightly better than making a decision purely based on frequencies. We also introduce several new ideas to enhance the architectural design, obtaining significant improvements of prediction accuracy, up to 25% error reduction on the same dataset used in previous work. Finally, we report large scale experiments on the entire Wall Street Journal section of the Penn Treebank. The best prediction accuracy of the model on this large dataset is 87.6%, a relative error reduction larger than 50% compared to previous results.
Traditional Chinese text chunking approach is to identify phrases using only one model and same features. It is shown that one model couldn't comprise each phrase's characteristics, and same features are not suitable to all phrases, data sparseness also appears. Multi-agent strategy uses several model and sensitive features of each phrase to identify different phrases. This paper describes the multi-agent strategy applied in the identification of Chinese phrases whose main features are: 1) easy and quick communication between phrases; 2) avoidance of data sparseness. Through testing on Chinese Penn Treebank, F score of Chinese text chunking using multi-agent strategy achieves to 95.82%, which is higher than the best result that has been reported.
Most recent statistical parsers fall into one of two groups. The largest group consists of parsers which are based on some variation of a probabilistic context-free grammar, use joint probability models, and use tabular methods to find the most probable parse. Parsers in the second group are based on probabilistic push-down automata, use conditional probability models, and use some form of state-space search to find the most probable parse. This thesis is a study of natural language parsing as a control problem. This view leads to parsers of the second type. We show that search can be done very efficiently for such parsers. The control approach leads to a particular interpretation of the history-based parsing tradition, in which history is equated with state. The corresponding probability model is called a Markov parsing model, which can be used both for syntactic disambiguation and for search. The resulting parsers are simple, fast, have excellent coverage, and are reasonably accurate. Using treebanks (collections of text, which are expert-annotated with syntactic structure), we learn controllers for parsers that can be applied with little or no search. We call these greedy or nearly-greedy policies. Thus we are studying parsers which are constrained to operate efficiently.
We describe a history-based generative parsing model which uses a k-nearest neighbour (k-NN) technique to estimate the model's parameters. Taking the output of a base n-best parser we use our model to re-estimate the log probability of each parse tree in the n-best list for sentences from the Penn Wall Street Journal treebank. By further decomposing the local probability distributions of the base model, enriching the set of conditioning features used to estimate the model's parameters, and using k-NN as opposed to the Witten-Bell estimation of the base model, we achieve an f-score of 89.2%, representing a 4% relative decrease in f-score error over the 1-best output of the base parser.
We present a treebank conversion method by which we construct an RMRS bank for HPSG parser evaluation from the TIGER Dependency Bank. Our method effectively performs automatic RMRS semantics construction from functional dependencies, following the semantic algebra of (Copestake et al., 2001). We present the semantics construction mechanism, and focus on some special phenomena. Automatic conversion is followed by manual validation. First evaluation results yield high precision of the automatic semantics construction rules. 1
In this paper we discuss the application of semi-supervised machine learning method-co-training on Chinese Text Chunking. Firstly, we give the definition of Chinese chunk,then the formalized definition of co-training algorithm.We proposed a example selection method based on the consistence, using two classifiers: Transductive HMM and fnTBL to combine a classification system to perform the Chinese text chunking task with the small-scale labled Chinese treebank and large-scale unlabled Chinese corpus. The result were compared with the self-training result and the result of the non co-training experiment in which we only used the small-scale Chinese treebank as training data and use one classifier(Transductive HMM or fnTBL) to recognize the Chinese chunk. The improvement is significant, the F value of the two classifiers reached 83.41%,85.34%, get a improvement of 2.13 points and 7.21 points respectively.
As lexical databases have proliferated in multiple formats, there has been a growing concern over the reusability of lexical resources. The interchange and integration of data, as well as the development of common software is increasingly important to avoid duplications of effort and enable the development of large-scale databases of linguistic information. A unified approach for the development of tools to create and manage lexical databases is necessary. Their structure must follow some patterns based on some clearly delimited abstraction levels and the implementation must be controlled by sound and well-founded software engineering methods. Relational database technology is suitable for data support and to attain a greater flexibility, reusability and expandability. With such a methodology we have developed tools for the creation and management of monolingual dictionaries based on a Directed Acyclic Graph shaped conceptual taxonomy with a single relation where a category can have more than one parent. This is a new step in the way to develop tools for managing well structured lexical databases and with multiple semantic relations
This paper presents a Chinese parsing method which takes data-oriented parsing technique as the basic framework and utilizes the similarity-based probability estimate technique. Through the initial selection process, the fragment-combination forms of the input sentence are acquired on the constructed knowledge source including treebank, fragment-bank and fragment-combination-bank. Then by using the similarity-based probability estimate technique, the combination parsing process can be completed successfully. To prove the method efficiency, the knowledge source is constructed on the real-world Chinese corpus, and the other corpus is used as the test set. The experiment results show that every test parameter is satisfied.
To address the task of detecting nonischemic motion abnormalities from animated displays of gated myocardial perfusion single photon emission computed tomography data, we performed an observer study to evaluate the difference in detection performance between gating to 8 and 16 frames. Images were created from the NCAT mathematical phantom with a realistic heart simulating hypokinetic motion in the left lateral wall. Realistic noise-free projection data were simulated for both normal and defective hearts to obtain 16 frames for the cardiac cycle. Poisson noise was then simulated for each frame to create 50 realizations of each heart, All datasets were processed in two ways: reconstructed as a 16-frame set, and collapsed to 8 frames and reconstructed. Ten observers viewed the cardiac images animated with a realistic real-time frame rate. Observers trained on 100 images and tested on 100 images, rating their confidence on the presence of a motion defect on a continuous scale. None of the observers showed a significant difference in performance between the two gating methods. The 95% confidence interval on the difference in areas under the ROC curve (Az8 - Az16) was -0.029-0.085. Our test did not find a significant difference in detection performance between 8-frame gating and 16-frame gating. We conclude that, for the task of detecting abnormal motion, increasing the number of gated frames from 8 to 16 offers no apparent advantage.
This article considers approaches which rerank the output of an existing probabilistic parser. The base parser produces a set of candidate parses for each input sentence, with associated probabilities that define an initial ranking of these parses. A second model then attempts to improve upon this initial ranking, using additional features of the tree as evidence. The strength of our approach is that it allows a tree to be represented as an arbitrary set of features, without concerns about how these features interact or overlap and without the need to define a derivation or a generative model which takes these features into account. We introduce a new method for the reranking task, based on the boosting approach to ranking problems described in Freund et al. (1998). We apply the boosting method to parsing the Wall Street Journal treebank. The method combined the log-likelihood under a baseline model (that of Collins [1999]) with evidence from an additional 500,000 features over parse trees that were not included in the original model. The new model achieved 89.75% F-measure, a 13% relative decrease in F-measure error over the baseline model's score of 88.2%. The article also introduces a new algorithm for the boosting approach which takes advantage of the sparsity of the feature space in the parsing data. Experiments show significant efficiency gains for the new algorithm over the obvious implementation of the boosting approach. We argue that the method is an appealing alternative-in terms of both simplicity and efficiency-to work on feature selection methods within log-linear (maximum-entropy) models. Although the experiments in this article are on natural language parsing (NLP), the approach should be applicable to many other NLP problems which are naturally framed as ranking tasks, for example, speech recognition, machine translation, or natural language generation.
Considering the popularity of the Internet, an automatic interactive feedback system for e-learning websites is becoming increasingly desirable. However, there are still some problems for computers to understand the natural language, especially the Chinese language. First, because the Chinese language has no space to segment the lexical entry, its segmentation method is more difficult than that of English. Second, the lack of complete grammar for Chinese language makes parsing more difficult and complicated. Building an automatic Chinese feedback system for special application domains could solve these problems. In this paper, an interactive mechanism is proposed to parse, understand and response to a Chinese sentence. This mechanism utilizes a specific lexical database according to the particular application. In this way, a Chinese interactive feedback e-learning website is built for a special application domain that will choose the proper response in a user friendly, accurate and timely manner.
Previous systems that automatically tag text with FrameNet labels have been trained from the FrameNet example data, as there is no FrameNet annotated corpus. The FrameNet data is systematically biased by the criteria for the examples ’ selection, as annotators attempt to select simple sentences that include the target word. Instead of using the FrameNet examples, we train a maximum entropy model classifier to identify verb frames on text from the Penn Treebank. We use examples of verbs with only one entry in FrameNet as training data, and evaluate the system on human annotated text from the Wall Street Journal. We accurately identify the frame used by 76 % of finite verbs. We also investigate how well the system performs on verbs it has not encountered before. This task examines the feasibility of using the system to automatically extend the coverage of FrameNet by classifying verbs with no FrameNet entries. The classifier accurately assigns a frame to 55 % of instances of verbs it has not been trained on. 1
This paper presents a circumplex taxonomy of related consumer motives based on valence ratings of 34 preferred brand personality traits. Results of INDSCAL analysis reveal a consistent, replicable preferred brand personality structure across 11 different countries and four different product categories. As preferred brand personality dimensions are considered as behavioral expressions of underlying motives, the found structure was reformulated in terms of a taxonomy of eight fundamental consumer motives i.e. Vitality, Pleasure, Conviviality, Belonging, Security, Control, Recognition and Power, determined by two basic, bipolar dimensions i.e. Intrapersonal versus Interpersonal axis. The proposed taxonomy appears to overlap considerably with prior classifications of human motives. Opportunities in the context of consumer research are discussed, as well as some directions for future research.
In this article, I explore the ways in which ethnic identity is expressed by following the formulaic socio-linguistic norm, the very method of which defies the authenticity of identity itself, thereby asserting the identity's multi-facetedness as sustained in performative linguistic practice. I look at multi-sited socio-linguistic interactions among Koreans in Japan, who claim their primary identity to be that of North Korea's overseas citizens even though none of them have North Korean passport or nationality. Their identity, in other words, is based on ideological commitment, which is in reality supported by their ongoing linguistic practice. A close look at their socio-linguistic life reveals their ethnicity's dual or multiple ontology, which challenges among other things the currently dominant assertion of Japanese self in the western academic discourse.
Research on child language acquisition would benefit from the availability of a large body of syntactically parsed utterances between parents and children. We consider the problem of generating such a ``treebank'' from the CHILDES corpus, which currently contains primarily orthographically transcribed speech tagged for lexical category.
"They... Speak Better English Than the English Do":Colonialism and the Origins of National Linguistic Standardization in America Paul K. Longmore (bio) Recent scholarship has traced efforts to fashion an American national language through standardization of forms and usage. Christopher Looby, in Voicing America: Language, Literary Form, and the Origins of the United States, David Simpson, in The Politics of American English, 1776–1850, and Kenneth Cmiel, in Democratic Eloquence: The Fight Over Popular Speech in Nineteenth-Century America, all examine public debates about these matters and, in particular, the labors of linguistic reformers to shape the national tongue. But these important studies focus mainly on the revolutionary, early national, and antebellum periods, and although Cmiel recounts the impact of late eighteenth-century British prescriptivists on postrevolutionary American thinking he does not extensively consider colonial efforts to regulate the language.1 In fact, attempts to shape written and spoken American English according to ideas of correctness, propriety, and, most important, a national standard began before American Independence. But those ideas and that standard were British rather than American. The effort reflected colonial desire to copy metropolitan English linguistic norms in order to attain cultural legitimacy within the British Empire. Postrevolutionary exertions perpetuated attitudes and activities that began in the late colonial period. This essay examines the colonial origins of the movement to standardize and nationalize American English. The central fact of colonials' experience is that they act as agents of an expansionist imperial society. As one result, dominant colonial groups are acutely aware of the metropolitan standard of the language they share with the homeland. In developing an extraterritorial variety of that language, they often labor to match the metropolitan standard. Transplanted speakers of various dialects of a common tongue encounter one another in [End Page 279] new geographical and social environments. Contact often produces dialect mixing and leveling and a compromise dialect called a koine. Koineization largely involves unconscious modification of speech forms. But the attentiveness of many colonials to a metropolitan standard indicates that colonial koines arise from not just spontaneous changes but conscious shaping. As users of the koine "nativize" their common tongue, they continuously render normative judgments about alternative usages. Prescribing what is correct, they seek to standardize the extraterritorial version of the language (Siegel 8; Haas; Stein). North American British colonials, especially those in the elite and middling ranks, took as their model the written and spoken English of the imperial center. Like elite and middling Britons, higher-status colonials used this "proper" and "true" English to distinguish themselves from people below them in the social hierarchy. Nonetheless and again like socially ambitious Britons, many colonials wielded linguistic correctness as a tool of social mobility. Colonials of all ranks emulated metropolitan Standard English in order to elevate their standing within the Empire. In the long run in a pattern typical of colonies of settlement, their efforts unintentionally helped to create a common language that provided one basis for American nationhood. Colonials' adoption of the metropolitan standard of English and their manner of applying it appear in three kinds of evidence: contemporary observers' evaluations of colonial speech; higher-status colonials' descriptions of British immigrants' non-standard English speech; and colonials' formal efforts to educate themselves in metropolitan Standard English. Eighteenth-century observers praised Anglophone colonials for matching metropolitan linguistic norms. They focused on pronunciation and accent, vocabulary and phraseology. William Eddis, secretary to Maryland's royal governor (1769–1777), avowed, "[T]he pronunciation of the generality of the people has an accuracy and elegance that cannot fail of gratifying the most judicious ear" (33). Jonathan Boucher, a tutor and Anglican priest in the Chesapeake (1759–1775), asserted that colonials displayed "the purest Pronunciation of the English Tongue that is anywhere to be met with" (30). "Accuracy," "elegance," and "purity" referred to both colonials' emulation of metropolitan standard pronunciation and the absence from their speech of British regional accents. Lord Adam Gordon, [End Page 280] a Scot, made the same point about word usage and grammar. Describing mid-1760s Philadelphia, he admitted that "the propriety of Language here surprized me much, the English tongue being spoken by all ranks, in a degree of purity and perfection, surpassing...
The purpose of this paper is to automatically generate Chinese chunk bracketing by a bottom-to-top mapping (BTM) model with a BTM dataset. The BTM model is designed as a supporting model with parsers. We define a word-layer matrix to generate the BTM dataset from Chinese Treebank. Our model matches auto-learned patterns and templates against segmented and POS-tagged Chinese sentences. A sentence that can be matched with some patterns or templates is called a matching sentence. The experimental results have shown that the chunk bracketing of the BTM model on the matching sentences is high and stable. By applying the BTM model to the matching sentences and the Ngram model to the non-matching sentences, the experiment results show the F-measure of an N-gram model can be improved. 1
This paper presents a high performance method to identify English proper nouns (PNs) based on maximum entropy model (MaxEnt). Most traditional PNs recognition systems use lexical resources such as name list, as new names are constantly coming into existence, these are necessarily incomplete. Therefore machine learning methods are used to identify PNs automatically. In the framework of MaxEnt model, semantic and lexical information of surrounding words and word itself acting as atomic features comprises feature templates and forms feature without requiring extra expert knowledge. The test on WSJ of Penn Treebank II shows that this method guarantees high precision and recall, and at the same time it can reduce the quantity of features dramatically, downsize system space consumption, and decrease the time of training and testing, so as to improve the efficiency considerably. The method in this paper can be transformed to identify other specific noun easily because the principle of methods is universal.
Purpose: Strategy selection and effort allocation in cognitive tasks are often mediated by metacognitive assessments of self-performance (e.g., Nelson & Leonesio, 1988). The current experiment examined the accuracy and role of predictive metacognitive judgments in a real-world visual search task. Method: Procedure was modeled after the judgments-of-learning task (e.g., Dunlosky & Nelson, 1992) commonly used to study metacognitive accuracy and control. In a pair of experiments, subjects performed a simulated luggage x-ray screening task, searching for knives hidden among varying numbers of background objects in passenger bags. Before performing the search task, subjects viewed each stimulus image without the embedded target item and rated how likely they would be to find the knife if it were hidden somewhere in that image. Ratings were made on a 5-point Likert scale. Experiment 1 used a 2IFC procedure for the visual search task. Experiment 2 used a speeded response procedure. Results: Experiment 1 produced a statistically significant but weak correlation between predicted and observed target detection performance (mean Goodman-Kruskal gamma =.161), indicating that subjects' predictive metacognitive judgments were only modestly accurate. Experiment 2 found that target-present RTs were similar across levels of predicted detection likelihood, but that target-absent RTs were longer for stimulus images in which target detection was predicted to be difficult. Conclusions: Results suggest that predictive metacognitive judgments are only modestly accurate, but that the information used in metacognitive judgments is nonetheless used to regulate criterion for terminating search when no target is detected.
The structural theory of metaphor (STM) uses techniques from possible worlds semantics to generate and interpret metaphors. STM is presented in detail in The Logic of Metaphor: Analogous Parts of Possible Worlds (Steinhart, 2001). STM is based on Kittay’s semantic field theory of metaphor (1987) and ultimately on Black’s interactionist theory (1962, 1979). STM uses an intensional calculus to specify truth-conditions for many grammatical forms of metaphor. The truth-conditional analysis in STM is inspired in part by Miller (1979) and Hintikka & Sandu (1994). STM is by no means a toy theory. It has been successfully tested on dozens of large texts taken from real authors. Its methods can be applied in very large linguistic databases like WordNet or MindNet.
Norms may also be understood as social realization of correctness notions and linguistic norms as performance instructions. This article reports on a case study of the application of Toury' s norm theory, particularly his operative translation norms, in subtitle translation. The authors believe that is a norm-governed communicative activity between two or more languages, and that subtitle translation, governed by linguistic and textual norms, should seek invisibility of subtitling as the ultimate goal.
The aim of this paper is to present a lexical database of English collocations used in scientific language, which is being built in three Spanish universities (Barcelona, Illes Balears and Leon) and is mainly intended for the Spanish-speaking scientific community. The shortage of specialized dictionaries providing contextual information on the grammatical and collocational patterns in specific registers prompted the onset of this project. Our database is based on the analysis of a corpus of written texts in the areas of biology, biochemistry, and biomedicine, and provides the grammatical, semantic, and collocational information necessary for the correct and precise use of each term in scientific discourse. The paper describes the steps followed in the creation of the data base and it includes the case study of one of its entries.
Toempower thegeneral massthrough access toinformation andknowledge, organized efforts arebeing madetodevelop relevant content inlocallanguages andprovide local language capabilities toutility software. Wehavedeveloped a Question Answering (QA)System forHindidocuments that wouldberelevant formassesusingHindiasprimary language ofeducation. Theusershould beabletoaccess information fromE-learning documents ina userfriendly way,that isbyquestioning thesystem intheir native language Hindi andthesystem will return theintended answer (also in Hindi) bysearching incontext fromtherepository ofHindi documents. Thelanguage constructs, querystructure, commonwords, etc.arecompletely different inHindias compared toEnglish. A novelstrategy, inaddition to conventional search andNLP techniques, wasusedto construct theHindi QAsystem. Thefocus isoncontext based retrieval ofinformation. Forthis purpose weimplemented a Hindi search engine that works onlocality-based similarity heuristics toretrieve relevant passages fromthecollection. It alsoincorporates language analysis modules like stemmer andmorphological analyzer aswellasself constructed lexical database ofsynonyms. Theexperimental results over corpus oftwoimportant domains ofagriculture andscience showeffectiveness ofourapproach.
Believing in Louis Althusser's axiom that writing is a campaign against absence, Shahrokh Meskoob struggled, throughout his literary and intellectual life, against all manners of absence. His language was a most potent weapon in, and the clearest manifestation of, his struggles. Many adjectives have been used by literary critics to describe his linguistic style. Some have called it a literary creation of first order. Others have characterized it as no less than a miracle; a phenomenon that defies definition. Indeed, Meskoob's language has an existence and identity of its own, palpably independent of the meanings and ideas that it projects. One can claim that his language a gate to a town; but a gate that deserves to be observed and admired in its own right. Meskoob was forever preoccupied with form. In a sense he constantly strove to flesh out and delineate abstract and diffused concepts. He wanted to embody and encase the flow of water, the fleeting time and the unbounded nature. In Meskoob's language, one does not come across the allegories common to classical and even modern Persian literature since he does not want to present his inner experiences through the filter of common linguistic norms or constructs and thereby pare away their original zest and liveliness. The sheer beauty, elegance and power of Meskoobs language is not only the natural byproduct of his mastery of Persian classic literature and western modern culture. It is also the concrete manifestation of his deep fascination with the language itself. In his own words: Language is the panacea of life and antidote to death. Ferdowsi used it to construct a lofty edifice never to be felled by the ravages of time.
Translation tests are widely used for high school term tests and entrance examinations as well as university entrance examinations. Although a considerable number of papers point out the possibility of low reliability for scoring, little is known about the factors raters play in the reliability of scoring (Watanabe, 1994). This study examines how the professional backgrounds of raters affect rating criteria. The results indicated that novice raters tended to over-estimate examinees' comprehension whereas experienced raters were more likely to focus on the correctness of the Japanese sentence. In addition, it turned out that the difficulty of sentences affected the scoring of both experienced and novice raters. After administering a sorting task, the difficulty of the sentences showed that the perception of sentence difficulty did not correspond to the difficulty of examinees' translation. The paper closes by suggesting several pedagogical implications for administering translation tests. Of particular importance is that test developers should consider not only the complexity of sentence structures and vocabulary, but also the examinees' topic familiarity of the sentences to be translated.
Knowledge acquisition is always regarded as a bottleneck in many NLP tasks, such as machine translation, information extraction. Treebank-based statistical parsing is not an exceptant. The latent linguistic knowledge in treebank is very rich, which, however, cant be acquired directly.In our model, the following three ways are used to incorporate such rich linguistic features for Chinese statistical parsing. First of all, non-recursive noun and verb phrases are annotated in the Penn Chinese Treebank because of their strong mark of boundaries. Second, a new head percolation table is designed based on Xias table. The last linguistic feature our model uses is the context configuration frame which provides a stronger representation of bilexical dependency structures. All these three linguistic features gain an improvement of remarkable 2.37% in terms of F1 measure, 5.36% in terms of complete match ratio.
This paper proposes a new document representation method to text categorization. It applies category-based semantic field (CBSF) theory for text categorization to gain a more efficient representation of documents. The lexical chain is introduced to compute CBSF and Hownet* used as a lexical database. In particular, the title of each document functions as a clue to forecast the potential CBSF of the test document. Combined with classifier, this approach is examined in text categorization and the result indicates that it performs better than conventional methods with features chosen on the basis of bag-of-words (BOW) system, on the same task.
This is a presentation of the historical development of human-computer interfaces in educational computer science, which makes it necessary for Natural Language Processing to understand and interpret the learner”s interventions. It is also an analysis of Lexical Databases and their application in education.
This master’s thesis describes a deterministic dependency parser using a memorybased learning approach to parse unrestricted English text. A converter transforms the Wall Street Journal section of the Penn Treebank to an intermediate dependency representation which is used to train the parser using the TiMBL (Daelemans, Zavrel, Sloot, & Bosch, 2003) library. The output of the parser is labeled dependency graphs, using as arc labels a combination of bracket labels and grammatical role labels constructed from the Penn Treebank II annotation scheme (Marcus, Kim, et al., 1994). The parser reaches a maximum unlabeled attachment score of 87.1% and produces labeled dependency graphs with an accuracy of of 86.0% with the correct head and arc label recognised. The results are close to the state of the art in dependency parsing, and the parser also outputs arc labels that other parsers do not produce.
Most existing statistical surface realizers either make use of hand-crafted grammars to provide coverage or are tuned to specific applications. This paper describes an initial effort toward building a statistical surface realization model that provides both precision and coverage. We trained a Maximum Entropy model that given a predicate-argument semantic representation, predicts the surface form for realizing a semantic concept and the ordering of sibling semantic concepts and their parent, on the Penn TreeBank and Proposition Bank corpora. Initial results have shown that the precisions for predicting surface forms and orderings reached 80% and 90% respectively, on a held-out part of Penn TreeBank. We use the model to generate sentences from our domain representations. We are in the process of evaluating the model on a corpus collected for our in-car applications.
TextTrees, introduced in (Newman, 2005), are skeletal representations formed by systematically converting parser output trees into unlabeled indented strings with minimal bracketing. Files of TextTrees can be read rapidly to evaluate the results of parsing long documents, and are easily edited to allow limited-cost treebank development. This paper reviews the TextTree concept, and then describes the implementation of the almost parser- and grammar-independent TextTree generator, as well as auxiliary methods for producing parser review files and inputs to bracket scoring tools. The results of some limited experiments in TextTree usage are also provided.