Papers reviewed and determined not to be word norm studies. Use the flag icon to report errors or suggest re-inclusion.
18625 papers
We exploit the resources in the Arabic Treebank (ATB) for the novel task of automatically creating lexical semantic verb classes for Modern Standard Arabic (MSA). Verbs are clustered into groups that share semantic elements of meaning as they exhibit similar syntactic behavior. The results of the clustering experiments are compared with a gold standard set of classes, which is approximated by using the noisy English translations provided in the ATB to create Levin-like classes for MSA. The quality of the clusters is found to be sensitive to the inclusion of information about lexical heads of the constituents in the syntactic frames, as well as parameters of the clustering algorithm. The best set of parameters yields an Fβ=1 score of 0.501, compared to a random baseline with an Fβ=1 score of 0.37.
TransBooster is a wrapper technology designed to improve the performance of wide-coverage machine translation \nsystems. Using linguistically motivated syntactic information, it automatically decomposes source language sentences into shorter and syntactically simpler chunks, and recomposes their translation to form target language sentences. This generally improves both the word order \nand lexical selection of the translation. To date, TransBooster has been successfully applied to rule-based MT, statistical MT, and multi-engine MT. This paper presents \nthe application of TransBooster to Example-Based Machine Translation. In an experiment conducted on test sets \nextracted from Europarl and the Penn II Treebank we show that our method can raise the BLEU score up to 3.8% relative \nto the EBMT baseline. We also conduct a manual evaluation, showing that TransBooster-enhanced EBMT produces \na better output in terms of fluency than the baseline EBMT in 55% of the cases and in terms of accuracy in 53% of the \ncases.
We report on a series of experiments with probabilistic context-free grammars predicting English and German syllable structure. The treebank-trained grammars are evaluated on a syllabification task. The grammar used by As she evaluates the grammar only for German, we reimplement the grammar and experiment with additional phonotactic features. Using bi-grams within the syllable, we can model the dependency from the previous consonant in the onset and coda. A 10fold cross validation procedure shows that syllabification can be improved by incorporating this type of phonotactic knowledge. Compared to the grammar of Mller (2002), syllable boundary accuracy increases from 95.8% to 97.2% for English, and from 95.9% to 97.2% for German. Moreover, our experiments with different syllable structures point out that there are dependencies between the onset on the nucleus for German but not for English. The analysis of one of our phonotactic grammars shows that interesting phonotactic constraints are learned. For instance, unvoiced consonants are the most likely first consonants and liquids and glides are preferred as second consonants in two-consonantal onsets.
Based on text chunking using HMM, transformation-based learning is made use of to improve the precision of chunk tags further. The training data and the test data are from Penn treebank 4.0, and 13 text chunks are used. Rules are learned automatically according to the rule templates. The precision is improved 4.48%. The detailed analysis that affects the text chunking is given. Different threshold, different scale of training data, different learning equation and different rule templates can affect the precision of the text chunking.
Unlexicalized probabilistic context-free parsing is a general and flexible approach that sometimes reaches competitive results in multilingual dependency parsing even if a minimum of language-specific information is supplied. Furthermore, integrating parser results (good at long dependencies) and tagger results (good at short range dependencies, and more easily adaptable to treebank peculiarities) gives competitive results in all languages.
ABSTRACT. We investigated the efficacy of beam search parsing and deep parsing techniques in probabilistic HPSG parsing. We first tested the beam thresholding and iterative parsing. Next, we tested three techniques originally developed for deep parsing: quick check, large constituent inhibition, and hybrid parsing with a CFG chunk parser. The quick check, iterative parsing and hybrid parsing greatly contributed to total parsing performance. The accuracy and average parsing time for the Penn treebank were 87.2 % and 355 ms. Finally, we tested robustness and scalability of HPSG parsing on the MEDLINE corpus consisting of around 1.4 billion words. The entire corpus was parsed in 9 days with 340 CPUs. RÉSUMÉ. Nous avons étudié l’efficacité de l’analyse de beam search et des techniques de l’analyse profonde dans le probabiliste HPSG analyse. D’abord, nous avons examiné le beam thresholding et l’analyse itérative. Ensuite, nous avons examiné trois techniques développées originalement pour l’analyse profonde: quick check, large constituent inhibition, et l’analyse hybride avec la CFG chunk parser. Le quick check, l’analyse itérative et l’analyse hybride contribuaient considérablement à la performance de l’analyse totale. L’exactitude et le temps d’analyse moyen pour le Penn Treebank étaient 87.2 % et 355ms. Finalement, nous avons examiné la robustesse et la extensibilité de HPSG analyse sur le corpus de MEDLINE contenant presque 1.4 milliard de mots. Le corpus entier a été analysé en 9 jours avec 340 CPUs.
We present an improved approach for learning dependency parsers from tree-bank data. Our technique is based on two ideas for improving large margin training in the context of dependency parsing. First, we incorporate local constraints that enforce the correctness of each individual link, rather than just scoring the global parse tree. Second, to cope with sparse data, we smooth the lexical parameters according to their underlying word similarities using Laplacian Regularization. To demonstrate the benefits of our approach, we consider the problem of parsing Chinese treebank data using only lexical features, that is, without part-of-speech tags or grammatical categories. We achieve state of the art performance, improving upon current large margin approaches.
In this paper, we construct a biomedical semantic role labeling (SRL) system that can be used to facilitate relation extraction. First, we construct a proposition bank on top of the popular biomedical GENIA treebank following the PropBank annotation scheme. We only annotate the predicate-argument structures (PAS's) of thirty frequently used biomedical predicates and their corresponding arguments. Second, we use our proposition bank to train a biomedical SRL system, which uses a maximum entropy (ME) model. Thirdly, we automatically generate argument-type templates which can be used to improve classification of biomedical argument types. Our experimental results show that a newswire SRL system that achieves an F-score of 86.29% in the newswire domain can maintain an F-score of 64.64% when ported to the biomedical domain. By using our annotated biomedical corpus, we can increase that F-score by 22.9%. Adding automatically generated template features further increases overall F-score by 0.47% and adjunct arguments (AM) F-score by 1.57%, respectively.
Resolving pronominal anaphors in English has been a focus of research in natural language processing for decades. Methods ranging from linguistics-oriented, rule-based approaches to data-oriented, machine-learning approaches have been applied to the problem of finding the antecedents of pronouns. In contrast to the abundance of research in English, there is almost no work on the problem in Chinese. This thesis addresses that gap. Both a rule-based and a machine-learning anaphora resolution approach are presented in this work. An important difference between Chinese and English is that Chinese, unlike English, is a pro-drop language, and has null (zero) pronouns. The rule-based approach is applied to resolving these null pronouns as well as to the overt, third-person pronouns. The Hobbs algorithm is used for the rule-based method of anaphora resolution. Three versions of the algorithm are presented. The first uses only syntactic structure to select an antecedent. The second uses limited number and gender agreement, while the third incorporates semantic constraints on the proposed antecedents. For the machine-learning method, maximum entropy, supervised machine-learning models are used. Different models were trained using sets of features that paralleled the information sources used by the different versions of the Hobbs algorithm. Two sets of data were used. The Penn Chinese Treebank provided the test data for resolution of both overt, third-person pronouns and of zero pronouns. The CTB parses were annotated for coreference using guidelines that were drawn up for the work presented here. Data annotated for the 2004 Chinese ACE program were used for training and testing the maximum entropy models to find the antecedents for overt, third-person pronouns. The results from experiments with the two basic methods using the different levels of linguistic information will be presented and discussed.
EDBL (Euskararen Datu-Base Lexikala) is a general-purpose lexical database used in Basque text-processing tasks. It is a large repository of lexical knowledge (currently around 80,000 entries) that acts as basis and support in a number of different NLP tasks, thus providing lexical information for several language tools: morphological analysis, spell checking and correction, lemmatization and tagging, syntactic analysis, and so on. It has been designed to be neutral in relation to the different linguistic formalisms, and flexible and open enough to accept new types of information. A browser-based user interface makes the job of consulting the database, correcting and updating entries, adding new ones, etc. easy to the lexicographer.
Existing mechanisms for concept discovery tend to pick up all possible relationships between terms in a document based on roles of terms identified. The proposed work aims to enhance this discovery process by employing machine learning and semantic modelling. We explore a framework for automatically discovering labeled clusters from a large collection of documents. The aim of this framework is to enable the extraction of concepts and to structure these into labeled concepts for use by text processing applications such as text summarization and text categorization. We have developed a mechanism for automatically inducing a set of words that captures the meaning of a collection of documents. The WordNet lexical database is used to extract root meanings and to determine relationships amongst these terms
This study examined whether the presence of a label and the length of viewing time affect the perception of art. Participants were 152 undergraduate students at an urban university in central New Jersey. A computer program randomly assigned participants to viewing 4 paintings under a label or no label condition and a 1-s, 5-s, 30-s, or 60-s time condition. The paintings were Cezanne's Still Life With Apples, Mondrian's Composition with Red, Yellow and Blue, Monet's Garden at Sainte-Adresse, and Davis' Report from Rockport. After viewing each painting, participants completed a rating scale of 24 adjective pairs. Multivariate analyses of variance indicated little support for the hypotheses that the label condition will lead to different ratings of the art as compared to the non-label condition and that length of viewing time will affect ratings of the art. The reliability coefficients for the rating scale were fairly strong. Results are discussed in terms of how ratings of art are dependent largely on the work of art itself.
In this paper, we present a novel approach to combine the outputs of multiple MT engines into a consensus translation. In contrast to previous Multi-Engine Machine \nTranslation (MEMT) techniques, we do not rely on word alignments of output hypotheses, but prepare the input sentence for multi-engine processing. We do this by using a recursive decomposition algorithm that produces simple chunks as input to the MT engines. A consensus translation \nis produced by combining the best chunk translations, selected through majority voting, a trigram language model \nscore and a confidence score assigned to each MT engine. We report statistically significant relative improvements \nof up to 9% BLEU score in experiments (English→Spanish) carried out on an 800-sentence test set extracted from the Penn-II Treebank.
BACKGROUND: The Bethesda System (TBS) along with its companion atlas was updated in 2001 to improve standardization, clarity, and reproducibility of cervical cytology reporting. METHODS: The authors used a novel web-based format to compare assessments of 77 images demonstrating a range of classical and borderline cytologic changes by a self-selected group of United States cytotechnologists (n = 216) and pathologists (n = 185). RESULTS: Participants were highly experienced, with 71.2% of cytotechnologists and 53.0% of pathologists reporting >10 years of practice. The mean percentage of exact agreement with the panel was slightly though significantly higher for cytotechnologists (57.0%) compared with pathologists (53.4%), adjusted for experience (P =.004); cervical cytology percentage effort (P =.0005); or cervical accession volume (P =.0002). Compared with the TBS panel, exact agreement was achieved for 55.1% of image ratings compared with 82.3% agreement at the level of Negative vs non-Negative for images with a single-panel interpretation. Agreement with the panel was highest for images classified as Low-Grade Squamous Intraepithelial Lesion and lowest for Atypical Squamous Cells qualified as either of Undetermined Significance or Cannot Exclude a High-Grade Squamous Intraepithelial Lesion. Reviewers were less sensitive in identifying high-grade glandular lesions than they were in identifying high-grade squamous lesions at any threshold (P <.001). CONCLUSIONS: Morphologic appearances of images were more important determinants than participants' academic or professional degrees with regard to interobserver reproducibility in classifying cervical cytology images. Experienced cytotechnologists and pathologists performed similarly. Participants achieved higher sensitivity for identifying high-grade squamous lesions than they did for high-grade glandular lesions. These findings demonstrated that web-based studies may be useful in assessing interobserver agreement in classifying images.
A grammatical method of combining two kinds of speech repair cues is presented. One cue, prosodic disjuncture, is detected by a decision tree-based ensemble classifier that uses acoustic cues to identify where normal prosody seems to be interrupted (Lickley, 1996). The other cue, syntactic parallelism, codifies the expectation that repairs continue a syntactic category that was left unfinished in the reparandum (Levelt, 1983). The two cues are combined in a Treebank PCFG whose states are split using a few simple tree transformations. Parsing performance on the Switchboard and Fisher corpora suggests that these two cues help to locate speech repairs in a synergistic way.
Grammars can be induced from treebanks for a potential variety (e.g., parsing), but this task faces two major problems. One is the existence of annotation er-rors in the treebank which can affect the final system performance (cf. [4]). The other is that the sheer number of rules is overwhelming for most applications. As
In this work, we apply statistical learning algorithms to Lexicalized Tree Adjoining Grammar (LTAG) parsing, as an effort toward statistical analysis over deep structures. LTAG parsing is a well known hard problem. Statistical methods successfully applied to LTAG parsing could also be used in many other structure prediction problems in NLP. For the purpose of achieving accurate and efficient LTAG parsing, we will investigate two aspects of the problem, the data structure and the algorithm. 1. We introduce LTAG-spinal, a variant of LTAG with very desirable linguistic, computational and statistical properties. It can be shown that LTAG-spinal with adjunction constraints is weakly equivalent to the traditional LTAG. For the purpose of statistical processing, we extract an LTAG-spinal treebank from the Penn Treebank with Propbank annotation. 2. We not only explore various parsing strategies, but also investigate the reranking approach. (a) We first propose a left-to-right incremental parser for LTAG-spinal, as an attempt to dynamically incorporate supertagging and dependency analysis. A perceptron like discriminative learning algorithm is used for training. We further investigate a bidirectional dependency parser for LTAG-spinal, in order to overcome the limitation of left-to-right processing. We propose a novel algorithm for graph-based incremental construction, and apply this algorithm to LTAG style dependency parsing. (b) We also explore learning algorithms for parse reranking, as well as other NLP problems, e.g. Machine Translation. We propose a novel reranking strategy, Ordinal Regression with Uneven Margins (ORUM), which achieves state-of-the-art performance on parse reranking for CFG parsing and MT reranking. To sum up, we have accomplished the following achievements. (i) A new formalism, LTAG-spinal, which is weakly equivalent to LTAG. (ii) An LTAG-spinal Treebank extracted from the PTB with the Propbank annotation. (iii) A left-to-right incremental parser for LTAG-spinal. (iv) A bidirectional LTAG-spinal dependency parser. (v) A novel graph-based incremental construction algorithm, which could be applied to many structure prediction problem in NLP, e.g. semantic role labeling. (vi) A novel discriminative reranking algorithm, ORUM, which has been successfully applied to parse reranking as well as other tasks, e.g. MT reranking.
Abstract The aim of this study was to examine associations between children's temperament, parent–child goodness-of-fit, and the emotional content of parent–child conversations about past events. Fifty one New Zealand 5- and 6-year-old children and their parents discussed 4 emotional past events. Parents rated children's temperament along 15 dimensions associated with effortful control, extroversion, and negative affect. Parents then rated their own expectations of children's temperament, from which parent–child goodness-of-fit was assessed. Children rated as higher in effortful control were involved in more emotional past-event conversations. Children whose negative affect ratings corresponded more closely with parental expectations were also involved in more emotional conversations. Our findings provide preliminary support for an association between temperament and narrative content.
AIM: (i) To determine the ability of general practitioners (GPs) and paediatricians to correctly identify children as overweight or obese by visual cues alone; (ii) to describe the current management practices of overweight and obese children by these practitioners; and (iii) to compare these with National Health and Medical Research Council (NHMRC) Clinical Practice Guidelines. METHODS: Forty-four GPs and 29 paediatricians participated in the study. Respondents completed a questionnaire based on a series of body images, rating the size of the child as acceptable weight, overweight or obese and indicating the likelihood of carrying out a series of management options. RESULTS: There was considerable variation in ability to rate images correctly with the total number of correct responses being 72% and 68%, respectively, for GPs and paediatricians. There were statistically significant differences in management between GPs and paediatricians in terms of conducting appropriate anthropometry and screening for co-morbidities, with paediatricians performing closer to the NHMRC Clinical Practice Guidelines. CONCLUSION: GPs and paediatricians have the opportunity to screen children for overweight and obesity during their everyday practice. Accurate determination of weight status cannot be performed by visualisation alone and all children should have height and weight measured and correctly interpreted. Some areas of current GP and paediatrician management of overweight and obese children fall short of the NHMRC clinical guidelines and areas for improvement are highlighted in this paper.
In this paper, we present a system which can extract syntactic feature structures from a Korean Treebank (Sejong Treebank) to develop a Feature-based Lexicalized
In this paper, we present an alternative approach to the problem of contextual relevance feedback in web-based information retrieval. Our approach utilises a rich contextual model that exploits a user's implicit and explicit data. Each user's implicit data are gathered from their Internet search histories on their local machine. The user's explicit data are captured from a lexical database, a shared contextual knowledge base and domain-specific concepts using data mining techniques and a relevance feedback approach. This data is later used by our approach to modify queries to more accurately reflect the user's interests as well as to continually build the user's contextual profile and a shared contextual knowledge base. Finally, the approach retrieves personalised or contextual search results from the search engine using the modified/expanded query. Preliminary experiments indicate that our approach has the potential to not only aid in the contextual relevance feedback but also contribute towards the long term goal of intelligent relevance feedback in web-based information retrieval.
The trees in the Penn Treebank have a standard representation that involves complete balanced bracketing. In this article, an alternative for this standard representation of the tree bank is proposed. The proposed representation for the trees is loss-less, but it reduces the total number of brackets by 28%. This is possible by omitting the redundant pairs of special brackets that encode initial and final embedding, using a technique proposed by Krauwer and des Tombe (1981). In terms of the paired brackets, the maximum nesting depth in sentences decreases by 78%. The 99.9% coverage is achieved with only five non-top levels of paired brackets. The observed shallowness of the reduced bracketing suggests that finite-state based methods for parsing and searching could be a feasible option for tree bank processing.
The correct attachment of prepositional phrases (PPs) is a central disambiguation problem in parsing natural languages. This paper compares the baseline situation in English, German and Swedish based on manual PP attachments in various treebanks for these languages. We argue that cross-language comparisons of the disambiguation results in previous research is impossible because of the different selection procedures when building the training and test sets. We perform uniform treebank queries and show that English has the highest noun attachment rate followed by Swedish and German. We also show that the high rate in English is dominated by the preposition of. From our study we derive a list of criteria for profiling data sets for PP attachment experiments.
This paper explores several important issues in developing syntactically annotated Korean corpora for higher-level language processing, including semantic-discourse parsing, question-answering, machine translation, information retrieval, etc.In particular, we compare the Penn Korean Treebank (PKT) and the Korean Treebank of the 21st Century Sejong Project (ST) and discuss four critical issues in syntactic annotation.We argue for the use of more sophisticated morphosyntactic information, and based on our comparative study, we propose revisions in the syntactic annotation schemes of the existing Korean Treebanks in order to improve the quality of annotated corpora and their usability both for conducting theoretical research and for developing computational tools.The results of our comparative study reveal four significant issues in syntactic annotations: the syntactic analysis of verbal complexes, the hierarchical structure of noun phrases, the representation of traces, and the marking of zero elements.These factors may trigger erroneous syntactic representations for certain linguistic phenomena, and they may increase difficulties in data search and lessen reliability in computational processing.Thus, evaluating and improving the syntactic annotation of Treebanks is an important task for aspects of both theoretical and computational linguistics.
We present the Heart of Gold middleware by demonstrating three XML-based integration scenarios where multi-dimensional markup produced online by multilingual natural language processing (NLP) components is combined to deliver rich, robust linguistic markup for use in NLP-based applications like information extraction, question answering and semantic web. The scenarios include (1) robust deep-shallow integration, (2) shallow processing cascades, and (3) treebank storage of multi-dimensionally annotated texts.
In recent years, research in parsing has extended in several new directions. One of these directions is concerned with parsing languages other than English. Treebanks have become available for many European languages, but also for Arabic, Chinese, or Japanese. However, it was shown that parsing results on these treebanks depend on the types of treebank annotations used [, ]. Another direction in parsing research is the development of dependency parsers. Dependency parsing profits from the non-hierarchical nature of dependency relations, thus lexical information can be included in the parsing process in a much more natural way. Especially machine learning based approaches are very successful (cf. e.g. [12, 13]). The results achieved by these dependency parsers are very competitive although comparisons are difficult because of the differences in annotation. For English, the Penn Treebank [11] has been converted to dependencies. For this version, Nivre et al. [14] report an accuracy rate of 86.3%, as compared to an F-score of 2.1 for Charniak’s parser [1]. The Penn Chinese Treebank [1 ] is also available in a constituent and a dependency representations. The best results reported for parsing experiments with this treebank give an F-score of 81.8 for the constituent version [2] and. % accuracy for the dependency version [14]. The general trend in comparisons between constituent and dependency parsers is that the dependency parser performs slightly worse than the constituent parser. The only exception occurs for German, where F-scores for constituent plus grammatical function parses range between 51.4 and 5.3, depending on the treebank, NEGRA [1 ] or TuBa-D/Z [1 ]. The dependency parser based on a converted version of Tuba-D/Z, in contrast, reached an accuracy of 3.4% [14], i.e. 12 percent points better than the best constituent analysis including grammatical functions.
Transforming syntactic representations in order to improve parsing accuracy has been exploited successfully in statistical parsing systems using constituency-based representations. In this paper, we show that similar transformations can give substantial improvements also in data-driven dependency parsing. Experiments on the Prague Dependency Treebank show that systematic transformations of coordinate structures and verb groups result in a 10% error reduction for a deterministic data-driven dependency parser. Combining these transformations with previously proposed techniques for recovering non-projective dependencies leads to state-of-the-art accuracy for the given data set.
The main purpose of this study was to compare the validity of two methodologies in measuring the change of a destination image resulting from a small-scale community festival. One method compared same respondents’ rating of image attributes during and after their event participation, while the other method asked respondents to directly report their image change, and chose which factors contributed to the change. Interestingly, the two separate measures employed within this study provided contrasting information on how the festival impacted the image of the host community. The more subjective method indicated that the vast majority (77.9%) of respondents felt that the festival improved their image of the hosting community, while the more objective measure identified decreased image ratings between on-site and mail-back measurement periods. Potential reasons of the conflicting results are proposed and implications of the findings are discussed.
Approximately 60 kinds of lexical relations have been recognized in languages of the world (Grimes & Grimes, 1993). In this paper, I present evidence for a wide range of lexical relations in the Ilokano language. Grimes explains the meaning of lexical relations in terms of the way two words are related but differ in meaning, giving examples such as write and writer, row and rower. I will exemplify some of the types of lexical relations attested in Ilokano: 1) Verbs with an incorporated nominal, e.g. ag-diram'os 'to wash one's face' where the implied noun is 'face'; aginnaw 'wash dishes', implied noun, 'dishes'. There is no word for 'face' in agdiram'os, nor word for 'dishes' in aginnaw. 2) Derived nouns expressing an agentive relation, e.g. from the verb agsugal 'to gamble' the derived noun is mannugal 'gambler', agsurat 'to write', mannurat 'writer'. 3) Reduplication of a noun describing a condition of that noun, e.g. saka 'foot', saka-saka 'barefoot'; ima 'hand', ima-ima 'emptyhanded'. 4) Derived verbs denoting animal vocalization, e.g. aso 'dog', agtaol (phonation) 'to bark', ul'ul'ol (onomatopoeia); 5) Derived verbs denoting a quantum, e.g. sangalilig a sua 'one section of a pomelo'; 6) Complements, e.g. biag ken patay 'life and death'; 7) Derived verbs denoting function, e.g. karayan 'river', agayos 'to flow', sabong flower', agukrad 'to bloom'. I will then show how these derivations are handled in the Ilokano Lexical Database where they are listed making use of the band format.
We present the state of the art of a computational platform for the analysis of classical Sanskrit. The platform comprises modules for phonology, morphology, segmentation and shallow syntax analysis, organized around a structured lexical database. It relies on the Zen toolkit for finite state automata and transducers, which provides data structures and algorithms for the modular construction and execution of finite state machines, in a functional framework.
This paper is concerned with Esperanto, the only planned language system that has managed the successful transition from the status of a mere project to a full-fledged language. This is partly due to linguostructural properties, but above all to extralinguistic factors. Esperanto has found a sufficiently diverse and productive speech community which guarantees the constant and sustained dissemination of the language. This paper describes Esperanto as a planned language of the autonomous a posteriori subgroup. Its linguistic norm, which is documented in the Fundamento de Esperanto (1905), has developed steadily and become stable. It is supervised by the Akademio de Esperanto. Self-regulation takes place in a field of tension between diversifying forces (e.g. different linguistic and cultural influences because of the speakers' native backgrounds) and unifying forces (e.g. application during international meetings, literature, and radio programs). Its productive and flexible word formation system and syntax make Esperanto a means of communication with high expressive quality and stylistic variation. The main reason for the ease of Esperanto communication, however, is its democratic character: the lack of a native speaker whose competence decides on the language standard facilitates symmetrical communication.
In this paper, we describe an empirical study of Chinese chunking on a corpus, which is extracted from UPENN Chinese Treebank-4 (CTB4). First, we compare the performance of the state-of-the-art machine learning models. Then we propose two approaches in order to improve the performance of Chinese chunking. 1) We propose an approach to resolve the special problems of Chinese chunking. This approach extends the chunk tags for every problem by a tag-extension function. 2) We propose two novel voting methods based on the characteristics of chunking task. Compared with traditional voting methods, the proposed voting methods consider long distance information. The experimental results show that the SVMs model outperforms the other models and that our proposed approaches can improve performance significantly.
We examined the effects of mood and the content (a priori valence and involvement) and formal (presentation modality: text vs. video) characteristics of messages presented on a small screen on emotional responses and involvement among 47 young adults. Mood was induced by autobiographical memories varying in affective valence and arousal. Facial electromyography (EMG) and cardiac interbeat intervals were used as physiological indexes of valence and arousal. Both mood and the emotional tone of a message exerted an independent influence on the emotional response to the message. A strong valence-related mood-congruency effect emerged in predicting involvement. The text modality elicited higher involvement, arousal ratings, and orbicularis oculi EMG activity compared to the video modality when in a depressed mood, whereas the reverse was true when in a joyful, relaxed, or fearful mood. The results point to the possibility of mood-adapted media services.
This paper investigates the complexity of dependencies at the discourse level, in particular the dependencies between discourse connectives and their argu-ments. Our study is based on data from the Penn Discourse Treebank (PDTB) and is therefore an exploration into the ways treebanks can inform linguistic issues. We observe that, unlike in syntax, there is more uncertainty and flex-ibility with regards to the location and extent of discourse arguments. This leads to a variety of possible patterns of dependencies between pairs of dis-course relations, including nested, crossed and a range of other non-tree-like configurations. Nevertheless, our main conclusion is that the types of dis-course dependencies are highly restricted since the more complex cases can be factored out by appealing to discourse notions like anaphora and attribu-tion. We conjecture that the complexity of dependencies is far more restricted at the discourse level as compared to the syntactic level. 1
Most of the work on treebank-based statistical parsing exclusively uses the Wall-Street-Journal part of the Penn treebank for evaluation purposes. Due to the presence of this quasi-standard, the question of to which degree parsing results depend on the properties of treebanks was often ignored. In this paper, we use two similar German treebanks, TüBa-D/Z and NeGra, and investigate the role that different annotation decisions play for parsing. For these purposes, we approximate the two treebanks by gradually taking out or inserting the corresponding annotation components and test the performance of a standard PCFG parser on all treebank versions. Our results give an indication of which structures are favorable for parsing and which ones are not.
We present a novel PCFG-based architecture for robust probabilistic generation based on wide-coverage LFG approximations (Cahill et al., 2004) automatically extracted from treebanks, maximising the probability of a tree given an f-structure. We evaluate our approach using string-based evaluation. We currently achieve coverage of 95.26%, a BLEU score of 0.7227 and string accuracy of 0.7476 on the Penn-II WSJ Section 23 sentences of length ≤20.
We describe experiments in parsing the German TIGER Treebank. In parsing the complete treebank, 86.44 % of the sentences receive full parses; 13.56 % receive fragment parses. We discuss the methods used to enhance coverage and parsing quality and we present an evaluation on a gold standard, to our knowledge the first one for a deep grammar of German. Considering the selection performed by our current version of a stochastic disambiguation component, we achieve an f-score of 84.2%, the upper and lower bounds being 87.4% and 82.3 % respectively. 1.
Abstract Understanding and modeling human experience and emotional response when listening to music are important for better understanding of the stylistic choices in musical composition. In this work, we explore the relation of audio signal structure to human perceptual and emotional reactions. Memory, repetition, and anticipatory structure have been suggested as some of the major factors in music that might influence and possibly shape these responses. The audio analysis was conducted on two recordings of an extended contemporary musical composition by one of the authors. Signal properties were analyzed using statistical analyses of signal similarities over time and information theoretic measures of signal redundancy. They were then compared to Familiarity Rating and Emotional Force profiles, as recorded continually by listeners hearing the two versions of the piece in a live‐concert setting. The analysis shows strong evidence that signal properties and human reactions are related, suggesting applications of these techniques to music understanding and music information‐retrieval systems.
Impaired emotional functioning in schizophrenia is a prominent clinical feature that manifests primarily as flat affect. Studies have examined the perception, experience, and expression of emotions in schizophrenia and reported normal ratings of experience but impaired affect identification. However, the relation between flat affect and performance on facial affect identification and cognitive tasks has not been systematically examined in relation to premorbid adjustment and clinical outcome. We report a prospective study of 63 patients with at least moderate severity of flat affect and 99 patients without flat affect, who were compared on functional domains, emotion processing tasks, and neurocognitive measures. Flat affect was more common in men and was associated with poorer premorbid adjustment, worse current quality of life, and worse outcome at 1-year follow-up. Patients overall performed more poorly on emotion processing tasks, one that required identification of happy and sad emotions and one that required differentiating among intensities within these emotions. They responded inaccurately yet faster than controls for the intensity differentiation task, suggesting a decomposition of the normal relation between accuracy and speed. Flat affect ratings, compared with other negative symptoms, uniquely predicted performance on emotion processing tasks. Patients with flat affect showed greater impairment in both emotion processing tasks, with the most pronounced impairment for the intensity differentiation task. However, the 2 patient groups did not differ in the neurocognitive profile except for verbal memory. We conclude that flat affect is an important clinical feature of schizophrenia that exacerbates the course of illness.
We propose a bootstrapping approach to creating a phrase-level alignment over a sentence-aligned parallel corpus, reporting concrete treebank annotation work performed on a sample of sentence tuples from the Europarl corpus, currently for English, French, German, and Spanish. The manually annotated seed data will be used as the basis for automatically labelling the rest of the corpus. Some preliminary experiments addressing the bootstrapping aspects are presented. The representation format for syntactic correspondence across parallel text that we propose as the starting point for a process of successive refinement emphasizes correspondences of major constituents that realize semantic arguments or modifiers; language-particular details of morphosyntactic realization are intentionally left largely unlabelled. We believe this format is a good basis for training NLP tools for multilingual application contexts in which consistency across languages is more central than fine-grained details in specific languages (in particular, syntax-based statistical Machine Translation). 1.