1,721,020 research outputs found
Statistical Deep parsing for spanish
Full text linkThis document presents the development of a statistical HPSG parser for Spanish. HPSG is a deep linguistic formalism that combines syntactic and semanticinformation in the same representation, and is capable of elegantly modelingmany linguistic phenomena. Our research consists in the following steps: design of the HPSG grammar, construction of the corpus, implementation of theparsing algorithms, and evaluation of the parsers performance. We created a simple yet powerful HPSG grammar for Spanish that modelsmorphosyntactic information of words, syntactic combinatorial valence, and semantic argument structures in its lexical entries. The grammar uses thirteenvery broad rules for attaching specifiers, complements, modifiers, clitics, relative clauses and punctuation symbols, and for modeling coordinations. In asimplification from standard HPSG, the only type of long range dependency wemodel is the relative clause that modifies a noun phrase, and we use semanticrole labeling as our semantic representation. We transformed the Spanish AnCora corpus using a semi-automatic processand analyzed it using our grammar implementation, creating a Spanish HPSGcorpus of 517,237 words in 17,328 sentences (all of AnCora). We implemented several statistical parsing algorithms and trained them overthis corpus. The implemented strategies are: a bottom-up baseline using bi-lexical comparisons or a multilayer perceptron; a CKY approach that uses theresults of a supertagger; and a top-down approach that encodes word sequencesusing a LSTM network. We evaluated the performance of the implemented parsers and compared them with each other and against other existing Spanish parsers. Our LSTM top-down approach seems to be the best performing parser over our test data, obtaining the highest scores (compared to our strategies and also to externalparsers) according to constituency metrics (87.57 unlabeled F1, 82.06 labeled F1), dependency metrics (91.32 UAS, 88.96 LAS), and SRL (87.68 unlabeled,80.66 labeled), but we must take in consideration that the comparison against the external parsers might be noisy due to the post-processing we needed to do in order to adapt them to our format. We also defined a set of metrics to evaluate the identification of some particular language phenomena, and the LSTM top-down parser out performed the baselines in almost all of these metrics as well.Este documento presenta el desarrollo de un parser HPSG estadístico para el español. HPSG es un formalismo lingüístico profundo que combina información sintáctica y semántica en sus representaciones, y es capaz de modelar elegantemente una buena cantidad de fenómenos lingüísticos. Nuestra investigación se compone de los siguiente pasos: diseño de la gramática HPSG, construcción del corpus, implementación de los algoritmos de parsing y evaluación de la performance de los parsers. Diseñamos una gramática HPSG para el español simple y a la vez poderosa, que modela en sus entradas léxicas la información morfosintáctica de las palabras, la valencia combinatoria sintáctica y la estructura argumental semántica. La gramática utiliza trece reglas genéricas para adjuntar especificadores, complementos, clíticos, cláusulas relativas y símbolos de puntuación, y también para modelar coordinaciones. Como simplificación de la teoría HPSG estándar, el único tipo de dependencia de largo alcance que modelamos son las cláusulas relativas que modifican sintagmas nominales, y utilizamos etiquetado de roles semánticos como representación semántica. Transformamos el corpus AnCora en español utilizando un proceso semiautomático y lo analizamos mediante nuestra implementación de la gramática, para crear un corpus HPSG en español de 517,237 palabras en 17,328 oraciones (todo el contenido de AnCora). Implementamos varios algoritmos de parsing estadístico entrenados sobre este corpus. En particular, teníamos como objetivo probar enfoques basados en redes neuronales. Las estrategias implementadas son: una línea base bottom-up que utiliza comparaciones bi-léxicas o un perceptrón multicapa; un enfoque tipo CKY que utiliza los resultados de un supertagger; y un enfoque top-down que codifica las secuencias de palabras mediante redes tipo LSTM. Evaluamos la performance de los parsers implementados y los comparamos entre sí y con un conjunto de parsers existententes para el español. Nuestro enfoque LSTM top-down parece ser el que tiene mejor desempeño para nuestro conjunto de test, obteniendo los mejores puntajes (comparado con nuestras estrategias y también con parsers externos) en cuanto a métricas de constituyentes (87.57 F1 no etiquetada, 82.06 F1 etiquetada), métricas de dependencias (91.32 UAS, 88.96 LAS), y SRL (87.68 no etiquetada, 80.66 etiquetada), pero debemos tener en cuenta que la comparación con parsers externos puede ser ruidosa debido al post procesamiento realizado para adaptarlos a nuestro formato. También definimos un conjunto de métricas para evaluar la identificación de algunos fenómenos particulares del lenguaje, y el parser LSTM top-down obtuvo mejores resultados que las baselines para casi todas estas métricas
Construcción de recursos lingüísticos para una gramática HPSG para el español
Full text linkEn este trabajo se presenta la construcción de recursos lingüísticos para trabajar con una gramática HPSG para el español. HPSG es un formalismo gramatical rico debido a que el resultado del análisis sintáctico con este formalismo es una representación de la oración que incluye información tanto sintáctica como semántica. Para el idioma inglés existen parsers estadísticos HPSG de alta performance y cobertura del idioma, pero para el español las herramientas existentes aún no llegan al mismo nivel. Se describe una gramática HPSG para el español, indicando sus estructuras de rasgos principales y sus reglas de combinación de expresiones. Se construyó un corpus de árboles HPSG para el español utilizando la gramática definida. Para esto, se partió del corpus AnCora y se transformaron las oraciones mediante un proceso automático, obteniendo como resultado un nuevo corpus etiquetado según el formalismo HPSG. Las heurísticas de transformación tienen un 95,3% de precisión en detección de núcleos y un 92,5% de precisión en clasificación de argumentos. A partir del corpus se definieron las entradas léxicas y se agruparon las entradas de las categorías léxicas de mayor complejidad combinatoria (verbos, nombres y adjetivos) según su comportamiento sintáctico-semántico. Estas agrupaciones de entradas léxicas se denominan frames léxicos. A partir de esto se construyó un supertagger para identificar los frames léxicos más probables dadas las palabras de una oración. El supertagger tiene un accuracy de 83,58% para verbos, 85,78% para nombres y 81,40% para adjetivos (considerando las tres etiquetas más probables)
Adaptive Prompting: Ad-hoc Prompt Composition for Social Bias Detection
Full text linkRecent advances on instruction fine-tuning have led to the development of various prompting techniques for large language models, such as explicit reasoning steps. However, the success of techniques depends on various parameters, such as the task, language model, and context provided. Finding an effective prompt is, therefore, often a trial-and-error process. Most existing approaches to automatic prompting aim to optimize individual techniques instead of compositions of techniques and their dependence on the input. To fill this gap, we propose an adaptive prompting approach that predicts the optimal prompt composition ad-hoc for a given input. We apply our approach to social bias detection, a highly context-dependent task that requires semantic understanding. We evaluate it with three large language models on three datasets, comparing compositions to individual techniques and other baselines. The results underline the importance of finding an effective prompt composition. Our approach robustly ensures high detection performance, and is best in several settings. Moreover, first experiments on other tasks support its generalizability
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
koamabayili/VECTRON-author-checklist: VECTRON author checklist
No full textWe have done our best to complete the author checklist relating to the use of animals in the hut study. Note that the objective for the hut study was to evaluate the IRS treatment applications for residual efficacy against Anopheles mosquitoes, including the local An. coluzzii mosquito population. Cows were only used to attract mosquitoes into the huts and no tests were carried out directly on the cows. The author checklist is intended for use with studies where experiments are carried out on animals, which is why we have had such difficulty in completing this for the hut study, as many of the questions do not relate to how the cows were used
- …
