1,721,006 research outputs found
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
A Fast and Sound Tagging Method for Discontinuous Named-Entity Recognition
No full textInternational audienceWe introduce a novel tagging scheme for discontinuous named entity recognition based on an explicit description of the inner structure of discontinuous mentions. We rely on a weighted finite state automaton for both marginal and maximum a posteriori inference. As such, our method is sound in the sense that (1) well-formedness of predicted tag sequences is ensured via the automaton structure and (2) there is an unambiguous mapping between well-formed sequences of tags and (discontinuous) mentions. We evaluate our approach on three English datasets in the biomedical domain, and report comparable results to state-of-the-art while having a way simpler and faster model
On the inconsistency of separable losses for structured prediction
Full text linkIn this paper, we prove that separable negative log-likelihood losses for
structured prediction are not necessarily Bayes consistent, or, in other words,
minimizing these losses may not result in a model that predicts the most
probable structure in the data distribution for a given input. This fact opens
the question of whether these losses are well-adapted for structured prediction
and, if so, why.Comment: Preprint, to appear in proc. of EACL 202
Méthodes de prédiction structurée pour l’analyse sémantique
No full textL'analyse sémantique est une tâche qui consiste à produire une représentation formelle manipulable par un ordinateur à partir d'un énoncé en langage naturel. Il s'agit d'une tâche majeure dans le traitement automatique des langues avec plusieurs applications comme le développement de systèmes de question-réponse ou la génération de code entre autres. Ces dernières années, les approches fondées sur les réseaux de neurones, et en particulier les architectures séquence-à-séquence, ont démontré de très bonnes performances pour cette tâche. Cependant, plusieurs travaux ont mis en avant les limites de ces analyseurs sémantiques sur des exemples hors distribution. En particulier, ils échouent lorsque la généralisation compositionnelle est requise. Il est donc essentiel de développer des analyseurs sémantiques qui possèdent de meilleures capacités de composition.La représentation du contenu sémantique est une autre préoccupation lorsque l'on aborde l'analyse sémantique. Comme différentes structures syntaxiques peuvent être utilisées pour représenter le même contenu sémantique, il est souhaitable d'utiliser des structures qui peuvent à la fois représenter précisément le contenu sémantique et s'ancrer facilement sur le langage naturel. À ces égards, cette thèse utilise des représentations fondées sur les graphes pour l'analyse sémantique et se concentre sur deux tâches. La première concerne l'entrainement des analyseurs sémantiques fondés sur les graphes. Ils doivent apprendre une correspondance entre les différentes parties du graphe sémantique et l'énoncé en langage naturel. Comme cette information est généralement absente des données d'apprentissage, nous proposons des algorithmes d'apprentissage qui traitent cette correspondance comme une variable latente. La deuxième tâche se concentre sur l'amélioration des capacités de composition des analyseurs sémantiques fondés sur les graphes dans deux contextes différents. Notons que dans la prédiction de graphes, la méthode traditionnelle consiste à prédire d'abord les nœuds, puis les arcs du graphe. Dans le premier contexte, nous supposons que les graphes à prédire sont nécessairement des arborescences et nous proposons un algorithme d'optimisation basé sur le lissage des contraintes et la méthode du graident conditionnel qui permet de prédire l'ensemble du graphe de manière jointe. Dans le second contexte, nous ne faisons aucune hypothèse quant à la nature des graphes sémantiques. Dans ce cas, nous proposons d'introduire une étape intermédiaire de superétiquetage dans l'algorithme d'inférence. Celle-ci va imposer des contraintes supplémentaires sur l'étape de prédiction des arcs. Dans les deux cas, nos contributions peuvent être vues comme l'introduction de contraintes locales supplémentaires pour garantir la validité de la prédiction globale. Expérimentalement, nos contributions améliorent de manière significative les capacités de composition des analyseurs sémantiques fondés sur les graphes et surpassent les approches comparables sur plusieurs jeux de données conçus pour évaluer la généralisation compositionnelle.Semantic parsing is the task of mapping a natural language utterance into a formal representation that can be manipulated by a computer program. It is a major task in Natural Language Processing with several applications, including the development of questions answers systems or code generation among others.In recent years, neural-based approaches and particularly sequence-to-sequence architectures have demonstrated strong performances on this task. However, several works have put forward the limitations of neural-based parsers on out-of-distribution examples. In particular, they fail when compositional generalization is required. It is thus essential to develop parsers that exhibit better compositional abilities.The representation of the semantic content is another concern when tackling semantic parsing. As different syntactic structures can be used to represent the same semantic content, one should focus on structures that can both accurately represent the semantic content and align well with natural language. In that regard, this thesis relies on graph-based representations for semantic parsing and focuses on two tasks.The first one deals with the training of graph-based semantic parsers. They need to learn a correspondence between the parts of the semantic graph and the natural language utterance. As this information is usually absent in the training data, we propose training algorithms that treat this correspondence as a latent variable.The second task focuses on improving the compositional abilities of graph-based semantic parsers in two different settings. Note that in graph prediction, the traditional pipeline is to first predict the nodes and then the arcs of the graph. In the first setting, we assume that the graphs that must be predicted are trees and propose an optimization algorithm based on constraint smoothing and conditional gradient that allows to predict the entire graph jointly. In the second setting, we do not make any assumption regarding the nature of the semantic graphs. In that case, we propose to introduce an intermediate supertagging step in the inference pipeline that constrains the arc prediction step. In both settings, our contributions can be viewed as introducing additional local constraints to ensure the well-formedness the overall prediction. Experimentally, our contributions significantly improve the compositional abilities of graph-based semantic parsers and outperform comparable baselines on several datasets designed to evaluate compositional generalization
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
A fast and sound tagging method for discontinuous named-entity recognition
Full text linkWe introduce a novel tagging scheme for discontinuous named entity recognition based on an explicit description of the inner structure of discontinuous mentions. We rely on a weighted finite state automaton for both marginal and maximum a posteriori inference. As such, our method is sound in the sense that (1) well-formedness of predicted tag sequences is ensured via the automaton structure and (2) there is an unambiguous mapping between well-formed sequences of tags and (discontinuous) mentions. We evaluate our approach on three English datasets in the biomedical domain, and report comparable results to state-of-the-art while having a way simpler and faster model.EMNLP 202
- …
