1,721,002 research outputs found
Pronoun-Focused MT and Cross-Lingual Pronoun Prediction: Findings of the 2015 DiscoMT Shared Task on Pronoun Translation
Full text linkWe describe the design, the evaluation setup, and the results of the DiscoMT 2015 shared task, which included two subtasks, relevant to both the machine translation (MT) and the discourse communities: (i) pronoun-focused translation, a practical MT task, and (ii) cross-lingual pronoun prediction, a classification task that requires no specific MT expertise and is interesting as a machine learning task in its own right. We focused on the English–French language pair, for which MT output is generally of high quality, but has visible issues with pronoun translation due to differences in the pronoun systems of the two languages. Six groups participated in the pronoun-focused translation task and eight groups in the cross-lingual pronoun prediction task
Findings of the 2017 DiscoMT Shared Task on Cross-lingual Pronoun Prediction
Full text linkWe describe the design, the setup, and the evaluation results of the DiscoMT 2017 shared task on cross-lingual pronoun prediction. The task asked participants to predict a target-language pronoun given a source-language pronoun in the context of a sentence. We further provided a lemmatized target-language human-authored translation of the source sentence, and automatic word alignments between the source sentence words and the target-language lemmata. The aim of the task was to predict, for each target-language pronoun placeholder, the word that should replace it from a small, closed set of classes, using any type of information that can be extracted from the entire document. We offered four subtasks, each for a different language pair and translation direction: English-to-French, English-to-German, German-to-English, and Spanish-to-English. Five teams participated in the shared task, making submissions for all language pairs. The evaluation results show that all participating teams outperformed two strong n-gram-based language model-based baseline systems by a sizable margin
Vagueness and referential ambiguity in a large-scale annotated corpus
No full textIn this paper, we argue that difficulties in the definition of coreference itself contribute to lower inter-annotator agreement in certain cases. Data from a large referentially annotated corpus serves to corroborate this point, using a quantitative investigation to assess which effects or problems are likely to be the most prominent. Several examples where such problems occur are discussed in more detail, and we then propose a generalisation of Poesio, Reyle and Stevenson’s Justified Sloppiness Hypothesis to provide a unified model for these cases of disagreement and argue that a deeper understanding of the phenomena involved allows to tackle problematic cases in a more principled fashion than would be possible using only pre-theoretic intuitions
Antecedent selection techniques for high-recall roreference resolution
No full textWe investigate methods to improve the recall in coreference resolution by also trying to resolve those definite descriptions where no earlier mention of the referent shares the same lexical head (coreferent bridging). The problem, which is notably harder than identifying coreference relations among mentions which have the same lexical head, has been tackled with several rather different approaches, and we attempt to provide a meaningful classification along with a quantitative comparison. Based on the different merits of the methods, we discuss possibilities to improve them and show how they can be effectively combined
Using the web to resolve coreferent bridging in German newspaper text
No full textWe adopt Markert and Nissim (2005)’s approach of using the World Wide Web to resolve cases of coreferent bridging for German and discuss the strength and weaknesses of this approach. As the general approach of using surface patterns to get information on ontological relations between lexical items has only been tried on English, it is also interesting to see whether the approach works for German as well as it does for English and what differences between these languages need to be accounted for. We also present a novel approach for combining several patterns that yields an ensemble that outperforms the best-performing single patterns in terms of both precision and recall
Tagging kausaler Relationen
No full textIn dieser Diplomarbeit geht es um kausale Beziehungen zwischen Ereignissen und Erklärungsbeziehungen zwischen Ereignissen, bei denen kausale Relationen eine wichtige Rolle spielen. Nachdem zeitliche Relationen einerseits ihrer einfacheren Formalisierbarkeit und andererseits ihrer gut sichtbaren Rolle in der Grammatik (Tempus und Aspekt, zeitliche Konjunktionen) wegen in jüngerer Zeit stärker im Mittelpunkt des Interesses standen, soll hier argumentiert werden, dass kausale Beziehungen und die Erklärungen, die sie ermöglichen, eine wichtigere Rolle im Kohärenzgefüge des Textes spielen. Im Gegensatz zu “tiefen” Verfahren, die auf einer detaillierten semantischen Repr¨asentation des Textes aufsetzen und infolgedessen für unrestringierten Text m. E. nicht geeignet sind, wird hier untersucht, wie man dieses Ziel erreichen kann, ohne sich auf eine aufwändig konstruierte Wissensbasis verlassen zu müssen.Causal relations between events and explanational relations among these events, where the causal relations play an important role, are the main topic of the present diploma thesis. After temporal relations between events have been more in the focus of interest recently because of both being easier to formalize and playing a visible role in grammar (notably the effects of time and aspect, as well as temporal conjunctions), I will argue that causal relations and the explanations they provide play the greater role in the coherence of a text. In contrast to “deep” approaches that rely on a fine-grained semantic representation of the text and by consequent can be unsuitable for unrestricted text, I will investigate how to reach this goal without requiring an expensive hand-coded knowledge base
The mention-pair model
No full textThis chapter introduces one of the early and most influential machine learning approaches to coreference resolution, the mention-pair model. Initiated in the mid-nineties and further developed into a more generic resolver by Soon et al. in 2001 and many others, the simple model still remains a popular benchmark in the learning-based resolution research. The mention-pair model recasts the coreference resolution problem as a classification task in which a classifier is trained to decide for a given pair of noun phrases whether they corefer or not. In a second step, full coreference chains are built by clustering these pairwise decisions. This chapter reviews the main building blocks of the mention-pair model: the construction of positive and negative instances and the related problem of data set skewness, the selection of informative features, and the choice of machine learner and clustering mechanism
Decorrelation and shallow semantic patterns for distributional clustering of nouns and verbs
No full textDistributional approximations to lexical semantics are very useful not only in helping the creation of lexical semantic resources (Kilgariff et al., 2004; Snow et al., 2006), but also when directly applied in tasks that can benefit from large-coverage semantic knowledge such as coreference resolution (Poesio et al., 1998; Gasperin and Vieira, 2004; Versley, 2007), word sense disambiguation (Mc- Carthy et al., 2004) or semantical role labeling (Gordon and Swanson, 2007). We present a model that is built from Webbased corpora using both shallow patterns for grammatical and semantic relations and a window-based approach, using singular value decomposition to decorrelate the feature space which is otherwise too heavily influenced by the skewed topic distribution of Web corpora
- …
