The Conference on Computational Natural Language Learning (CoNLL) features a shared task, in which participants train and test their learning systems on the same data sets. In 2017, one of two tasks was devoted to learning dependency parsers for a large number of languages, in a realworld setting without any gold-standard annotation on input. All test sets followed a unified annotation scheme, namely that of Universal Dependencies. In this paper, we define the task and evaluation methodology, describe data preparation, report and analyze the main results, and provide a brief categorization of the different approaches of the participating systems.
Universal dependencies (UD) is a framework for morphosyntactic annotation of human language, which to date has been used to create treebanks for more than 100 languages. In this article, we outline the linguistic theory of the UD framework, which draws on a long tradition of typologically oriented grammatical theories. Grammatical relations between words are centrally used to explain how predicate–argument structures are encoded morphosyntactically in different languages while morphological features and part-of-speech classes give the properties of words. We argue that this theory is a good basis for cross-linguistically consistent annotation of typologically diverse languages in a way that supports computational natural language understanding as well as broader linguistic studies.
This paper describes the MeMAD project entry to the WMT Multimodal Machine Translation Shared Task.We propose adapting the Transformer neural machine translation (NMT) architecture to a multi-modal setting. In this paper, we also describe the preliminary experiments with textonly translation systems leading us up to this choice.We have the top scoring system for both English-to-German and English-to-French, according to the automatic metrics for flickr18.Our experiments show that the effect of the visual features in our system is small. Our largest gains come from the quality of the underlying text-only NMT system. We find that appropriate use of additional data is effective.
Multimodal machine translation involves drawing information from more than one modality, based on the assumption that the additional modalities will contain useful alternative views of the input data. The most prominent tasks in this area are spoken language translation, image-guided translation, and video-guided translation, which exploit audio and visual modalities, respectively. These tasks are distinguished from their monolingual counterparts of speech recognition, image captioning, and video captioning by the requirement of models to generate outputs in a different language. This survey reviews the major data resources for these tasks, the evaluation campaigns concentrated around them, the state of the art in end-to-end and pipeline approaches, and also the challenges in performance evaluation. The paper concludes with a discussion of directions for future research in these areas: the need for more expansive and challenging datasets, for targeted evaluations of model performance, and for multimodality in both the input and output space.
The potential of processing user-generated texts freely available on the web is widely recognized, but due to the non-canonical nature of the language used in the web, it is not possible to process these data using conventional methodologies designed for well-edited formal texts. Procedures for properly annotating raw web data have not been as extensively researched as those for annotating well-edited texts, as also evident from the viewpoint of Turkish language processing. Moreover, there is a considerable shortage of human-annotated corpora derived from Turkish web data. The ITU Web Treebank is the first attempt for a diverse corpus compiled from Turkish texts found on the web. In this paper, we first present our survey of the non-canonical aspects of the language used in the Turkish web. Next, we discuss in detail the annotation procedure followed in the ITU Web Treebank, revised for compatibility with the language of the web. Finally, we describe the web-based annotation tool following this procedure, on which the treebank was annotated.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.