Articles

AbstractIn this paper, we present a multimodal parallel text-image corpus, and propose an image annotation method that exploits the textual information associated with images. Our corpus contains news articles composed of a text, images and image captions, and is significantly larger than the other news corpora proposed in image annotation …...

AbstractWe describe the compilation of a large corpus of French-Dutch sentence pairs from official Belgian documents which are available in the online version of the publication Belgisch Staatsblad/Moniteur belge, and which have been published between 1997 and 2006. After downloading files in batch, we filtered out documents which have no …...

AbstractStatistical machine translation to morphologically richer languages is a challenging task and more so if the source and target languages differ in word order. Current state-of-the-art MT systems thus deliver mediocre results. Adding more parallel data often helps improve the results; if it doesn't, it may be caused by various …...

AbstractIn this article I present a lexicon for Arabic verbs which exploits Levin’s verb-classes (Levin, 1993) and the basic development procedure used by (Schuler, 2005). The verb lexicon in its current state has 173 classes which contain 4392 verbs and 498 frames providing information about verb root, the deverbal form …...

AbstractWe present the methodology that underlies mew metrics for semantic machine translation evaluation we are developing. Unlike widely-used lexical and n-gram based MT evaluation metrics, the aim of semantic MT evaluation is to measure the utility of translations. We discuss the design of empirical studies to evaluate the utility of …...

AbstractThis paper summarizes our work on creating a full-scale coreference resolution (CR) system for Italian, using BART ― an open-source modular CR toolkit initially developed for English corpora. We discuss our experiments on language-specific issues of the task. As our evaluation experiments show, a language-agnostic system (designed primarily for English) …...

AbstractRecent developments on hybrid systems that combine rule-based machine translation (RBMT) systems with statistical machine translation (SMT) generally neglect the fact that RBMT systems tend to produce more syntactically well-formed translations than data-driven systems. This paper proposes a method that alleviates this issue by preserving more useful structures produced by …...

AbstractWe have previously reported on ProPOSEL, a purpose-built Prosody and PoS English Lexicon compatible with the Python Natural Language ToolKit. ProPOSEC is a new corpus research resource built using this lexicon, intended for distribution with the Aix-MARSEC dataset. ProPOSEC comprises multi-level parallel annotations, juxtaposing prosodic and syntactic information from different …...

AbstractIn this paper we present a new approach for obtaining the terminology of a given domain using the category and page structures of the Wikipedia in a language independent way. Our approach consists basically, for each domain, on navigating the Category graph of the Wikipedia starting from the root nodes …...

AbstractIn this paper, we present the first results of the parallel Czech discourse annotation in the Prague Dependency Treebank 2.0. Having established an annotation scenario for capturing semantic relations crossing the sentence boundary in a discourse, and having annotated the first sections of the treebank according to these guidelines, we …...

AbstractToday's natural language processing systems are growing more complex with the need to incorporate a wider range of language resources and more sophisticated statistical methods. In many cases, it is necessary to learn a component with input that includes the predictions of other learned components or to assign simultaneously the …...

AbstractRecently, language resources (LRs) are becoming indispensable for linguistic researches. However, existing LRs are often not fully utilized because their variety of usage is not well known, indicating that their intrinsic value is not recognized very well either. Regarding this issue, lists of usage information might improve LR searches and …...

AbstractWe describe a web application called “ANC2Go” that enables the user to select data from the Open American National Corpus (OANC) and the Manually Annotated Sub-corpus (MASC) together with some or all of the annotations available. The user also may select from among a variety of options for output format, …...

AbstractThe LTSE-VAD is one of the best known algorithms for voice activity detection. In this paper we present a modified version of this algorithm, that makes the VAD decision not taking into account account the estimated background noise level, but the signal to noise ratio (SNR). This makes the algorithm …...

AbstractCollocations play a significant role in second language acquisition. In order to be able to offer efficient support to learners, an NLP-based CALL environment for learning collocations should be based on a representative collocation error annotated learner corpus. However, so far, no theoretically-motivated collocation error tag set is available. Existing …...

AbstractThe Brandeis Annotation Tool (BAT) is a web-based text annotation tool that is centered around the notions of layered annotation and task decomposition. It allows annotations to refer to other annotations and to take a complicated task and split it into easier subtasks. The central organizing concept of BAT is …...

AbstractThe paper describes an approach to expedite the process of manual annotation of a Hindi dependency treebank which is currently under development. We propose a way by which consistency among a set of manual annotators could be improved. Furthermore, we show that our setup can also prove useful for evaluating …...

AbstractThe explosion of biomedical literature and with it the -uncontrolled- creation of abbreviations presents some special challenges for both human readers and computer applications. We developed an annotated corpus of Dutch medical text, and experimented with two approaches to abbreviation detection and resolution. Our corpus is composed of abstracts from …...

AbstractThis paper discusses our ongoing work on constructing an annotated corpus of children’s stories for further studies on the linguistic, computational, and cognitive aspects of story structure and understanding. Given its semantic nature and the need for extensive common sense and world knowledge, story understanding has been a notoriously difficult …...

AbstractIn this work we propose a hybrid unsupervised approach for semantic relation extraction from Italian and English texts. The system takes as input pairs of ""distributionally similar"" terms, possibly involved in a semantic relation. To validate and label the anonymous relations holding between the terms in input, the candidate pairs …...