Articles

Stemma generation can be understood as a task where an original manuscript M gets copied and copies – due to the manual mode of copying – vary from each other and from M. Copies M1, .., Mk which survive historical loss serve as input to a mapping process estimating a …...

Abbreviation is a common phenomenon across languages, especially in Chinese. In most cases, if an expression can be abbreviated, its abbreviation is used more often than its fully expanded forms, since people tend to convey information in a most concise way. For various language processing tasks, abbreviation is an obstacle …...

Large collections of texts are commonly generated by large organizations and making sense of these collections of texts is a significant challenge. One method for handling this is to organize the concepts into a hierarchical structure such that similar concepts can be discovered and easily browsed. This approach was the …...

Knowledge Base Completion infers missing facts from existing ones in knowledge bases. As recent Open Information Extraction systems allow us to extract ever larger (yet incomplete) open-domain Knowledge Bases from text, we seek to probabilistically extend the limited coverage we get from existing facts, to arbitrary queries about plausible information. …...

This paper presents a novel prototype for biomedical term normalization of electronic health record excerpts with the Unified Medical Language System (UMLS) Metathesaurus, a large, multi-lingual compendium of biomedical and health-related terminologies. Despite the prototype being multilingual and cross-lingual by design, we first focus on processing clinical text in Spanish …...

In this paper we present Multilingual IsA (MIsA), which is a collection of hypernymy relations in five languages (i.e., English, Spanish, French, Italian and Dutch) extracted from the corresponding full Wikipedia corpus. For each language, we first established a set of existing (viz. found in literature) or newly defined lexico-syntactic …...

We present a novel, minimally supervised method of generating word embedding evaluation datasets for a large number of languages. Our approach utilizes existing dependency treebanks and parsers in order to create language-specific syntactic analogy datasets that do not rely on translation or human annotation. As part of our work, we …...

Matics is a free and open-source software suite for exploring annotated data and evaluation results. It proposes a dataframe data model allowing the intuitive exploration of data characteristics and evaluation results and provides support for graphing the values and running appropriate statistical tests. The tools already run on several Natural …...

We present a new approach to evaluate computational models for the task of text understanding by the means of out-of-context error detection. Through the novel design of our automated modification process, existing large-scale data sources can be adopted for a vast number of text understanding tasks. The data is thereby …...

Projects that set out to create a linguistic resource often do so by using a machine learning model that pre-annotates or filters the content that goes through to a human annotator, before going into the final version of the resource. However, available budgets are often limited, and the amount of …...

This paper proposes the task of Visual COPA (VCOPA). Given a premise image and two alternative images, the task is to identify the more plausible alternative with their commonsense causal context. The VCOPA task is designed as its desirable machine system needs a more detailed understanding of the image, commonsense …...

Perceptual evaluation is still the most common method in clinical practice for the diagnosis and monitoring of the condition progression of people suffering from dysarthria (or speech disorders more generally). Such evaluations are frequently described as non-trivial, subjective and highly time-consuming (depending on the evaluation level). Clinicians have, therefore, expressed …...

Recent development of spoken dialog systems has moved away from a command-style input and aims at allowing a natural input style. Obtaining suitable data for training and testing such systems is a significant challenge. We investigate with which methods data elicited via crowdsourcing can be assessed with respect to its …...

In this paper, we present the evaluation of several bilingual dictionary building methods applied to {Komi-Permyak, Komi-Zyrian, Hill Mari, Meadow Mari, Northern Saami, Udmurt}–{English, Finnish, Hungarian, Russian} language pairs. Since these Finno-Ugric minority languages are under-resourced and standard dictionary building methods require a large amount of pre-processed data, we had …...

We applied a method for automatic extraction of bilingual multiword units (BMWUs) from a parallel corpus in order to investigate their contribution to translation quality in terms of adequacy and fluency. Our statistical analysis is based on generalized additive modelling. It has been shown that normalised BMWU ratios can be …...

Analyzing historical languages, such as Ancient Greek and Latin, is challenging. Such languages are often under-resourced and lack primary material for certain time periods. This prevents applying advanced natural-language processing (NLP) techniques and requires resorting to basic NLP not relying on machine learning. An important analysis is the discovery and …...

Casual talk or social conversation is a fundamental form of spoken interaction. Corpora of casual talk often comprise relatively short dyadic conversations, although research into such talk has found longer multiparty interaction to be very common. This genre of spoken interaction is attracting more interest with attempts to build more …...

We present a new evaluation scheme for the lexical substitution task. Following (McCarthy and Navigli, 2007) we conducted an annotation task for French that mixes two datasets: in the first one, 300 sentences containing a target word (among 30 different) were submitted to annotators who were asked to provide substitutes. …...

We introduce TREEANNOTATOR, a graphical tool for annotating tree-like structures, in particular structures that jointly map dependency relations and inclusion hierarchies, as used by Rhetorical Structure Theory (RST). TREEANNOTATOR is browser-based, embedded within the UIMA framework and provides two visualization modes. TREEANNOTATOR’s interoperability exceeds similar tools, providing a wider range …...

Dialogue act recognition is an important part of natural language understanding. We investigate the way dialogue act corpora are annotated and the learning approaches used so far. We find that the dialogue act is context-sensitive within the conversation for most of the classes. Nevertheless, previous models of dialogue act classification …...