Articles

We present a first empirical effort in annotating attribution in Modern Standard Arabic (MSA). Identifying attributed arguments to the source is applied successfully in diverse systems such as authorship identification, information retrieval, and opinion mining. Current studies focus on using lexical terms in long texts to verify, for example, the …...

Cross-lingual word embeddings are the representations of words across languages in a shared continuous vector space. Cross-lingual word embeddings have been shown to be helpful in the development of cross-lingual natural language processing tools. In case of more than two languages involved, we call them multilingual word embeddings. In this …...

Argumentative corpora are costly to create and are available in only few languages with English dominating the area. In this paper we release the first publicly available corpora in all Balkan languages and Arabic. The corpora are obtained by using parallel corpora where the source language is English and target …...

In text simplification (TS), parallel corpora consisting of original sentences and their manually simplified counterparts are very scarce and small in size, which impedes building supervised automated TS systems with sufficient coverage. Furthermore, the existing corpora usually do not distinguish sentence pairs which present full matches (both sentences contain the …...

German is a language with complex morphological processes. Its long and often ambiguous word forms present a bottleneck problem in natural language processing. As a step towards morphological analyses of high quality, this paper introduces a morphological treebank for German. It is derived from the linguistic database CELEX which is …...

Word formation via compounding is a very widely observed but quite diverse phenomenon across the world’s languages, but the compositional semantics of a compound are often productively correlated between even distant languages. Using only freely available bilingual dictionaries and no annotated training data, we derive novel models for analyzing compound …...

We present rule-based morphological parsers in the Tigrinya and Oromo languages, based on a parser-combinator rather than finite-state paradigm. This paradigm allows rapid development and ease of integration with other systems, although at the cost of non-optimal theoretical efficiency. These parsers produce multiple output representations simultaneously, including lemmatization, morphological segmentation, …...

The paper provides a cognitively motivated method for evaluating the inflectional complexity of a language, based on a sample of "raw" inflected word forms processed and learned by a recurrent self-organising neural network with fixed parameter setting. Training items contain no information about either morphological content or structure. This makes …...

Following the development of the universal dependencies (UD) framework and the CoNLL 2017 Shared Task on end-to-end UD parsing, we address the need for a universal representation of morphological analysis which on the one hand can capture a range of different alternative morphological analyses of surface tokens, and on the …...

We present an ongoing effort on the first large-scale morphologically manually annotated corpus of Emirati Arabic. This corpus includes about 200,000 words selected from eight Gumar corpus novels in the Emirati Arabic variety. The selected texts are being annotated for tokenization, part-of-speech, lemmatization, English glosses and dialect identification. The orthography …...

We compare manual and automatic approaches to the problem of extracting bitexts from the Web in the framework of a case study on building a Russian-Kazakh parallel corpus. Our findings suggest that targeted, site-specific crawling results in cleaner bitexts with a higher ratio of parallel sentences. We also find that …...

We introduce a notion of pause-word ratio computed using ranges of pause lengths rather than lower cutoffs for pause lengths. Standard pause-word ratios are indicators of cognitive effort during different translation modalities.The pause range version allows for the study of how different types of pauses relate to the extent of …...

Inspired by the tasks of Multimodal Machine Translation and Visual Sense Disambiguation we introduce a task called Multimodal Lexical Translation (MLT). The aim of this new task is to correctly translate an ambiguous word given its context - an image and a sentence in the source language. To facilitate the …...

Speech corpora are key components needed by both: linguists (in language analyses, research and teaching languages) and Natural Language Processing (NLP) researchers (in training and evaluating several NLP tasks such as speech recognition, text-to-speech and speech-to-text synthesis). Despite of the great demand, there is still a huge shortage in available …...

The recent years have seen a revival of interest in textual entailment, sparked by i) the emergence of powerful deep neural network learners for natural language processing and ii) the timely development of large-scale evaluation datasets such as SNLI. Recast as natural language inference, the problem now amounts to detecting …...

This paper presents a fine-grained error comparison of the English-to-Dutch translations of a commercial neural, phrase-based and rule- based machine translation (MT) system. For phrase-based and rule-based machine translation, we make use of the annotated SCATE corpus of MT errors, enriching it with the annotation of neural MT errors and …...

In this paper, we present evaluation corpora covering four genres for four language pairs that we harvested from the web in an automated fashion. We use these multi-genre benchmarks to evaluate the impact of genre differences on machine translation (MT). We observe that BLEU score differences between genres can be …...

The goal of this work is to design a machine translation (MT) system for a low-resource family of dialects, collectively known as Swiss German, which are widely spoken in Switzerland but seldom written. We collected a significant number of parallel written resources to start with, up to a total of …...

We explore ways of identifying terms from monolingual texts and integrate them into investigating the contribution of terminology to translation quality.The researchers proposed a supervised learning method using common statistical measures for termhood and unithood as features to train classifiers for identifying terms in cross-domain and cross-language settings. On its …...

In this paper, we present results of employing multilingual and multi-way neural machine translation approaches for morphologically rich languages, such as Estonian and Russian. We experiment with different NMT architectures that allow achieving state-of-the-art translation quality and compare the multi-way model performance to one-way model performance. We report improvements of …...