Clustering news across languages enables efficient media monitoring by aggregating articles from multilingual sources into coherent stories. Doing so in an online setting allows scalable processing of massive news streams. To this end, we describe a novel method for clustering an incoming stream of multilingual documents into monolingual and crosslingual story clusters. Unlike typical clustering approaches that consider a small and known number of labels, we tackle the problem of discovering an ever growing number of cluster labels in an online fashion, using real news datasets in multiple languages. Our method is simple to implement, computationally efficient and produces state-of-the-art results on datasets in German, English and Spanish.

No abstract

This paper presents LVBERT – the first publicly available monolingual language model pre-trained for Latvian. We show that LVBERT improves the state-of-the-art for three Latvian NLP tasks including Part-of-Speech tagging, Named Entity Recognition and Universal Dependency parsing. We release LVBERT to facilitate future research and downstream applications for Latvian NLP.

No abstract

No abstract

No abstract

In the medical domain various approaches are used to produce examination reports and other medical records. Depending on the language-specific technology support, the type of examination, the size of the hospital or clinic, and other aspects, the reporting workflow can range from completely manual to (semi-)automated. A manual workflow may completely depend on the doctor itself or may include a transcriptionist centre in the loop. In an automated workflow, the transcriptionist centre is typically replaced by an automatic speech recognition (ASR) system. While the latter approach is well suited for high resource languages where word error rate (WER) is as low as 5-10%, for less resourced languages a dual approach combining automated transcription with the support from a transcriptionist centre may be more suited. In this paper, we present a platform that supports both workflows simultaneously. The RUTA:MED platform currently includes an ASR pipeline for the less resourced Latvian language, and it is being deployed and tested at several hospitals and clinics in Latvia. The platform can be adopted for any other language, and it emphasizes that WER is only one of the performance indicators in case of medical transcription.

Today, most dialogue systems are fully or partly built using neural network architectures. A crucial prerequisite for the creation of a goaloriented neural network dialogue system is a dataset that represents typical dialogue scenarios and includes various semantic annotations, e.g. intents, slots and dialogue actions, that are necessary for training a particular neural network architecture. In this demonstration paper, we present an easy to use interface and its backend which is oriented to domain experts for the collection of goal-oriented dialogue samples. The platform not only allows to collect or write sample dialogues in a structured way, but also provides a means for simple annotation and interpretation of the dialogues. The platform itself is language-independent; it depends only on the availability of particular language processing components for a specific language. It is currently being used to collect dialogue samples in Latvian (a highly inflected language) which represent typical communication between students and the student service.