Open speech corpora of substantial size are seldom available for less-spoken languages, and this was recently the case also for Latvian with its 1.5M native speakers. While there exist several closed Latvian speech corpora of 100+ hours, used to train competitive models for automatic speech recognition (ASR), there were only a few tiny open datasets available at the beginning of 2023, the 18-hour Latvian Common Voice 13.0 dataset being the largest one. In the result of a successful national crowdsourcing initiative, organised jointly by several institutions, the size and speaker diversity of the Latvian Common Voice 17.0 release have increased more than tenfold in less than a year. A successful follow-up initiative was also launched for Latgalian, which has been recognized as an endangered historic variant of Latvian with 150k speakers. The goal of these initiatives is not only to enlarge the datasets but also to make them more diverse in terms of speakers and accents, text genres and styles, intonations, grammar and lexicon. They have already become considerable language resources for both improving ASR and conducting linguistic research. Since we use the Mozilla Common Voice platform to record and validate speech samples, this paper focuses on (i) the selection of text snippets to enrich the language data and to stimulate various intonations, (ii) an indicative evaluation of the acquired corpus and the first ASR models fine-tuned on this data, (iii) our social campaigns to boost and maintain this initiative.

LNCC is a diverse collection of Latvian language corpora representing both written and spoken language and is useful for both linguistic research and language modelling. The collection is intended to cover diverse Latvian language use cases and all the important text types and genres (e.g. news, social media, blogs, books, scientific texts, debates, essays, etc.), taking into account both quality and size aspects. To reach this objective, LNCC is a continuous multi-institutional and multi-project effort, supported by the Digital Humanities and Language Technology communities in Latvia. LNCC includes a broad range of Latvian texts from the Latvian National Library, Culture Information Systems Centre, Latvian National News Agency, Latvian Parliament, Latvian web crawl, various Latvian publishers, and from the Latvian language corpora created by Institute of Mathematics and Computer Science and its partners, including spoken language corpora. All corpora of LNCC are re-annotated with a uniform morpho-syntactic annotation scheme which enables federated search and consistent linguistics analysis in all the LNCC corpora, as well as facilitates to select and mix various corpora for pre-training large Latvian language models like BERT and GPT.

Today, most dialogue systems are fully or partly built using neural network architectures. A crucial prerequisite for the creation of a goal-oriented 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 back-end 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.

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 clusters. Unlike typical clustering approaches that report results on datasets with 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. In our formulation, the monolingual clusters group together documents while the crosslingual clusters group together monolingual clusters, one per language that appears in the stream. Our method is simple to implement, computationally efficient and produces state-of-the-art results on datasets in German, English and Spanish.

Coreference resolution (CR) is a current problem in natural language processing (NLP) research and it is a key task in applications such as question answering, text summarization and information extraction for which text understanding is of crucial importance. We describe an implementation of coreference resolution tools for Latvian language, developed as a part of a tool chain for newswire text analysis but usable also as a separate, publicly available module. LVCoref is a rule based CR system that uses entity centric model that encourages the sharing of information across all mentions that point to the same real-world entity. The system is developed to provide starting ground for further experiments and generate a reference baseline to be compared with more advanced rule-based and machine learning based future coreference resolvers. It now reaches 66.6 F-score using predicted mentions and 78.1% F-score using gold mentions. This paper describes current efforts to create a CR system and to improve NER performance for Latvian. Task also includes creation of the corpus of manually annotated coreference relations.

In this paper we investigate how different dependency representations of a treebank influence the accuracy of the dependency parser trained on this treebank and the impact on several parser applications: named entity recognition, coreference resolution and limited semantic role labeling. For these experiments we use Latvian Treebank, whose native annotation format is dependency based hybrid augmented with phrase-like elements. We explore different representations of coordinations, complex predicates and punctuation mark attachment. Our experiments shows that parsers trained on the variously transformed treebanks vary significantly in their accuracy, but the best-performing parser as measured by attachment score not always leads to best accuracy for an end application.