The latest large language models (LLM) have significantly advanced natural language processing (NLP) capabilities across various tasks. However, their performance in low-resource languages, such as Latvian with 1.5 million native speakers, remains substantially underexplored due to both limited training data and the absence of comprehensive evaluation benchmarks. This study addresses this gap by conducting a systematic assessment of prominent open-source LLMs on natural language understanding (NLU) and natural language generation (NLG) tasks in Latvian. We utilize standardized high school centralized graduation exams as a benchmark dataset, offering relatable and diverse evaluation scenarios that encompass multiple-choice questions and complex text analysis tasks. Our experimental setup involves testing models from the leading LLM families, including Llama, Qwen, Gemma, and Mistral, with OpenAI’s GPT-4 serving as a performance reference. The results reveal that certain open-source models demonstrate competitive performance in NLU tasks, narrowing the gap with GPT-4. However, all models exhibit notable deficiencies in NLG tasks, specifically in generating coherent and contextually appropriate text analyses, highlighting persistent challenges in NLG for low-resource languages. These findings contribute to efforts to develop robust multilingual benchmarks and improve LLM performance in diverse linguistic contexts.

The following is a description of the RIGA team’s submissions for the SMM4H-2024 Task 1: Extraction and normalization of adverse drug events (ADEs) in English tweets. Our approach focuses on utilizing Large Language Models (LLMs) to generate data that enhances the fine-tuning of classification and Named Entity Recognition (NER) models. Our solution significantly outperforms mean and median submissions of other teams. The efficacy of our ADE extraction from tweets is comparable to the current state-of-the-art solution, established as the task baseline. The code for our method is available on GitHub (https://github.com/emukans/smm4h2024-riga)

The following is a description of the RIGA team’s submissions for the English track of the SemEval-2023 Task 2: Multilingual Complex Named Entity Recognition (MultiCoNER) II. Our approach achieves 17% boost in results by utilizing pre-existing Large-scale Language Models (LLMs), such as GPT-3, to gather additional contexts. We then fine-tune a pre-trained neural network utilizing these contexts. The final step of our approach involves meticulous model and compute resource scaling, which results in improved performance. Our results placed us 12th out of 34 teams in terms of overall ranking and 7th in terms of the noisy subset ranking. The code for our method is available on GitHub (https://github.com/emukans/multiconer2-riga).

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.

Described are our two entries “emukans” and “guntis” for the definition modeling track of CODWOE SemEval-2022 Task 1. Our approach is based on careful scaling of a GRU recurrent neural network, which exhibits double descent of errors, corresponding to significant improvements also per human judgement. Our results are in the middle of the ranking table per official automatic metrics.

The open-source SUMMA Platform is a highly scalable distributed architecture for monitoring a large number of media broadcasts in parallel, with a lag behind actual broadcast time of at most a few minutes. The Platform offers a fully automated media ingestion pipeline capable of recording live broadcasts, detection and transcription of spoken content, translation of all text (original or transcribed) into English, recognition and linking of Named Entities, topic detection, clustering and cross-lingual multi-document summarization of related media items, and last but not least, extraction and storage of factual claims in these news items. Browser-based graphical user interfaces provide humans with aggregated information as well as structured access to individual news items stored in the Platform’s database. This paper describes the intended use cases and provides an overview over the system’s implementation.

We present the latest version of the SUMMA platform, an open-source software platform for monitoring and interpreting multi-lingual media, from written news published on the internet to live media broadcasts via satellite or internet streaming.

The open-source SUMMA Platform is a highly scalable distributed architecture for monitoring a large number of media broadcasts in parallel, with a lag behind actual broadcast time of at most a few minutes. It assembles numerous state-of-the-art NLP technologies into a fully automated media ingestion pipeline that can record live broadcasts, detect and transcribe spoken content, translate from several languages (original text or transcribed speech) into English, recognize Named Entities, detect topics, cluster and summarize documents across language barriers, and extract and store factual claims in these news items. This paper describes the intended use cases and discusses the system design decisions that allowed us to integrate state-of-the-art NLP modules into an effective workflow with comparatively little effort.

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.

By addressing both text-to-AMR parsing and AMR-to-text generation, SemEval-2017 Task 9 established AMR as a powerful semantic interlingua. We strengthen the interlingual aspect of AMR by applying the multilingual Grammatical Framework (GF) for AMR-to-text generation. Our current rule-based GF approach completely covered only 12.3% of the test AMRs, therefore we combined it with state-of-the-art JAMR Generator to see if the combination increases or decreases the overall performance. The combined system achieved the automatic BLEU score of 18.82 and the human Trueskill score of 107.2, to be compared to the plain JAMR Generator results. As for AMR parsing, we added NER extensions to our SemEval-2016 general-domain AMR parser to handle the biomedical genre, rich in organic compound names, achieving Smatch F1=54.0%.

We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring. The platform contains a rich suite of low-level and high-level natural language processing technologies: automatic speech recognition of broadcast media, machine translation, automated tagging and classification of named entities, semantic parsing to detect relationships between entities, and automatic construction / augmentation of factual knowledge bases. Implemented on the Docker platform, it can easily be deployed, customised, and scaled to large volumes of incoming media streams.

The paper steps outside the comfort-zone of the traditional NLP tasks like automatic speech recognition (ASR) and machine translation (MT) to addresses two novel problems arising in the automated multilingual news monitoring: segmentation of the TV and radio program ASR transcripts into individual stories, and clustering of the individual stories coming from various sources and languages into storylines. Storyline clustering of stories covering the same events is an essential task for inquisitorial media monitoring. We address these two problems jointly by engaging the low-dimensional semantic representation capabilities of the sequence to sequence neural translation models. To enable joint multi-task learning for multilingual neural translation of morphologically rich languages we replace the attention mechanism with the sliding-window mechanism and operate the sequence to sequence neural translation model on the character-level rather than on the word-level. The story segmentation and storyline clustering problem is tackled by examining the low-dimensional vectors produced as a side-product of the neural translation process. The results of this paper describe a novel approach to the automatic story segmentation and storyline clustering problem.

Frame-semantic parsing is a kind of automatic semantic role labeling performed according to the FrameNet paradigm. The paper reports a novel approach for boosting frame-semantic parsing accuracy through the use of the C5.0 decision tree classifier, a commercial version of the popular C4.5 decision tree classifier, and manual rule enhancement. Additionally, the possibility to replace C5.0 by an exhaustive search based algorithm (nicknamed C6.0) is described, leading to even higher frame-semantic parsing accuracy at the expense of slightly increased training time. The described approach is particularly efficient for languages with small FrameNet annotated corpora as it is for Latvian, which is used for illustration. Frame-semantic parsing accuracy achieved for Latvian through the C6.0 algorithm is on par with the state-of-the-art English frame-semantic parsers. The paper includes also a frame-semantic parsing use-case for extracting structured information from unstructured newswire texts, sometimes referred to as bridging of the semantic gap.