Croatia

In the light of recent developments in NLP, the problem of understanding and interpreting large language models has gained a lot of urgency. Methods developed to study this area are subject to considerable scrutiny. In this work, we take a closer look at one such method, the structural probe introduced by Hewitt and Manning (2019). We run a series of experiments involving multiple languages, focusing principally on the group of Slavic languages. We show that probing results can be seen as a reflection of linguistic classification, and conclude that multilingual BERT learns facts about languages and their groups.

EACL 2023

Is German secretly a Slavic language? What BERT probing can tell us about language groups

slavic languages

probing

bert

workshop paper

### Welcome to the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL) 
Continuing its mission of expanding and involving the science community of all European countries, EACL had selected the Ukrainian community for the 16th EACL, which took place online due to the COVID pandemic. Unfortunately, the ongoing war made the organisation in Kyiv impossible. Considering the importance of physical interaction among researchers, especially after the restrictions imposed by the COVID pandemic, in addition to an online mode, the conference will be held in Dubrovnik, Croatia, from 2 to 6 of May, 2023. The original aim of strengthening the connection with the Ukrainian community will not change as our program will feature a dedicated session and a workshop to highlight work on Ukrainian language technologies. As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

You need to register for the conference in order to access this site. Please visit https://2023.eacl.org/registration for more information.

As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

Despite the rapid recent progress in creating accurate and compact in-context learners, most recent work focuses on in-context learning (ICL) for tasks in English. However, the ability to interact with users of languages outside English presents a great potential for broadening the applicability of language technologies to non-English speakers.
In this work, we collect the infrastructure necessary for training and evaluation of ICL in a selection of Slavic languages: Czech, Polish, and Russian. We link a diverse set of datasets and cast these into a unified instructional format through a set of transformations and newly-crafted templates written purely in target languages. Using the newly-curated dataset, we evaluate a set of the most recent in-context learners and compare their results to the supervised baselines. Finally, we train, evaluate and publish a set of in-context learning models that we train on the collected resources and compare their performance to previous work.
We find that ICL models tuned in English are also able to learn some tasks from non-English contexts, but multilingual instruction fine-tuning consistently improves the ICL ability. We also find that the massive multitask training can be outperformed by single-task training in the target language, uncovering the potential for specializing in-context learners to the language(s) of their application.

Resources and Few-shot Learners for In-context Learning in Slavic Languages

This paper focuses on Named Entity Recognition for South-Slavic languages using pre-trained multilingual neural network models. We investigate whether the performance of the models for a target language can be improved by using data from closely related languages. The results show that this is not the case for the Slovene language, while for Croatian and Serbian, the results are better in selected cross-lingual settings. The most significant performance improvement is observed for the Serbian language, which has the smallest corpora, showing the potential of the method in less-resourced settings.

Analysis of Transfer Learning for Named Entity Recognition in South-Slavic Languages

Radiology reports are vital elements of directing patient care. They are usually delivered in free text form, which makes them prone to errors, such as omission in reporting radiological findings and using difficult-to-comprehend mental shortcuts. Although structured reporting is the recommended method, its adoption continues to be limited. Radiologists find structured reports too limiting and burdensome. In this paper, we propose the model, which is meant to preserve the benefits of free text, while moving towards a structured report. The model automatically parametrizes Polish radiology reports based on language models. The models are trained on a large dataset of 1200 chest computed tomography (CT) reports annotated by multiple medical experts reports with 44 observation tags. Experimental analysis shows that models based on language models are able to achieve satisfactory results despite being pre-trained on general domain corpora. Overall, the model achieves an F1 score of 81% and is able to successfully parametrize the most common radiological observations, allowing for potential adaptation in clinical practice. Our model is publicly available at {github.com/AleksanderObuchowski/PLRadIE.

Information Extraction from Polish Radiology Reports using Language Models

Can BERT eat RuCoLA? Topological Data Analysis to Explain

Named Entity Recognition (NER) is a fundamental NLP tasks with a wide range of practical applications. The performance of state-of-the-art NER methods depends on high quality manually anotated datasets which still do not exist for some languages. In this work we aim to remedy this situation in Slovak by introducing WikiGoldSK, the first sizable human labelled Slovak NER dataset. 
We benchmark it by evaluating state-of-the-art multilingual Pretrained Language Models and comparing it to the existing silver-standard Slovak NER dataset.
We also conduct few-shot experiments and show that training on a sliver-standard dataset yields better results. To enable future work that can be based on Slovak NER, we release the dataset, code, as well as the trained models publicly under permissible licensing terms at https://github.com/NaiveNeuron/WikiGoldSK.

WikiGoldSK: Annotated Dataset, Baselines and Few-Shot Learning Experiments for Slovak Named Entity Recognition

Pre-trained language models have been known to perpetuate biases from the underlying datasets to downstream tasks. However, these findings are predominantly based on monolingual language models for English, whereas there are few investigative studies of biases encoded in language models for languages beyond English. In this paper, we fill this gap by analysing gender bias in West Slavic language models. We introduce the first template-based dataset in Czech, Polish, and Slovak for measuring gender bias towards male, female and non-binary subjects. We complete the sentences using both mono- and multilingual language models and assess their suitability for the masked language modelling objective. Next, we measure gender bias encoded in West Slavic language models by quantifying the toxicity and genderness of the generated words. We find that these language models produce hurtful completions that depend on the subject's gender. Perhaps surprisingly, Czech, Slovak, and Polish language models produce more hurtful completions with men as subjects, which, upon inspection, we find is due to completions being related to violence, death, and sickness.

Measuring Gender Bias in West Slavic Language Models

This paper reports on the results of prelimi- nary experiments on the detection of persua- sion techniques in online news in Polish and Russian, using a taxonomy of 23 persuasion techniques. The evaluation addresses differ- ent aspects, namely, the granularity of the per- suasion technique category, i.e., coarse- (6 la- bels) versus fine-grained (23 labels), and the focus of the classification, i.e., at which level the labels are detected (subword, sentence, or paragraph). We compare the performance of mono- verus multi-lingual-trained state-of-the- art transformed-based models in this context.

On Experiments of Detecting Persuasion Techniques in Polish and Russian Online News: Preliminary Study

This presentation describes Adam Mickiewicz University’s (AMU) solution for the 4th Shared Task on SlavNER. The task involves the identification, categorization, and lemmatization of named entities in Slavic languages. Our approach involved exploring the use of foundation models for these tasks. In particular, we used models based on the popular BERT and T5 model architectures. Additionally, we used external datasets to further improve the quality of our models. Our solution obtained promising results, achieving high metrics scores in both tasks. We describe our approach and the results of our experiments in detail, showing that the method is effective for NER and lemmatization in Slavic languages. Additionally, our models for lemmatization will be available at: https://huggingface.co/amu-cai.

Exploring the Use of Foundation Models for Named Entity Recognition and Lemmatization Tasks in Slavic Languages

Large Language Models for Multilingual Slavic Named Entity Linking

Novel intent discovery automates the process of grouping similar messages (questions) to identify previously unknown intents. However, current research focuses on publicly available datasets which have only the question field and significantly differ from real-life datasets. This paper proposes methods to improve the intent discovery pipeline deployed in a large e-commerce platform. We show the benefit of pre-training language models on in-domain data: both self-supervised and with weak supervision. We also devise the best method to utilize the conversational structure (i.e., question and answer) of real-life datasets during fine-tuning for clustering tasks, which we call Conv. All our methods combined to fully utilize real-life datasets give up to 33pp performance boost over state-of-the-art Constrained Deep Adaptive Clustering (CDAC) (Lin et al., 2020) model for question only. By comparison CDAC model for the question data only gives only up to 13pp performance boost over the naive baseline.

Downloads

Next from EACL 2023

Resources and Few-shot Learners for In-context Learning in Slavic Languages