Papers by Tanja Samardzic
DistaLs: a Comprehensive Collection of Language Distance Measures (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Existing work on how to measure distances between languages has focused on intuition and typological distance. |
| Approach: | They propose a toolkit that provides users with easy access to language distance measures. |
| Outcome: | The proposed toolkit provides easy access to a wide variety of language distance measures. |
Early Guessing for Dialect Identification (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Current research on dialect identification is model-centric, focusing on performance. |
| Approach: | They propose a data-centric approach to find the shortest input needed to make a plausible guess. |
| Outcome: | The proposed method generalizes across dialects and datasets with two shortening criteria. |
From characters to words: the turning point of BPE merges (2021.eacl-main)
Copied to clipboard
| Challenge: | morphological complexity is still a major challenge for NLP and the study of language. |
| Approach: | They perform a cross-linguistic comparison following incremental merges of BPE for 47 diverse languages. |
| Outcome: | The results show that language distributions are similar under specific levels of tokenization. |
Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasks (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) pre-trained on massive text data in many languages are preferred solution for various Natural Language processing tasks. |
| Approach: | They compare tokenization parity and information parity as representational biases in pre-trained models . they find TP is better predictor of performance on tasks reliant on syntactic and morphological cues . |
| Outcome: | The proposed model improves on dialect classification, topic classification, and extractive question answering tasks. |
A Measure for Transparent Comparison of Linguistic Diversity in Multilingual NLP Data Sets (2024.findings-naacl)
Copied to clipboard
| Challenge: | a new study aims to assess linguistic diversity of multilingual data sets against a reference language sample . linguistic diversity is typically measured as the number of languages included in the data set . but such measures do not consider structural properties of the included languages . |
| Approach: | They propose to measure linguistic diversity against a reference language sample to maximise linguistic diversity. |
| Outcome: | The proposed measure can be used to identify the types of languages that are not represented in a data set. |
Functional Lexicon in Subword Tokenization (2025.naacl-long)
Copied to clipboard
| Challenge: | Function units are hard to map across languages, while being the most frequent tokens. |
| Approach: | They analyze subword tokens in terms of their productivity and try to find thresholds that best distinguish function from content tokens. |
| Outcome: | The proposed method can be used to identify functional lexical units in low-resource languages with minimal annotated data. |
Subword Evenness (SuE) as a Predictor of Cross-lingual Transfer to Low-resource Languages (2022.emnlp-main)
Copied to clipboard
| Challenge: | English is the most natural choice for cross-lingual transfer, but it is often not the best choice for low-resource languages. |
| Approach: | They propose to use pre-trained multilingual models to improve performance in low-resource languages via cross-lingual transfer. |
| Outcome: | The results show that languages written in non-Latin and non-alphabetic scripts are the best choices for improving performance on Masked Language Modelling tasks in a diverse set of 30 low-resource languages. |
TeDDi Sample: Text Data Diversity Sample for Language Comparison and Multilingual NLP (2022.lrec-1)
Copied to clipboard
| Challenge: | a deep understanding of language is being achieved through increased access to data from minority and low-resource languages. |
| Approach: | They present a diversity sample of text data for language comparison and multilingual natural language processing. |
| Outcome: | The TeDDi sample features 89 languages based on the typological diversity sample in the World Atlas of Language Structures . |
Interpretability for Morphological Inflection: from Character-level Predictions to Subword-level Rules (2021.eacl-main)
Copied to clipboard
| Challenge: | Neural models for morphological inflection have recently attained very high results, but their interpretation remains challenging. |
| Approach: | They propose a linguistically-motivated variant to the encoder-decoder model with attention that incorporates a character-level cross-attention mechanism and a self-attention module over substrings of the input. |
| Outcome: | The proposed model performs well on three typologically-different languages and is highly interpretable. |