Papers by Filip Miletić
Understanding Computational Models of Semantic Change: New Insights from the Speech Community (2023.emnlp-main)
Copied to clipboard
| Challenge: | Using type-level and token-level word embeddings, we obtain semantic change estimates from type-based models and empirical linguistic properties. |
| Approach: | They analyze 40 target words with type-level and token-level word embeddings, empirical linguistic properties, and speaker-provided acceptability ratings and qualitative remarks. |
| Outcome: | The proposed models are able to describe the sociolinguistic issue of contact-induced semantic shifts in Quebec English and are validated by qualitative interviews with 15 speakers from Montreal. |
Gender Identity in Pretrained Language Models: An Inclusive Approach to Data Creation and Probing (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Pretrained language models encode binary gender information of text authors, raising the risk of skewed representations and downstream harms. |
| Approach: | They use a corpus of YouTube transcripts from transgender, cisgender and non-binary speakers to examine whether pretrained language models encode binary gender information. |
| Outcome: | The proposed model encodes gender information for all gender identities but to different extents. |
What Can Diachronic Contexts and Topics Tell Us about the Present-Day Compositionality of English Noun Compounds? (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods to determine the semantic relatedness between compounds and constituents have applied a synchronic perspective, but this study examines what diachronic changes in contexts and semantic topics reveal about the compounds’ present-day compositionality. |
| Approach: | They propose to use two diachronic vector spaces to model compositional patterns between compounds with low and high present-day compositionality. |
| Outcome: | The proposed model performs on par with co-occurrence space and captures similar information. |
Modeling the Evolution of English Noun Compounds with Feature-Rich Diachronic Compositionality Prediction (2025.acl-long)
Copied to clipboard
| Challenge: | Empirical research directly addressing these issues is limited to a small number of studies suggesting that compounding is a highly productive process. |
| Approach: | They represent English noun compounds as vectors of time-specific values and implement a set of features to classify them for present-day compositionality and assess the informativeness of the corresponding linguistic patterns. |
| Outcome: | The proposed method captures relevant and complementary information across approaches and shows that low-compositional meanings are reflected by a parallel drop in compositionality and sustained semantic change. |
Multi-word Measures: Modeling Semantic Change in Compound Nouns (2025.findings-acl)
Copied to clipboard
| Challenge: | Compound words provide a multifaceted challenge for diachronic models of semantic change . novel sense-targeting approach targets both noun compounds and their constituent parts . |
| Approach: | They propose a dataset of relatedness judgements of noun compounds in English and german . they use contrasting vector representations to evaluate their ability to cluster example sentence pairs . |
| Outcome: | The proposed approach captures diachronic meaning changes for multi-word expressions without condensing individual senses into an aggregate value. |
Spanish Dialect Classification: A Comparative Study of Linguistically Tailored Features, Unigrams and BERT Embeddings (2025.acl-srw)
Copied to clipboard
| Challenge: | Existing models for automatic dialect classification use bag-of-words unigram features instead of linguistic knowledge. |
| Approach: | They propose to use dialect-specific unigram features to train machine learning models . they also use a transformer-based model to find potentially useful dialect-related features . |
| Outcome: | The proposed model outperforms existing models but sacrifices explainability and interpretability. |