--

Networking and refreshments.

By Bryan Wilie, Samuel Cahyawijaya, Junxian He, Pascale Fung

Abstract: Large language models (LLMs) trained on massive multilingual datasets hint at the formation of interlingual constructs--a shared region in the representation space. However, evidence regarding this phenomenon is mixed, leaving it unclear whether these models truly develop unified interlingual representations, or present a partially aligned constructs. We explore 31 diverse languages varying on their resource-levels, typologies, and geographical regions; and find that multilingual LLMs exhibit inconsistent cross-lingual alignments. To address this, we propose an interlingual representation framework identifying both the shared interlingual semantic region and fragmented components, existed due to representational limitations. We introduce Interlingual Local Overlap (ILO) score to quantify interlingual alignment by comparing the local neighborhood structures of high-dimensional representations. We utilize ILO to investigate the impact of single-language fine-tuning on the interlingual alignment in multilingual LLMs. Our results indicate that training exclusively on a single language disrupts the alignment in early layers, while freezing these layers preserves the alignment of interlingual representations, leading to improved cross-lingual generalization. These results validate our framework and metric for evaluating interlingual representation, and further underscore that interlingual alignment is crucial for scalable multilingual learning.

--

Lunch and poster browsing.

Poster session I.

By Robert Forkel

Abstract: One of the key contributions typology can make to multilingual NLP is a fuller picture of the diversity of the world's languages. This diversity is also reflected in widely varying documentation across languages. Thus, informing computational approaches to language processing by this diversity requires operationalizing a variety of data types describing very different languages. Getting a computational grasp on cross-linguistic information has been the main motivation behind CLDF - the Cross-Linguistic Data Formats. This talk will explore the eco-system of cross-linguistic data that is now opened up via CLDF

By Amanda Kann

Abstract: Gradient, token-level measures of word order preferences within a language are useful both for cross-linguistic comparison in linguistic typology and for multilingual NLP applications. However, such measures might not be representative of general language use when extracted from translated corpora, due to noise introduced by structural effects of translation. We attempt to quantify this uncertainty in a case study of subject/verb order statistics extracted from a parallel corpus of parliamentary speeches in 21 European languages. We find that word order proportions in translated texts generally resemble those extracted from non-translated texts, but tend to skew somewhat toward the dominant word order of the target language. We also investigate the potential presence of underlying source language-specific effects, but find that they do not sufficiently explain the variation across translations.

Networking and refreshments.

By Lisa Bylinina

Abstract: One of the central questions in linguistic typology is: What constrains the space of natural languages? In a somewhat narrower formulation: How do different grammatical properties of a language relate to each other, and why are some combinations of features that would, in principle, be possible, in fact not attested? I would like to put these questions in the context of recent language models. Can (L)LMs help us understand interconnections within linguistic grammatical systems? I will argue for a moderately optimistic view and suggest some ways to make progress in this direction, with a focus on the linguistic generalisations (L)LMs make under different training conditions. My goal is to encourage discussion about the usefulness of (L)LMs for theoretical and typological linguistic research.

Poster session II.

By Antoni Brosa Rodríguez, M. Dolores Jiménez López

Abstract: This study explores the impact of annotation inconsistencies in Universal Dependencies (UD) treebanks on typological research in computational linguistics. UD provides a standardized framework for cross-linguistic annotation, facilitating large-scale empirical studies on linguistic diversity and universals. However, despite rigorous guidelines, annotation inconsistencies persist across treebanks. The objective of this paper is to assess how these inconsistencies affect typological universals, linguistic descriptions, and complexity metrics. We analyze systematic annotation errors in multiple UD treebanks, focusing on morphological features. Case studies on Spanish and Dutch demonstrate how differing annotation decisions within the same language create contradictory typological profiles. We classify the errors into two main categories: overgeneration errors (features incorrectly annotated, since do not actually exist in a language) and data omission errors (inconsistent or incomplete annotation of features that do exist). Our results show that these inconsistencies significantly distort typological analyses, leading to false generalizations and miscalculations of linguistic complexity. We propose methodological safeguards for typological research using UD data. Our findings highlight the need for methodological improvements to ensure more reliable cross-linguistic generalizations in computational typology.

By Gerhard Jäger

Abstract: Computational phylogenetics has become an established tool in historical linguistics, with many language families now analyzed using likelihood-based inference. However, standard approaches rely on expert-annotated cognate sets, which are sparse, labor-intensive to produce, and limited to individual language families. This paper explores alternatives by comparing the established method to two fully automated methods that extract phylogenetic signal directly from lexical data. One uses automatic cognate clustering with unigram/concept features; the other applies multiple sequence alignment (MSA) derived from a pair-hidden Markov model. Both are evaluated against expert classifications from Glottolog and typological data from Grambank. Also, the intrinsic strengths of the phylogenetic signal in the characters are compared. Results show that MSA-based inference yields trees more consistent with linguistic classifications, better predicts typological variation, and provides a clearer phylogenetic signal, suggesting it as a promising, scalable alternative to traditional cognate-based methods. This opens new avenues for global-scale language phylogenies beyond expert annotation bottlenecks.

By Barend Beekhuizen

Abstract: This paper presents a computational method for token-level lexical semantic comparative research in an original text setting, as opposed to the more common massively parallel setting. Given a set of (non-massively parallel) bitexts, the method consists of leveraging pre-trained contextual vectors in a reference language to induce, for a token in one target language, the lexical items that all other target languages would have used, thus simulating a massively parallel set-up. The method is evaluated on its extraction and induction quality, and the use of the method for lexical semantic typological research is demonstrated.

Thank you for joining SIGTYP!