Papers by Leonie Weissweiler
BabyLM’s First Constructions: Causal interventions provide a signal of learning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent work shows sensitivity to constructions in pretrained language models, but their relevance to human language learning is doubted. |
| Approach: | They use construction grammars to demonstrate sensitivity to constructions in pretrained language models. |
| Outcome: | The proposed models learn diverse constructions even hard cases that are superficially indistinguishable. |
UCxn: Typologically-Informed Annotation of Constructions Atop Universal Dependencies (2024.lrec-main)
Copied to clipboard
Leonie Weissweiler, Nina Böbel, Kirian Guiller, Santiago Herrera, Wesley Samuel Scivetti, Arthur Lorenzi, Nurit Melnik, Archna Bhatia, Hinrich Schütze, Lori Levin, Amir Zeldes, Joakim Nivre, William Croft, Nathan Schneider
| Challenge: | Grammatical constructions that convey meaning through a particular combination of several morphosyntactic elements are not labeled holistically. |
| Approach: | They propose to augment UD annotations with a ‘UCxn’ annotation layer for such meaning-bearing grammatical constructions and to approach this in a typologically informed way so that morphosyntactic strategies can be compared across languages. |
| Outcome: | The proposed annotation layer could be used to annotate meaning-bearing constructions across languages and to compare them across languages. |
How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives (2023.acl-short)
Copied to clipboard
| Challenge: | Recent studies show that intermediate layer distillation (ILD) objectives improve model compression, but a comprehensive evaluation of distillation objectives in both task-specific and task-agnostic settings is lacking. |
| Approach: | They propose to use knowledge distillation to improve model compression by transferring knowledge from one model to another. |
| Outcome: | The proposed framework improves on the task of QNLI with lower teacher layers and higher teacher layers. |
Verbing Weirds Language (Models): Evaluation of English Zero-Derivation in Five LLMs (2024.lrec-main)
Copied to clipboard
| Challenge: | Lexical-syntactic flexibility is a hallmark of English morphology . conversion involves placing a word with one part of speech in a non-prototypical context . |
| Approach: | They propose to test lexical-syntactic flexibility in the form of conversion . conversion is a process where a word with one part of speech is placed in a non-prototypical context . |
| Outcome: | The proposed task tests the ability of five language models to generalize over words with a non-prototypical part of speech. |
A Crosslingual Investigation of Conceptualization in 1335 Languages (2023.acl-long)
Copied to clipboard
Yihong Liu, Haotian Ye, Leonie Weissweiler, Philipp Wicke, Renhao Pei, Robert Zangenfeind, Hinrich Schütze
| Challenge: | Conceptualizer is a method that creates a bipartite directed alignment graph between source language concepts and sets of target language strings. |
| Approach: | They propose a method that creates a bipartite directed alignment graph between source language concepts and sets of target language strings. |
| Outcome: | The proposed method has good alignment accuracy across all languages and on 32 Swadesh concepts. |
SynthEval: Hybrid Behavioral Testing of NLP Models with Synthetic Evaluation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing frameworks for benchmarking in NLP often overestimate performance . however, manually creating a variety of test types requires significant human labor . |
| Approach: | They propose a framework that leverages large language models to generate a wide range of test types . they first generate sentences via LLMs and then identifies challenging examples . |
| Outcome: | The proposed framework overestimates performance on two classification tasks. |
MultiBLiMP 1.0: A Massively Multilingual Benchmark of Linguistic Minimal Pairs (2026.tacl-1)
Copied to clipboard
| Challenge: | MultiBLiMP 1.0 is a massively multilingual benchmark of linguistic minimal pairs covering 101 languages and 2 types of subject-verb agreement. |
| Approach: | They propose to use multilingual benchmarks to evaluate linguistic minimal pairs in 101 languages and 2 types of subject-verb agreement to create the minimal pairs. |
| Outcome: | The proposed benchmark covers 101 languages and 2 types of subject-verb agreement, and contains more than 128,000 minimal pairs. |
The better your Syntax, the better your Semantics? Probing Pretrained Language Models for the English Comparative Correlative (2022.emnlp-main)
Copied to clipboard
| Challenge: | Construction Grammar posits constructions as the central building blocks of language . human-like performance of pretrained language models on many NLP tasks has been alleged . |
| Approach: | They propose to use construction grammar to posit constructions as the central building blocks of language . they conduct experiments with three pretrained language models to examine their ability to classify and understand English comparative correlative . |
| Outcome: | The proposed models are able to recognise the English comparative correlative (CC) but fail to use its meaning. |
Constructions are Revealed in Word Distributions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Construction grammar posits that constructions are form-meaning pairings that are acquired through experience with language. |
| Approach: | They propose to use a RoBERTa model to model constructions as patterns of statistical affinity . they show that statistical affinity is likely an important, but partial, signal available to learners . |
| Outcome: | The proposed model shows that constructions will be revealed as patterns of statistical affinity . the proposed model is based on a model that is able to distinguish constructions from text . |
Counting the Bugs in ChatGPT’s Wugs: A Multilingual Investigation into the Morphological Capabilities of a Large Language Model (2023.emnlp-main)
Copied to clipboard
Leonie Weissweiler, Valentin Hofmann, Anjali Kantharuban, Anna Cai, Ritam Dutt, Amey Hengle, Anubha Kabra, Atharva Kulkarni, Abhishek Vijayakumar, Haofei Yu, Hinrich Schuetze, Kemal Oflazer, David Mortensen
| Challenge: | Existing studies on large language models (LLMs) ignore the remarkable ability of humans to generalize and focus only on English. |
| Approach: | They conduct the first rigorous analysis of the morphological capabilities of ChatGPT in four typologically varied languages. |
| Outcome: | The proposed model massively underperforms purpose-built systems, particularly in English. |
CaMEL: Case Marker Extraction without Labels (2022.acl-long)
Copied to clipboard
| Challenge: | Existing models for morphological case marking and semantic content are not isomorphic. |
| Approach: | They propose a model that extracts case markers from a multilingual corpus using a noun phrase chunker and an alignment system. |
| Outcome: | The proposed model can extract case markers in 83 languages and visualise similarities and differences between case systems and annotate fine-grained deep cases in languages where they are not overtly marked. |
Constructions Are So Difficult That Even Large Language Models Get Them Right for the Wrong Reasons (2024.lrec-main)
Copied to clipboard
| Challenge: | In this paper, we examine the ability of large language models (LLMs) to identify different meanings in sentences that are superficially similar. |
| Approach: | They propose a challenge dataset for NLP with large lexical overlap which minimises the possibility of models discerning entailment solely based on token distinctions. |
| Outcome: | The proposed model fails to distinguish between constructions with three classes of adjectives which cannot be distinguished by surface features. |
Crosslingual Transfer Learning for Low-Resource Languages Based on Multilingual Colexification Graphs (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing work on colexification patterns relies on annotated word lists, limiting scalability and usefulness in NLP. |
| Approach: | They propose two methods to train multilingual graphs from colexification patterns using an unannotated parallel corpus. |
| Outcome: | The proposed methods achieve high recall on CLICS and transfer learning in multilingual graphs. |