2 citations · 2 across the 9 of their papers we have counts for
9 papers · 1 filter
Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model
Lisa Bylinina
A language model normally begins training with random word embeddings: whatever 'banana' means must be learned from training corpora. I implement St. Augustine's picture of word le…
Model Merging to Maintain Language-Only Performance in Developmentally Plausible Multimodal Models
Ece Takmaz, Lisa Bylinina, Jakub Dotlacil
State-of-the-art vision-and-language models consist of many parameters and learn from enormous datasets, surpassing the amounts of linguistic data that children are exposed to as t…
Are BabyLMs Second Language Learners?
Lukas Edman, Lisa Bylinina, Faeze Ghorbanpour +1
This paper describes a linguistically-motivated approach to the 2024 edition of the BabyLM Challenge (Warstadt et al. 2023). Rather than pursuing a first language learning (L1) par…
Individuation in Neural Models with and without Visual Grounding
Alexey Tikhonov, Lisa Bylinina, Ivan P. Yamshchikov
We show differences between a language-and-vision model CLIP and two text-only models - FastText and SBERT - when it comes to the encoding of individuation information. We study la…
Black Big Boxes: Tracing Adjective Order Preferences in Large Language Models
Jaap Jumelet, Lisa Bylinina, Willem Zuidema +1
In English and other languages, multiple adjectives in noun phrases follow intricate ordering patterns. These patterns have been widely studied in linguistics and provide a useful…
Too Much Information: Keeping Training Simple for BabyLMs
Lukas Edman, Lisa Bylinina
This paper details the work of the University of Groningen for the BabyLM Challenge. We follow the idea that, like babies, language models should be introduced to simpler concepts…
Leverage Points in Modality Shifts: Comparing Language-only and Multimodal Word Representations
Aleksey Tikhonov, Lisa Bylinina, Denis Paperno
Multimodal embeddings aim to enrich the semantic information in neural representations of language compared to text-only models. While different embeddings exhibit different applic…
Connecting degree and polarity: An artificial language learning study
Lisa Bylinina, Alexey Tikhonov, Ekaterina Garmash
We investigate a new linguistic generalization in pre-trained language models (taking BERT (Devlin et al., 2019) as a case study). We focus on degree modifiers (expressions like sl…
Transformers in the loop: Polarity in neural models of language
Lisa Bylinina, Alexey Tikhonov
Representation of linguistic phenomena in computational language models is typically assessed against the predictions of existing linguistic theories of these phenomena. Using the…