Papers by Lisa Beinborn

11 papers
Multilingual Language Models Predict Human Reading Behavior (2021.naacl-main)

Copied to clipboard

Challenge: Recent studies show that cognitively motivated "attention" mechanism in neural models is not a good indicator for relative importance.
Approach: They compare the performance of language-specific and multilingual pretrained transformer models to predict reading time measures reflecting natural human sentence processing.
Outcome: The proposed models predict reading time measures on Dutch, English, German, and Russian texts.
Multimodal Grounding for Language Processing (C18-1)

Copied to clipboard

Challenge: Recent developments in multimodal processing facilitate conceptual grounding of language.
Approach: They analyze multimodal processing to examine the benefits and challenges of multimodal grounding . they focus on multimodal linguistic grounding of verbs which play a crucial role in compositional power of language.
Outcome: The proposed methods improve the cognitive models of human information processing and address the challenges that arise.
Vocabulary Shapes Cross-Lingual Variation of Word-Order Learnability in Language Models (2026.acl-long)

Copied to clipboard

Challenge: a coarse distinction between free- and fixed-word-order languages does not explain cross-lingual variation . aaron e. smith: human languages have emerged over millennia through communicative and cognitive constraints . but, within those universally shared bounds, languages exhibit striking typological diversity .
Approach: They propose to train transformer language models on a spectrum of synthetic word-order variants of natural languages.
Outcome: a new study shows that word order irregularities raise model surprisal, but only weakly affects learnability . the study also shows that vocabulary structure emerges as a key driver of word-order learnability across languages.
Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods (2023.emnlp-main)

Copied to clipboard

Challenge: Feature attribution scores are used to explain the prediction of a text classifier to users by highlighting a k number of tokens.
Approach: They propose to determine the number of optimal k tokens that should be displayed from sequential properties of attribution scores.
Outcome: The proposed method is dynamic across sentences, method-agnostic, and deals with sentence length bias.
Mitigating Frequency Bias and Anisotropy in Language Model Pre-Training with Syntactic Smoothing (2024.emnlp-main)

Copied to clipboard

Challenge: Language models rely on frequency information because they maximize the likelihood of tokens during training.
Approach: They propose a method for quantifying the frequency bias of a language model by assessing sentence-level perplexity with respect to token-level frequency.
Outcome: The proposed method reduces the frequency bias of a language model by inducing a syntactic prior over token representations during pre-training.
Generating Image Descriptions via Sequential Cross-Modal Alignment Guided by Human Gaze (2020.emnlp-main)

Copied to clipboard

Challenge: a long tradition of cognitive studies shows that the interplay between language and vision is complex.
Approach: They propose an approach to image description generation where visual processing is modelled sequentially.
Outcome: The proposed model exploits gaze-driven attention to produce better descriptions . it sheds light on human cognitive processes by comparing different ways of aligning gaze with language production.
The Role of Syntactic Span Preferences in Post-Hoc Explanation Disagreement (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for post-hoc explanations for transformer models disagree with each other . disagreement is often overlooked and the reasons for disagreement are not investigated .
Approach: They propose to use a dynamic *k* approach to estimate syntactic spans to improve agreement between different methods.
Outcome: The proposed method better agrees on syntactic span level, especially for the methods that agree the least with other methods.
Relative Importance in Sentence Processing (2021.acl-short)

Copied to clipboard

Challenge: In natural language processing, the relative importance of words is usually interpreted with respect to a specific task.
Approach: They compare the relative importance of words in English language processing by humans and neural language models by using saliency methods.
Outcome: The proposed method could be used to interpret neural language models.
Probing Multilingual BERT for Genetic and Typological Signals (2020.coling-main)

Copied to clipboard

Challenge: Recent cross-lingual models provide representations for about 100 languages and vary in their training objectives.
Approach: They probe the layers in multilingual BERT for phylogenetic and geographic language signals across 100 languages and compute language distances based on the mBERT representations.
Outcome: The proposed model is best explained by phylogenetic and worst by structural factors and correlates with published ranked lists based on linguistic approaches.
Cross-Lingual Transfer of Cognitive Processing Complexity (2023.findings-eacl)

Copied to clipboard

Challenge: Recent studies indicate that multilingual language models utilize structural similarities between languages to facilitate cross-lingual transfer.
Approach: They propose a multilingual model that uses structural similarities between languages to facilitate cross-lingual transfer by a meaningful bias towards sentence length and cross-linguistic differences.
Outcome: The proposed model can predict varied patterns for 13 languages, despite being fine-tuned only on English data.
Analyzing Cognitive Plausibility of Subword Tokenization (2023.emnlp-main)

Copied to clipboard

Challenge: Existing evaluations of subword tokenization focus on engineering criteria such as compression rate . a recent study evaluated subwords for their cognitive plausibility in languages with limited vocabulary size .
Approach: They propose a new evaluation paradigm that focuses on the cognitive plausibility of subword tokenization.
Outcome: The proposed tokenization algorithm yields less cognitively plausible tokenization behavior and worse coverage of derivational morphemes than previous evaluations.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations