Search Results for author:
Found 23 papers, 10 papers with code
CMCL 2021 Shared Task on Eye-Tracking Prediction
The goal of the task is to predict 5 different token- level eye-tracking metrics of the Zurich Cognitive Language Processing Corpus (ZuCo).
CMCL 2022 Shared Task on Multilingual and Crosslingual Prediction of Human Reading Behavior
We present the second shared task on eye-tracking data prediction of the Cognitive Modeling and Computational Linguistics Workshop (CMCL).
How LLMs Learn: Tracing Internal Representations with Sparse Autoencoders
Large Language Models (LLMs) demonstrate remarkable multilingual capabilities and broad knowledge.
If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation?
Recent work in computational psycholinguistics has revealed intriguing parallels between attention mechanisms and human memory retrieval, focusing primarily on Transformer architectures that operate on token-level representations.
Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition
Large language models exhibit general linguistic abilities but significantly differ from humans in their efficiency of language acquisition.
BabyLM Challenge: Exploring the Effect of Variation Sets on Language Model Training Efficiency
While current large language models have achieved a remarkable success, their data efficiency remains a challenge to overcome.
Is Structure Dependence Shaped for Efficient Communication?: A Case Study on Coordination
The results demonstrate that the language with the structure-dependent reduction operation is significantly more communicatively efficient than the counterfactual languages.
Can Language Models Induce Grammatical Knowledge from Indirect Evidence?
What kinds of and how much data is necessary for language models to induce grammatical knowledge to judge sentence acceptability?
LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs
This paper introduces LLM-jp, a cross-organizational project for the research and development of Japanese large language models (LLMs).
Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision
Syntactic Language Models (SLMs) can be trained efficiently to reach relatively high performance; however, they have trouble with inference efficiency due to the explicit generation of syntactic structures.
Emergent Word Order Universals from Cognitively-Motivated Language Models
The world's languages exhibit certain so-called typological or implicational universals; for example, Subject-Object-Verb (SOV) languages typically use postpositions.
Psychometric Predictive Power of Large Language Models
In other words, pure next-word probability remains a strong predictor for human reading behavior, even in the age of LLMs.
JCoLA: Japanese Corpus of Linguistic Acceptability
In this paper, we introduce JCoLA (Japanese Corpus of Linguistic Acceptability), which consists of 10, 020 sentences annotated with binary acceptability judgments.
Composition, Attention, or Both?
In this paper, we propose a novel architecture called Composition Attention Grammars (CAGs) that recursively compose subtrees into a single vector representation with a composition function, and selectively attend to previous structural information with a self-attention mechanism.
Context Limitations Make Neural Language Models More Human-Like
Language models (LMs) have been used in cognitive modeling as well as engineering studies -- they compute information-theoretic complexity metrics that simulate humans' cognitive load during reading.
Modeling Human Sentence Processing with Left-Corner Recurrent Neural Network Grammars
In computational linguistics, it has been shown that hierarchical structures make language models (LMs) more human-like.
Lower Perplexity is Not Always Human-Like
Overall, our results suggest that a cross-lingual evaluation will be necessary to construct human-like computational models.
Effective Batching for Recurrent Neural Network Grammars
However, RNNGs are known to be harder to scale due to the difficulty of batched training.
Design of BCCWJ-EEG: Balanced Corpus with Human Electroencephalography
Importantly, this inter-fertilization between NLP, on one hand, and the cognitive (neuro)science of language, on the other, has been driven by the language resources annotated with human language processing data.
Inverting and Modeling Morphological Inflection
Previous {``}wug{''} tests (Berko, 1958) on Japanese verbal inflection have demonstrated that Japanese speakers, both adults and children, cannot inflect novel present tense forms to {``}correct{''} past tense forms predicted by rules of existent verbs (de Chene, 1982; Vance, 1987, 1991; Klafehn, 2003, 2013), indicating that Japanese verbs are merely stored in the mental lexicon.
Modeling Hierarchical Syntactic Structures in Morphological Processing
Sentences are represented as hierarchical syntactic structures, which have been successfully modeled in sentence processing.
