byungdoh / llm_surprisalLinks
Surprisal calculation using HuggingFace LMs ("Frequency Explains the Inverse Correlation of Large Language Models’ Size, Training Data Amount, and Surprisal’s Fit to Reading Times," EACL24)
☆16Updated last year
Alternatives and similar repositories for llm_surprisal
Users that are interested in llm_surprisal are comparing it to the libraries listed below
Sorting:
- Structural Supervision & Human Psycholinguistic Data☆11Updated 4 years ago
- SAP Benchmark☆18Updated 9 months ago
- ☆12Updated 3 years ago
- Corpus of naturalistic stories with annotation and psycholinguistic measures☆57Updated 2 months ago
- A psycholinguistic modeling toolkit☆28Updated 2 weeks ago
- ☆15Updated 2 years ago
- A neural language model that estimates incremental processing complexity☆39Updated 3 years ago
- The Universal Decompositional Semantics (UDS) dataset and the Decomp toolkit☆57Updated 2 years ago
- ☆20Updated 3 years ago
- Diagnostic tests for linguistic capacities in language models☆66Updated 3 years ago
- Organized inventory of research using the Abstract Meaning Representation☆39Updated last week
- ☆22Updated 3 years ago
- Code and data for "A Systematic Assessment of Syntactic Generalization in Neural Language Models"☆28Updated 4 years ago
- A repository for the 2022 Inflection Shared Task☆9Updated 3 years ago
- Data and scripts for the proper evaluation of cross-lingual embeddings in multiple languages☆14Updated 5 years ago
- Unsupervised Grammar Induction with Combinatory Categorial Grammars☆10Updated 4 years ago
- Modular implementation of an AM dependency parser in AllenNLP.☆32Updated last year
- PERIN is Permutation-Invariant Semantic Parser developed for MRP 2020☆45Updated 2 years ago
- A package for handy processing of semantic graphs such as AMR, with a special focus on standardized evaluation☆24Updated 2 months ago
- Utility for behavioral and representational analyses of Language Models☆151Updated last week
- Scripts to evaluate scoped meaning representations☆20Updated 3 years ago
- A simple, Python-based, command-line runner for MGIZA++.☆11Updated 3 years ago
- ☆28Updated 7 months ago
- ☆12Updated 2 months ago
- Constituency parser for English and Chinese, built on the RNNG and In-Order parsers with BERT☆38Updated 5 years ago
- Code and CoarseWSD-20 datasets for "Language Models and Word Sense Disambiguation: An Overview and Analysis"☆25Updated 3 years ago
- Source code for CoNLL 2021 paper by Huebner et al. 2021☆19Updated 2 years ago
- ☆21Updated last year
- Twpipe is a pipeline toolkit that parses raw tweets into universal dependencies.☆28Updated 6 years ago
- ☆17Updated 3 weeks ago