Papers by Chen Shani
Rethinking Word Similarity: Semantic Similarity through Classification Confusion (2025.naacl-long)
Copied to clipboard
| Challenge: | Word similarity measures cannot capture context-dependent, asymmetrical, polysemous nature of semantic similarity. |
| Approach: | They propose a new measure of similarity that reframes semantic similarity in terms of feature-based classification confusion. |
| Outcome: | The proposed model is comparable to cosine similarity in matching human similarity judgments across several datasets and can measure similarity using predetermined features of interest. |
Beyond Tokens: Concept-Level Training Objectives for LLMs (2026.eacl-short)
Copied to clipboard
| Challenge: | Large language models (LLMs) are trained with a surprisingly narrow objective: predicting the next token in a sequence. |
| Approach: | They propose a shift from token-level to concept-level prediction where concepts group multiple surface forms of the same idea. |
| Outcome: | The proposed model improves on human-level models on diverse NLP benchmarks. |
Towards Concept-Aware Large Language Models (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Concepts play a pivotal role in various human cognitive functions, including reasoning and communication. |
| Approach: | They analyze how well contemporary large language models capture human concepts and their structure . they propose a method for pretraining LLMs using concepts and a simpler approach . |
| Outcome: | The proposed method matches human intuition and improves robustness of predictions. |
FAME: Flexible, Scalable Analogy Mappings Engine (2023.emnlp-main)
Copied to clipboard
| Challenge: | Most work on computational analogy relies heavily on complex, manually crafted input. |
| Approach: | They propose to use commonsense representations to identify mappings between entities and use them to interpret their output. |
| Outcome: | The proposed model outperforms human models on large analogy problems and outperfies human predictions. |
🧑‍🍳 Cooking Up Creativity: Enhancing LLM Creativity through Structured Recombination (2026.tacl-1)
Copied to clipboard
| Challenge: | Large Language Models excel at many tasks, yet struggle to generate truly creative ideas. |
| Approach: | They propose a novel approach that enhances Large Language Models' creativity by manipulating structured representations of existing ideas. |
| Outcome: | The proposed model outperforms GPT-4o in novelty and diversity and outperformed GPT-0 in creative generation. |
Language (Re)modelling: Towards Embodied Language Understanding (2020.acl-main)
Copied to clipboard
| Challenge: | Despite the rapid progress in NLU, current systems lack the rich mental representations that people use for language understanding. |
| Approach: | They propose an approach to representation and learning based on the tenets of embodied cognitive linguistics (ECL) they propose a system architecture along with a roadmap towards realizing this vision. |
| Outcome: | The proposed approach will improve the performance of existing systems and provide a roadmap towards realizing this vision. |
How Did This Get Funded?! Automatically Identifying Quirky Scientific Achievements (2021.acl-long)
Copied to clipboard
| Challenge: | Humor is an important social phenomenon, serving complex social and psychological functions. |
| Approach: | They propose a novel algorithm for automatically detecting funny scientific papers . they use a dataset containing thousands of funny papers to learn classifiers . |
| Outcome: | The proposed task is based on a dataset containing thousands of funny scientific papers . it is a novel task that can be automated and improves on existing methods . |