Papers by Boaz Carmeli
Concept-Best-Matching: Evaluating Compositionality In Emergent Communication (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation methods do not expose compositionality of emergent communication . compositionality is a trait that enables the construction of complex meanings from the meaning of parts. |
| Approach: | They propose to find best-match between emergent words and natural language concepts to assess compositionality of emergentic communication. |
| Outcome: | The proposed algorithm provides a global score and translation-map between emergent words and natural language concepts. |
Will it Merge? On The Causes of Model Mergeability (2026.findings-acl)
Copied to clipboard
| Challenge: | Model merging has emerged as a promising technique for combining fine-tuned models into a single expert model without retraining. |
| Approach: | They propose a model merging technique that preserves weak model knowledge . they define mergeability as a property of model updates that captures how well they retain trained knowledge when merged with other model updates. |
| Outcome: | The proposed method preserves weak knowledge in the base model. |
Balancing via Generation for Multi-Class Text Classification Improvement (2020.findings-emnlp)
Copied to clipboard
| Challenge: | balancing is a known technique for improving classification performance . balancy is based on a balancing policy and a text generation mechanism . |
| Approach: | They propose a balancing-via-generation framework that augments a dataset for more balanced distribution by using a text generation mechanism. |
| Outcome: | The proposed framework can augment a dataset for more balanced distribution while under-sampling others. |
More Bang for your Context: Virtual Documents for Question Answering over Long Documents (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models struggle to utilize long contexts efficiently, resulting in a question answering problem. |
| Approach: | They propose a method to generate a short document that contains the most relevant parts for a given context window. |
| Outcome: | The proposed method improves the QA task by providing a short and focused VDoc to the LLM while keeping the context window full. |
Exploration of the Usage of Color Terms by Color-blind Participants in Online Discussion Platforms (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on the role of sensory vs. linguistic input in the way we acquire and use language have not explored the relative effects of various factors on our linguistic system. |
| Approach: | They propose to use a newly curated dataset to examine the conceptual perception of colors by color-blind speakers. |
| Outcome: | The findings shed some new and interesting light on the role of sensory experience on our linguistic system. |
Unsupervised FAQ Retrieval with Question Generation and BERT (2020.acl-main)
Copied to clipboard
| Challenge: | Frequently Asked Questions (FAQ) retrieval requires labeled datasets for training neural models. |
| Approach: | They propose to exploit FAQ pairs to train two BERT models that match user queries to FAQ answers and questions. |
| Outcome: | The proposed model outperforms supervised models on existing datasets and is on par with existing dataset. |