Papers by Ori Ram
Few-Shot Question Answering by Pretraining Span Selection (2021.acl-long)
Copied to clipboard
| Challenge: | Pretraining models with recurring span selection are effective, but perform poorly in a few-shot setting. |
| Approach: | They propose recurring span selection scheme that asks model to select correct span in passage with multiple sets of recurring recurrings. |
| Outcome: | The proposed model achieves 72.7 F1 on multiple benchmarks while maintaining competitive performance in the high-resource setting. |
Cross-Lingual Alignment of Contextual Word Embeddings, with Applications to Zero-shot Dependency Parsing (N19-1)
Copied to clipboard
| Challenge: | Existing methods for multilingual transfer are limited by their dynamic nature. |
| Approach: | They propose a method that utilizes deep contextual embeddings, pretrained in an unsupervised fashion. |
| Outcome: | The proposed method outperforms the state-of-the-art on 6 languages, yielding an improvement of 6.8 LAS points on average. |
What Are You Token About? Dense Retrieval as Distributions Over the Vocabulary (2023.acl-long)
Copied to clipboard
| Challenge: | Dense retrieval models based on text representations have proven very effective, but when applied off-the-shelf they often experience a severe drop in performance. |
| Approach: | They propose to interpret the vector representations produced by dual encoders by projecting them into the model’s vocabulary space. |
| Outcome: | The proposed model significantly improves on the BEIR benchmark and in zero-shot settings. |
Transformer Language Models without Positional Encodings Still Learn Positional Information (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Using positional embeddings, Causal transformer language models learn an implicit notion of absolute positions. |
| Approach: | They propose to use positional embeddings to encode positional information in transformer language models. |
| Outcome: | The proposed model learns an implicit notion of absolute positions across datasets, model sizes, and sequence lengths. |
Coreference Resolution without Span Representations (2021.acl-short)
Copied to clipboard
| Challenge: | Pretraining has reduced many complex task-specific NLP models to simple lightweight layers. |
| Approach: | They propose a lightweight end-to-end coreference model that removes the dependency on span representations, handcrafted features, pruning heuristics, and more. |
| Outcome: | The proposed model performs competitively with the current standard model, while being simpler and more efficient. |
Generating Benchmarks for Factuality Evaluation of Language Models (2024.eacl-long)
Copied to clipboard
Dor Muhlgay, Ori Ram, Inbal Magar, Yoav Levine, Nir Ratner, Yonatan Belinkov, Omri Abend, Kevin Leyton-Brown, Amnon Shashua, Yoav Shoham
| Challenge: | Existing methods for factuality evaluation of LLM generation focus on facts sampled from the LM itself and might under-represent domain specific or rare facts. |
| Approach: | They propose a method that transforms a factual corpus into a benchmark evaluating an LM's propensity to generate true facts from the corpus . |
| Outcome: | The proposed framework transforms a factual corpus of interest into a benchmark evaluating an LM's propensity to generate true facts from the corpus vs. similar but incorrect statements. |
Learning to Retrieve Passages without Supervision (2022.naacl-main)
Copied to clipboard
| Challenge: | Dense retrievers for open domain question answering have been shown to achieve impressive performance by training on large datasets of question-passage pairs. |
| Approach: | They propose to use recurring spans to create pseudo examples for contrastive learning. |
| Outcome: | The proposed model outperforms all pretrained baselines on a wide range of ODQA datasets and is competitive with BM25, a strong sparse baseline. |
SenseBERT: Driving Some Sense into BERT (2020.acl-main)
Copied to clipboard
Yoav Levine, Barak Lenz, Or Dagan, Ori Ram, Dan Padnos, Or Sharir, Shai Shalev-Shwartz, Amnon Shashua, Yoav Shoham
| Challenge: | Existing approaches for self-supervision operate at word form level, which serves as a surrogate for the underlying semantic content. |
| Approach: | They propose a method to employ weak-supervision directly at the word sense level, without the use of human annotation. |
| Outcome: | The proposed model achieves significantly improved lexical understanding without human annotation on the ‘Word in Context’ task. |
In-Context Retrieval-Augmented Language Models (2023.tacl-1)
Copied to clipboard
| Challenge: | Existing RALM methods focus on modifying the LM architecture to facilitate incorporation of external information, complicating deployment. |
| Approach: | They propose to condition a language model on relevant documents from a grounding corpus during generation by conditioning on external knowledge sources. |
| Outcome: | The proposed method significantly improves language modeling performance and provides natural source attribution mechanism. |
Parallel Context Windows for Large Language Models (2023.acl-long)
Copied to clipboard
Nir Ratner, Yoav Levine, Yonatan Belinkov, Ori Ram, Inbal Magar, Omri Abend, Ehud Karpas, Amnon Shashua, Kevin Leyton-Brown, Yoav Shoham
| Challenge: | Existing efforts to address context window limitation for off-the-shelf LLMs involve training specialized architectures. |
| Approach: | They propose a method that carves a long context into chunks and restricts attention to apply only within each window. |
| Outcome: | The proposed method shows significant improvements on in-context learning tasks with diverse input and output spaces. |