Papers by Peter Izsak

6 papers
Optimizing Retrieval-augmented Reader Models via Token Elimination (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for ODQA use a retrieval-augmented language model . a generative model can cause a significant bottleneck in decoding time .
Approach: They propose to eliminate some of the retrieved information that might not contribute essential information to the answer generation process.
Outcome: The proposed method reduces run-time by up to 62.2% with only 2% reduction in performance and improves performance.
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.
CoTAR: Chain-of-Thought Attribution Reasoning with Multi-level Granularity (2024.findings-emnlp)

Copied to clipboard

Challenge: State-of-the-art QA systems employ Large Language Models (LLMs) however, these models tend to hallucinate information in their responses.
Approach: They propose an attribution-oriented Chain-of-Thought reasoning method to enhance attributions.
Outcome: The proposed method outperforms existing models on context enhanced question-answering datasets and shows that it can be used to improve accuracy.
Term Set Expansion based NLP Architect by Intel AI Lab (D18-2)

Copied to clipboard

Challenge: SetExpander is a corpus-based system for expanding a seed set of terms into a more complete set of words belonging to the same semantic class.
Approach: They propose a corpus-based system for expanding a seed set of terms into a more complete set of words that belong to the same semantic class.
Outcome: The proposed system can expand a seed set of terms into a more complete set of words belonging to the same semantic class.
How to Train BERT with an Academic Budget (2021.emnlp-main)

Copied to clipboard

Challenge: Large language models such as BERT are used in many NLP tasks, but their pretraining phase can be prohibitively expensive for startups and academic research groups.
Approach: They propose a recipe for pretraining a large language model in 24 hours using a low-end deep learning server.
Outcome: The proposed model can be trained on GLUE tasks at fraction of the cost of pretraining.
SetExpander: End-to-end Term Set Expansion Based on Multi-Context Term Embeddings (C18-2)

Copied to clipboard

Challenge: SetExpander is a corpus-based system for expanding a seed set of terms into a more complete set of words belonging to the same semantic class.
Approach: They propose to use a corpus-based system for expanding a seed set of terms into a more complete set of words that belong to the same semantic class.
Outcome: The proposed system can expand a seed set of terms, validate it, re-expand the expanded set and store it, thus simplifying the extraction of domain-specific fine-grained semantic classes.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations