Papers by Assaf Toledo

4 papers
Automatic Argument Quality Assessment - New Datasets and Methods (D19-1)

Copied to clipboard

Challenge: 6.3k arguments were collected from contributors of various levels, and are released as part of this work.
Approach: They propose to use a language model to annotate arguments for argument ranking and argument-pair classification.
Outcome: The proposed methods outperform state-of-the-art methods in the argument ranking task and argument-pair classification task.
Benchmark Data and Evaluation Framework for Intent Discovery Around COVID-19 Vaccine Hesitancy (2023.findings-eacl)

Copied to clipboard

Challenge: As COVID-19 vaccines were rolled out, they were met with widespread hesitancy.
Approach: They propose a new framework for intent discovery that leverages existing intent classifiers to provide a real-world conversational dataset of conversations conducted by actual users with VIRA.
Outcome: The proposed framework enables users to find out what they are doing and why they are hesitant.
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.
Out of the Echo Chamber: Detecting Countering Debate Speeches (2020.acl-main)

Copied to clipboard

Challenge: Existing algorithms to detect articles that counter the arguments in debate speeches are unsuccessful, suggesting room for further research.
Approach: They propose a task to detect articles that counter the arguments made in debate speeches by annotating them from a dataset of 3,685 such speeches.
Outcome: The proposed algorithm can detect articles that counter the arguments made in debate speeches, and some are successful, but none are human-like.

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