Papers by Michal Jacovi

6 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.
A Dataset of General-Purpose Rebuttal (D19-1)

Copied to clipboard

Challenge: a key element in argumentation is rebuttal, the ability to contest an argument by presenting a counter-argument.
Approach: They propose a method based on general rebuttal arguments to produce a critical response to a long argumentative text.
Outcome: The proposed method overcomes the need for topic-specific arguments to be provided . it allows creating responses beyond the scope of topics for which specific arguments are available .
Listening Comprehension over Argumentative Content (D18-1)

Copied to clipboard

Challenge: In argumentation domain, people are exposed directly to audio (or the video), without access to a written version.
Approach: They present a task for machine listening comprehension in the argumentation domain and a dataset in English.
Outcome: The proposed task is based on 200 speeches arguing for or against 50 controversial topics and uses baseline methods to address it.
Crowd-sourcing annotation of complex NLU tasks: A case study of argumentative content annotation (D19-59)

Copied to clipboard

Challenge: Recent advances in machine reading and listening comprehension involve the annotation of long texts.
Approach: They propose a way to perform a sentence-by-sentence annotation task with crowd annotators.
Outcome: The proposed approach can be used to identify claims in a debate speech.
A Recorded Debating Dataset (L18-1)

Copied to clipboard

Challenge: Existing research in computational argumentation and debating technologies focuses on argumentation mining, but other tasks are being addressed as well.
Approach: They describe a dataset of debating speeches in English that is used for research . they use an automatic speech recognition system to produce a more "nLP-friendly" text .
Outcome: The proposed dataset contains 60 speeches on various controversial topics, each in five formats corresponding to different stages in production.
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