paper-with-me

Papers

Committed Belief Tagging on the Factbank and LU Corpora: A Comparative Study

2015-06-01 · WS 2015 6 · Gregory Werner, Vinodkumar Prabhakaran, Mona Diab, Owen Rambow
📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Using Hedge Detection to Improve Committed Belief Tagging

2018-06-01 · WS 2018 6 · Morgan Ulinski, Seth Benjamin, Julia Hirschberg

We describe a novel method for identifying hedge terms using a set of manually constructed rules. We present experiments adding hedge features to a committed belief system to improve classification. We compare performanc…

General ClassificationSentence Classification

Zero-Shot Belief: A Hard Problem for LLMs

2025-02-12 · John Murzaku, Owen Rambow

We present two LLM-based approaches to zero-shot source-and-target belief prediction on FactBank: a unified system that identifies events, sources, and belief labels in a single pass, and a hybrid approach that uses a fi…

Event Detection

Re-Examining FactBank: Predicting the Author’s Presentation of Factuality

2022-10-01 · COLING 2022 10 · John Murzaku, Peter Zeng, Magdalena Markowska, Owen Rambow

We present a corrected version of a subset of the FactBank data set. Previously published results on FactBank are no longer valid. We perform experiments on FactBank using multiple training paradigms, data smoothing tech…

valid

Detecting Level of Belief in Chinese and Spanish

2016-12-01 · WS 2016 12 · Juan Pablo Colomer, Keyu Lai, Owen Rambow

There has been extensive work on detecting the level of committed belief (also known as {``}factuality{''}) that an author is expressing towards the propositions in his or her utterances. Previous work on English has rev…

BeSt: The Belief and Sentiment Corpus

2022-06-01 · LREC 2022 6 · Jennifer Tracey, Owen Rambow, Claire Cardie, Adam Dalton 외

We present the BeSt corpus, which records cognitive state: who believes what (i.e., factuality), and who has what sentiment towards what. This corpus is inspired by similar source-and-target corpora, specifically MPQA an…