Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
News background linking is the problem of finding useful background resources that a reader of a given query article can read next for a better contextual understanding of the article. This problem was introduced and addressed mainly in the Text REtrieval Conference (TREC) during the years 2018–2021 (Soboroff, Huang & Harman, 2018; Soboroff, Huang & Harman, 2019a; Soboroff, Huang & Harman, 2020).1 Several methods were proposed to address this problem.
Stage 2: Paraphrasing CAsT dataset The aim of this stage is to generate raw and manual paraphrases to augment CAsT data by building a novel conversation paraphrase dataset. Neural models are used to generate the paraphrases. To implement the paraphrase generation model T5-Para, we fine-tune the T5 model using the Quora Question Pairs (QQP) dataset (Iyer, Dandekar & Csernai, 2017). QQP is one of the most popular existing datasets for question paraphrases.
News articles as sources of background knowledge A news background linking task was recently introduced as a new challenge in the news track in TREC 2018 (Soboroff, Huang & Harman, 2018), and as a follow-up task in TREC 2019 (Soboroff, Huang & Harman, 2019), and TREC 2020 (Soboroff, Huang & Harman, 2020). A number of teams participated in this challenge proposing different methods that are surveyed below.
Abstract Web search is commonly used by fact checking systems as a source of evidence for claim verification. In this work, we demonstrate that the task of retrieving pages useful for fact checking, called evidential pages, is indeed different from the task of retrieving topically relevant pages that are typically optimized by search engines; thus, it should be handled differently.
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.