Recognizing textual entailment: Rational, evaluation and approaches – Erratum

By Ido Dagan, William B. Dolan, Bernardo Magnini, Dan Roth. 2010

133 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Unifying Question Answering and Text Classification via Span Extraction (2019, background): “Finally, we note, perhaps surprisingly, that question answering datasets (SQuAD and TriviaQA) improve performance of some of the classiﬁcation tasks. from the Wiki version of TriviaQA) and RTE (pre-trained from any of the three datasets).”
The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only (2023, neutral): “Tasks Type Random small core main ext HellaSwag (Zellers et al., 2019) Sentence completion 25.0 ✓ ✓ ✓ ✓ LAMBADA (Paperno et al., 2016) Sentence completion 0.0 ✓ ✓ ✓ Winogrande (Sakaguchi et al., 2021) Coreference resolution 50.0 ✓ ✓ ✓ ✓ PIQA (Bisk et al., 2020) Multiple-choice question answering 50.”
Answering Complex Questions Using Open Information Extraction (2017, methodology): “Unlike standard alignment models used for tasks such as Recognizing Textual Entailment (RTE) (Dagan et al., 2010), however, we must score alignments between a set Tqa ∪ T ′ qa of structured tuples and a (potentially multi-sentence) multiple-choice question qa.”
Read + Verify: Machine Reading Comprehension with Unanswerable Questions (2018, background): “Recognizing textual entailment (RTE) (Dagan et al., 2010; Marelli et al., 2014), or known as natural language inference (NLI) (Bowman et al., 2015), requires systems to understand entailment, contradiction or semantic neutrality between two sentences.”
From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project (2019, methodology): “Unlike standard alignment models used for tasks such as Recognizing Textual Entailment (RTE) (Dagan et al., 2010), however, we must score alignments between the tuples retrieved from the two sources above, T qa ∪ T qa , and a (potentially multi-sentence) multiple choice question qa .”
Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation (2018, background): “This continues an aspect of the initial RTE collection, designed to be representative of downstream tasks like QA, MT, and IR (Dagan et al., 2010).”
A Survey on Natural Language Processing for Fake News Detection (2018, methodology): “The RTE-based (Recognizing Textual Entailment) (Dagan et al., 2010) method is frequently used to gather and to utilize evidence.”
DocNLI: A Large-scale Dataset for Document-level Natural Language Inference (2021, background): “A fundamental challenge of natural language processing (NLP) lies in the variability of semantic expression, where the same meaning can be conveyed by, or inferred from, different pieces of text (Dagan et al., 2009).”
GPT-4 passes the bar exam (2024, background): “In Table 3 Building up the broader concept of textual entailment, 64,65,66 earlier work studying Bar Exams treated “the relationship between the question and the multiple-choice answers as a form of textual entailment” 67 where the ability to identify wrong answers (non-entailment) is…”
Learning To Use Formulas To Solve Simple Arithmetic Problems (2016, methodology): “…includes the Winograd Schema challenge for commonsense reasoning (Levesque, 2011), Story Comprehension Challenge (Richardson et al., 2013), Facebook bAbl task (Weston et al., 2015), Semantic Textual Similarity (Agirre et al., 2012) and Textual Entailment (Bowman et al., 2015; Dagan et al., 2010).”