The Third PASCAL Recognizing Textual Entailment Challenge

By Danilo Giampiccolo, Bernardo Magnini, Ido Dagan, Bill Dolan. 2007

290 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, Evaluation & Benchmarks

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

In Evaluation & Benchmarks

Citations in the corpus

Language Models are Few-Shot Learners (2020, methodology): “RTa in a more systematic way, we also evaluate GPT-3 on a standardized collection of datasets, the SuperGLUE benchmark [WPN+19] [WPN +19] [CLC 19] [DMST19] [RBG11] [KCR 18] [ZLL+18] [DGM06] [BHDD+06] [GMDD07] [BDD+09] [PCC18] [PHR+18]. GPT-3’s test-set performance on the SuperGLUE dataset is shown i”
SpanBERT: Improving Pre-training by Representing and Predicting Spans (2019, background): “• Four natural language inference tasks including MNLI (Williams et al., 2018), QNLI (Ra-jpurkar et al., 2016), RTE (Dagan et al., 2005; Bar-Haim et al., 2006; Giampiccolo et al., 2007) and WNLI (Levesque et al., 2011).”
Unified Language Model Pre-training for Natural Language Understanding and Generation (2019, methodology): “ge understanding tasks, including question answering [33], linguistic acceptability [46], sentiment analysis [38], text similarity [5], paraphrase detection [10], and natural language inference (NLI) [7, 2, 17, 3, 24, 47]. Our model is ﬁne-tuned as a bidirectional LM. We use Adamax [21] as our optim”
Pretrained Transformers for Text Ranking: BERT and Beyond (2020, background): “aphrases or not.109 • Entailment. The notion of entailment is formalized in terms of truth values: a text tentails another text hif, typically, a human reading twould infer that his most likely true [Giampiccolo et al., 2007]. Thus, “John sold the violin to Mary” entails “Mary now owns the Violin”. ”
Measuring and Improving Consistency in Pretrained Language Models (2021, background): “This deﬁnition is in the spirit of the RTE deﬁnition (Dagan et al., 2005), which similarly supports a more ﬂexible use of the notion of entailment.”
ERNIE: Enhanced Language Representation with Informative Entities (2019, background): “, 2018) is a collection of diverse natural language understanding tasks (Warstadt et al., 2018; Socher et al., 2013; Dolan and Brockett, 2005; Agirre et al., 2007; Williams et al., 2018; Rajpurkar et al., 2016; Dagan et al., 2006; Bar Haim et al., 2006; Giampiccolo et al., 2007; Bentivogli et al., 2”
Ordinal Common-sense Inference (2016, methodology): “nding of language as well as common background knowledge. This deﬁnition strayed from the more strict notion of entailment as used by linguistic semanticists, such as those involved with FRACAS. WhileGiampiccolo et al. (2008) extended binary RTE with an “unknown” category, the entailment community h”
EQUATE: A Benchmark Evaluation Framework for Quantitative Reasoning in Natural Language Inference (2019, methodology): “(Gururangan et al., 2018). 3) ALIGN: A bag-of-words alignment model inspired by MacCartney (2009).10 4) CBOW: A simple bag-of-embeddings sentence representation model (Williams et al.”
Combining Similarity and Transformer Methods for Case Law Entailment (2019, background): “…models have achieved impressive results in a wide range of publicly available benchmarks of di�erent common natural language tasks, such as RACE (reading comprehension) [20] , COPA (common sense reasoning) [29], CoLA (linguistic acceptability) [31] and RTE (textual entailment) [11] to name a few.”