Neural Models of Factuality

By Rachel Rudinger, Aaron Steven White, Benjamin Van Durme. 2018

89 citations recorded by the source corpus.

We present two neural models for event factuality prediction, which yield significant performance gains over previous models on three event factuality datasets: FactBank, UW, and MEANTIME. We also present a substantial expansion of the It Happened portion of the Universal Decompositional Semantics dataset, yielding the largest event factuality dataset to date. We report model results on this extended factuality dataset as well.

Subfields: 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 Natural Language Processing

Citations in the corpus

Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference (2019, background): “Several past works (Pavlick and Callison-Burch, 2016; Rudinger et al., 2018; White et al., 2018; White and Rawlins, 2018) have studied such behavior for verbs (e.”
Linguistic Knowledge and Transferability of Contextual Representations (2019, methodology): “We use the Universal Decompositional Semantics It Happened v2 dataset (Rudinger et al., 2018), and the model is trained to predict a (non)factuality value in the range [ − 3 , 3] .”
Automatically Neutralizing Subjective Bias in Text (2019, methodology): “…properties with tasks like detecting framing or epistemological bias (Recasens, Danescu-Niculescu-Mizil, and Jurafsky 2013), or veridicality assessment/factuality prediction (Saur´ı and Pustejovsky 2009; Marneffe, Manning, and Potts 2012; Rudinger, White, and Van Durme 2018; White et al. 2018).”
Unsupervised Discovery of Gendered Language through Latent-Variable Modeling (2019, background): “Recent NLP research has focused on gender biases in word embeddings (Boluk-basi et al., 2016; Zhao et al., 2017) and co-reference systems (Zhao et al., 2018; Rudinger et al., 2018).”
Commonsense Reasoning for Natural Language Understanding: A Survey of Benchmarks, Resources, and Approaches (2019, methodology): “Gendered Anaphora Resolution, recast from the Winogender dataset (Rudinger et al., 2018a) 4.”
Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation (2018, methodology): “Using a similar formula Rudinger et al. (2018a) introduce Winogender schemas, minimal sentence pairs that differ only by pronoun gender.”
Towards a Unified Natural Language Inference Framework to Evaluate Sentence Representations (2018, methodology): “We recast event factuality annotations from three existing datasets: UW (Lee et al., 2015), MEANTIME (Minard et al., 2016), and the JHU Universal Decompositional Semantics (Decomp) It Happened v2 (Rudinger et al., 2018b).7 Context sentences are simple sentences from the three 6 https://www.decomp.ne”
Lexicosyntactic Inference in Neural Models (2018, methodology): “Rudinger et al. (2018) propose a stacked bidirectional extension to the child-sum dependency tree LSTM (T-LSTM; Tai et al., 2015).”