TwoWingOS: A Two-Wing Optimization Strategy for Evidential Claim Verification

By Wenpeng Yin, Dan Roth. 2018

77 citations recorded by the source corpus.

Determining whether a given claim is supported by evidence is a fundamental NLP problem that is best modeled as Textual Entailment. However, given a large collection of text, finding evidence that could support or refute a given claim is a challenge in itself, amplified by the fact that different evidence might be needed to support or refute a claim. Nevertheless, most prior work decouples evidence finding from determining the truth value of the claim given the evidence. We propose to consider these two aspects jointly. We develop TwoWingOS (two-wing optimization strategy), a system that, while identifying appropriate evidence for a claim, also determines whether or not the claim is supported by the evidence. Given the claim, TwoWingOS attempts to identify a subset of the evidence candidates; given the predicted evidence, it then attempts to determine the truth value of the corresponding claim entailment problem. We treat this problem as coupled optimization problems, training a joint model for it. TwoWingOS offers two advantages: (i) Unlike pipeline systems it facilitates flexible-size evidence set, and (ii) Joint training improves both the claim entailment and the evidence identification. Experiments on a benchmark dataset show state-of-the-art performance.

Subfields: Artificial Intelligence, Natural Language Processing, Safety, Robustness & Interpretability

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 Safety, Robustness & Interpretability

Citations in the corpus

Reasoning Over Semantic-Level Graph for Fact Checking (2019, background): “Instead of training each component separately, Yin and Roth (2018) show that joint learning could improve both claim verification and evidence identification.”
GEAR: Graph-based Evidence Aggregating and Reasoning for Fact Verification (2019, methodology): “Unlike these methods, Yin and Roth (2018) propose the T WO W ING OS sys-tem which trains the evidence identiﬁcation and claim veriﬁcation modules jointly.”
Fine-grained Fact Verification with Kernel Graph Attention Network (2019, background): “TwoWingOS (Yin and Roth, 2018) further incorporates evidence identification to improve claim verification.”
Program Enhanced Fact Verification with Verbalization and Graph Attention Network (2020, methodology): “Some previous models are developed on the of-ﬁcial baseline (Thorne et al., 2018) with three step pipeline (Chen et al., 2017a) for fact veriﬁcation (Hanselowski et al., 2018; Yoneda et al., 2018; Yin and Roth, 2018; Nie et al., 2019).”
Evidence Sentence Extraction for Machine Reading Comprehension (2019, background): “…paragraph retrieval for factoid question answering (Chen et al., 2017; Wang et al., 2018c; Choi et al., 2017; Lin et al., 2018), sentence selection for machine reading comprehension (Hewlett et al., 2017; Min et al., 2018), and fact verification (Yin and Roth, 2018; Hanselowski et al., 2018).”
A Multi-Level Attention Model for Evidence-Based Fact Checking (2021, result): “Unlike previous work that jointly trains two models (Yin and Roth, 2018; Li et al., 2020; Hidey et al., 2020; Nie et al., 2020), our approach is still a pipeline process where only a subset of potential candidate sentences produced by any sentence selector can be used for joint training.”
Kernel Graph Attention Network for Fact Verification (2019, methodology): “TwoWingOS (Yin and Roth, 2018) proposes a joint training system for both the evidence identiﬁcation and claim veriﬁcation modules.”