1 |
Don't Go Far Off: An Empirical Study on Neural Poetry Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Don't Go Far Off: An Empirical Study on Neural Poetry Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
ENTRUST: Argument Reframing with Language Models and Entailment ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Implicit Premise Generation with Discourse-aware Commonsense Knowledge Models ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
ENTRUST: Argument Reframing with Language Models and Entailment ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
$R^3$: Reverse, Retrieve, and Rank for Sarcasm Generation with Commonsense Knowledge ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
DeSePtion: Dual Sequence Prediction and Adversarial Examples for Improved Fact-Checking ...
|
|
|
|
Abstract:
The increased focus on misinformation has spurred development of data and systems for detecting the veracity of a claim as well as retrieving authoritative evidence. The Fact Extraction and VERification (FEVER) dataset provides such a resource for evaluating end-to-end fact-checking, requiring retrieval of evidence from Wikipedia to validate a veracity prediction. We show that current systems for FEVER are vulnerable to three categories of realistic challenges for fact-checking -- multiple propositions, temporal reasoning, and ambiguity and lexical variation -- and introduce a resource with these types of claims. Then we present a system designed to be resilient to these "attacks" using multiple pointer networks for document selection and jointly modeling a sequence of evidence sentences and veracity relation predictions. We find that in handling these attacks we obtain state-of-the-art results on FEVER, largely due to improved evidence retrieval. ... : ACL 2020 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2004.12864 https://dx.doi.org/10.48550/arxiv.2004.12864
|
|
BASE
|
|
Hide details
|
|
|
|