Stochastic Answer Networks for Natural Language Inference
We propose a stochastic answer network (SAN) to explore multi-step inference strategies in Natural Language Inference. Rather than directly predicting the results given the inputs, the model maintains a state and iteratively refines its predictions. Our experiments show that SAN achieves the state-of-the-art results on three benchmarks: Stanford Natural Language Inference (SNLI) dataset, MultiGenre Natural Language Inference (MultiNLI) dataset and Quora Question Pairs dataset.
Code (3)
Tasks
Natural Language InferenceSimilar Papers 제목 키워드 기반
Chance-Constrained Inference for Hallucination Risk Control in Large Language Models
Large language models generate outputs stochastically and may produce fluent but invalid responses, including factual hallucinations. Existing mitigation strategies reduce average error rates but do not provide explicit …
Multi-hop Question AnsweringUncertainty-Aware Natural Language Inference with Stochastic Weight Averaging
This paper introduces Bayesian uncertainty modeling using Stochastic Weight Averaging-Gaussian (SWAG) in Natural Language Understanding (NLU) tasks. We apply the approach to standard tasks in natural language inference (…
Language ModelingNatural Language InferenceNatural Language UnderstandingUsing Natural Language Relations between Answer Choices for Machine Comprehension
When evaluating an answer choice for Reading Comprehension task, other answer choices available for the question and the answers of related questions about the same paragraph often provide valuable information. In this p…
Natural Language InferenceQuestion AnsweringReading ComprehensionTransforming Question Answering Datasets Into Natural Language Inference Datasets
Existing datasets for natural language inference (NLI) have propelled research on language understanding. We propose a new method for automatically deriving NLI datasets from the growing abundance of large-scale question…
Natural Language InferenceQuestion AnsweringSentenceANU-CSIRO at MEDIQA 2019: Question Answering Using Deep Contextual Knowledge
We report on our system for textual inference and question entailment in the medical domain for the ACL BioNLP 2019 Shared Task, MEDIQA. Textual inference is the task of finding the semantic relationships between pairs o…
Medical Question AnsweringNatural Language InferenceQuestion Answering