OCNLI: Original Chinese Natural Language Inference

by   Hai Hu, et al.

Despite the tremendous recent progress on natural language inference (NLI), driven largely by large-scale investment in new datasets (e.g., SNLI, MNLI) and advances in modeling, most progress has been limited to English due to a lack of reliable datasets for most of the world's languages. In this paper, we present the first large-scale NLI dataset (consisting of  56,000 annotated sentence pairs) for Chinese called the Original Chinese Natural Language Inference dataset (OCNLI). Unlike recent attempts at extending NLI to other languages, our dataset does not rely on any automatic translation or non-expert annotation. Instead, we elicit annotations from native speakers specializing in linguistics. We follow closely the annotation protocol used for MNLI, but create new strategies for eliciting diverse hypotheses. We establish several baseline results on our dataset using state-of-the-art pre-trained models for Chinese, and find even the best performing models to be far outpaced by human performance ( 12 resource that we hope will help to accelerate progress in Chinese NLU. To the best of our knowledge, this is the first human-elicited MNLI-style corpus for a non-English language.


page 1

page 2

page 3

page 4


Can Language Models Make Fun? A Case Study in Chinese Comical Crosstalk

Language is the principal tool for human communication, in which humor i...

IndoNLI: A Natural Language Inference Dataset for Indonesian

We present IndoNLI, the first human-elicited NLI dataset for Indonesian....

AnchiBERT: A Pre-Trained Model for Ancient ChineseLanguage Understanding and Generation

Ancient Chinese is the essence of Chinese culture. There are several nat...

Shallow Discourse Annotation for Chinese TED Talks

Text corpora annotated with language-related properties are an important...

CLUECorpus2020: A Large-scale Chinese Corpus for Pre-trainingLanguage Model

In this paper, we introduce the Chinese corpus from CLUE organization, C...

Categorization in the Wild: Generalizing Cognitive Models to Naturalistic Data across Languages

Categories such as animal or furniture are acquired at an early age and ...

Reliable Evaluations for Natural Language Inference based on a Unified Cross-dataset Benchmark

Recent studies show that crowd-sourced Natural Language Inference (NLI) ...