Years have passed since the NLP community has last focused on linguistic acceptability. In this work, we revisit this topic in the context of large language models. We introduce CoLAC - Corpus of Linguistic Acceptability in Chinese, the first large-scale non-English acceptability dataset that is verified by native speakers and comes with two sets of labels. Our experiments show that even the largest InstructGPT model performs only at chance level on CoLAC, while ChatGPT's performance (48.30 MCC) is also way below supervised models (59.03 MCC) and human (65.11 MCC). Through cross-lingual transfer experiments and fine-grained linguistic analysis, we demonstrate for the first time that knowledge of linguistic acceptability can be transferred across typologically distinct languages, as well as be traced back to pre-training.
AI generated content (AIGC) presents considerable challenge to educators around the world. Instructors need to be able to detect such text generated by large language models, either with the naked eye or with the help of some tools. There is also growing need to understand the lexical, syntactic and stylistic features of AIGC. To address these challenges in English language teaching, we first present ArguGPT, a balanced corpus of 4,038 argumentative essays generated by 7 GPT models in response to essay prompts from three sources: (1) in-class or homework exercises, (2) TOEFL and (3) GRE writing tasks. Machine-generated texts are paired with roughly equal number of human-written essays with three score levels matched in essay prompts. We then hire English instructors to distinguish machine essays from human ones. Results show that when first exposed to machine-generated essays, the instructors only have an accuracy of 61% in detecting them. But the number rises to 67% after one round of minimal self-training. Next, we perform linguistic analyses of these essays, which show that machines produce sentences with more complex syntactic structures while human essays tend to be lexically more complex. Finally, we test existing AIGC detectors and build our own detectors using SVMs and RoBERTa. Results suggest that a RoBERTa fine-tuned with the training set of ArguGPT achieves above 90% accuracy in both essay- and sentence-level classification. To the best of our knowledge, this is the first comprehensive analysis of argumentative essays produced by generative large language models. Machine-authored essays in ArguGPT and our models will be made publicly available at https://github.com/huhailinguist/ArguGPT
Pretrained Language Models (PLMs) have achieved tremendous success in natural language understanding tasks. While different learning schemes -- fine-tuning, zero-shot and few-shot learning -- have been widely explored and compared for languages such as English, there is comparatively little work in Chinese to fairly and comprehensively evaluate and compare these methods. This work first introduces Chinese Few-shot Learning Evaluation Benchmark (FewCLUE), the first comprehensive small sample evaluation benchmark in Chinese. It includes nine tasks, ranging from single-sentence and sentence-pair classification tasks to machine reading comprehension tasks. Given the high variance of the few-shot learning performance, we provide multiple training/validation sets to facilitate a more accurate and stable evaluation of few-shot modeling. An unlabeled training set with up to 20,000 additional samples per task is provided, allowing researchers to explore better ways of using unlabeled samples. Next, we implement a set of state-of-the-art (SOTA) few-shot learning methods (including PET, ADAPET, LM-BFF, P-tuning and EFL), and compare their performance with fine-tuning and zero-shot learning schemes on the newly constructed FewCLUE benchmark.Our results show that: 1) all five few-shot learning methods exhibit better performance than fine-tuning or zero-shot learning; 2) among the five methods, PET is the best performing few-shot method; 3) few-shot learning performance is highly dependent on the specific task. Our benchmark and code are available at https://github.com/CLUEbenchmark/FewCLUE
Multilingual transformers (XLM, mT5) have been shown to have remarkable transfer skills in zero-shot settings. Most transfer studies, however, rely on automatically translated resources (XNLI, XQuAD), making it hard to discern the particular linguistic knowledge that is being transferred, and the role of expert annotated monolingual datasets when developing task-specific models. We investigate the cross-lingual transfer abilities of XLM-R for Chinese and English natural language inference (NLI), with a focus on the recent large-scale Chinese dataset OCNLI. To better understand linguistic transfer, we created 4 categories of challenge and adversarial tasks (totaling 17 new datasets) for Chinese that build on several well-known resources for English (e.g., HANS, NLI stress-tests). We find that cross-lingual models trained on English NLI do transfer well across our Chinese tasks (e.g., in 3/4 of our challenge categories, they perform as well/better than the best monolingual models, even on 3/5 uniquely Chinese linguistic phenomena such as idioms, pro drop). These results, however, come with important caveats: cross-lingual models often perform best when trained on a mixture of English and high-quality monolingual NLI data (OCNLI), and are often hindered by automatically translated resources (XNLI-zh). For many phenomena, all models continue to struggle, highlighting the need for our new diagnostics to help benchmark Chinese and cross-lingual models. All new datasets/code are released at https://github.com/huhailinguist/ChineseNLIProbing.
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% absolute performance gap), making it a challenging new 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.
We introduce CLUE, a Chinese Language Understanding Evaluation benchmark. It contains eight different tasks, including single-sentence classification, sentence pair classification, and machine reading comprehension. We evaluate CLUE on a number of existing full-network pre-trained models for Chinese. We also include a small hand-crafted diagnostic test set designed to probe specific linguistic phenomena using different models, some of which are unique to Chinese. Along with CLUE, we release a large clean crawled raw text corpus that can be used for model pre-training. We release CLUE, baselines and pre-training dataset on Github.
We present a new logic-based inference engine for natural language inference (NLI) called MonaLog, which is based on natural logic and the monotonicity calculus. In contrast to existing logic-based approaches, our system is intentionally designed to be as lightweight as possible, and operates using a small set of well-known (surface-level) monotonicity facts about quantifiers, lexical items and tokenlevel polarity information. Despite its simplicity, we find our approach to be competitive with other logic-based NLI models on the SICK benchmark. We also use MonaLog in combination with the current state-of-the-art model BERT in a variety of settings, including for compositional data augmentation. We show that MonaLog is capable of generating large amounts of high-quality training data for BERT, improving its accuracy on SICK.
Do state-of-the-art models for language understanding already have, or can they easily learn, abilities such as boolean coordination, quantification, conditionals, comparatives, and monotonicity reasoning (i.e., reasoning about word substitutions in sentential contexts)? While such phenomena are involved in natural language inference (NLI) and go beyond basic linguistic understanding, it is unclear the extent to which they are captured in existing NLI benchmarks and effectively learned by models. To investigate this, we propose the use of semantic fragments---systematically generated datasets that each target a different semantic phenomenon---for probing, and efficiently improving, such capabilities of linguistic models. This approach to creating challenge datasets allows direct control over the semantic diversity and complexity of the targeted linguistic phenomena, and results in a more precise characterization of a model's linguistic behavior. Our experiments, using a library of 8 such semantic fragments, reveal two remarkable findings: (a) State-of-the-art models, including BERT, that are pre-trained on existing NLI benchmark datasets perform poorly on these new fragments, even though the phenomena probed here are central to the NLI task. (b) On the other hand, with only a few minutes of additional fine-tuning---with a carefully selected learning rate and a novel variation of "inoculation"---a BERT-based model can master all of these logic and monotonicity fragments while retaining its performance on established NLI benchmarks.
We present a machine learning approach to distinguish texts translated to Chinese (by humans) from texts originally written in Chinese, with a focus on a wide range of syntactic features. Using Support Vector Machines (SVMs) as classifier on a genre-balanced corpus in translation studies of Chinese, we find that constituent parse trees and dependency triples as features without lexical information perform very well on the task, with an F-measure above 90%, close to the results of lexical n-gram features, without the risk of learning topic information rather than translation features. Thus, we claim syntactic features alone can accurately distinguish translated from original Chinese. Translated Chinese exhibits an increased use of determiners, subject position pronouns, NP + 'de' as NP modifiers, multiple NPs or VPs conjoined by a Chinese specific punctuation, among other structures. We also interpret the syntactic features with reference to previous translation studies in Chinese, particularly the usage of pronouns.