Related papers: Syntactic Data Augmentation Increases Robustness t…
Machine learning models can reach high performance on benchmark natural language processing (NLP) datasets but fail in more challenging settings. We study this issue when a pre-trained model learns dataset artifacts in natural language…
While recent research on natural language inference has considerably benefited from large annotated datasets, the amount of inference-related knowledge (including commonsense) provided in the annotated data is still rather limited. There…
Neural network models have been very successful at achieving high accuracy on natural language inference (NLI) tasks. However, as demonstrated in recent literature, when tested on some simple adversarial examples, most of the models suffer…
Pre-trained Transformer-based neural language models, such as BERT, have achieved remarkable results on varieties of NLP tasks. Recent works have shown that attention-based models can benefit from more focused attention over local regions.…
Existing NLP datasets contain various biases, and models tend to quickly learn those biases, which in turn limits their robustness. Existing approaches to improve robustness against dataset biases mostly focus on changing the training…
Natural Language Inference (NLI) is the task of inferring whether the hypothesis can be justified by the given premise. Basically, we classify the hypothesis into three labels(entailment, neutrality and contradiction) given the premise. NLI…
Attention-based models have shown significant improvement over traditional algorithms in several NLP tasks. The Transformer, for instance, is an illustrative example that generates abstract representations of tokens inputted to an encoder…
Adding linguistic information (syntax or semantics) to neural machine translation (NMT) has mostly focused on using point estimates from pre-trained models. Directly using the capacity of massive pre-trained contextual word embedding models…
Fine-tuning pre-trained language models like BERT has become an effective way in NLP and yields state-of-the-art results on many downstream tasks. Recent studies on adapting BERT to new tasks mainly focus on modifying the model structure,…
The release of large natural language inference (NLI) datasets like SNLI and MNLI have led to rapid development and improvement of completely neural systems for the task. Most recently, heavily pre-trained, Transformer-based models like…
A machine learning system can score well on a given test set by relying on heuristics that are effective for frequent example types but break down in more challenging cases. We study this issue within natural language inference (NLI), the…
We introduce a data augmentation technique based on byte pair encoding and a BERT-like self-attention model to boost performance on spoken language understanding tasks. We compare and evaluate this method with a range of augmentation…
Recently proposed BERT-based evaluation metrics for text generation perform well on standard benchmarks but are vulnerable to adversarial attacks, e.g., relating to information correctness. We argue that this stems (in part) from the fact…
A growing body of work shows that models exploit annotation artifacts to achieve state-of-the-art performance on standard crowdsourced benchmarks---datasets collected from crowdworkers to create an evaluation task---while still failing on…
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…
Data augmentation is an effective performance enhancement in neural machine translation (NMT) by generating additional bilingual data. In this paper, we propose a novel data augmentation enhancement strategy for neural machine translation.…
Pre-trained models for natural language inference (NLI) often achieve high performance on benchmark datasets by using spurious correlations, or dataset artifacts, rather than understanding language touches such as negation. In this project,…
Larger language models have higher accuracy on average, but are they better on every single instance (datapoint)? Some work suggests larger models have higher out-of-distribution robustness, while other work suggests they have lower…
Language models can achieve high accuracy on natural language tasks such as NLI, but performance suffers on manually created adversarial examples. We investigate the performance of a language model trained on the Stanford Natural Language…
Recently, the pre-trained language model, BERT (and its robustly optimized version RoBERTa), has attracted a lot of attention in natural language understanding (NLU), and achieved state-of-the-art accuracy in various NLU tasks, such as…