Related papers: From Superficial Patterns to Semantic Understandin…

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,…

Natural Language Processing models like BERT can provide state-of-the-art word embeddings for downstream NLP tasks. However, these models yet to perform well on Semantic Textual Similarity, and may be too large to be deployed as lightweight…

Learning high-quality sentence representations benefits a wide range of natural language processing tasks. Though BERT-based pre-trained language models achieve high performance on many downstream tasks, the native derived sentence…

Fine-tuned pre-trained language models (LMs) have achieved enormous success in many natural language processing (NLP) tasks, but they still require excessive labeled data in the fine-tuning stage. We study the problem of fine-tuning…

The performance of sentence encoders can be significantly improved through the simple practice of fine-tuning using contrastive loss. A natural question arises: what characteristics do models acquire during contrastive learning? This paper…

Most research on hate speech detection has focused on English where a sizeable amount of labeled training data is available. However, to expand hate speech detection into more languages, approaches that require minimal training data are…

Model interpretability methods are often used to explain NLP model decisions on tasks such as text classification, where the output space is relatively small. However, when applied to language generation, where the output space often…

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…

Pretrained language models such as BERT, GPT have shown great effectiveness in language understanding. The auxiliary predictive tasks in existing pretraining approaches are mostly defined on tokens, thus may not be able to capture…

Success in natural language inference (NLI) should require a model to understand both lexical and compositional semantics. However, through adversarial evaluation, we find that several state-of-the-art models with diverse architectures are…

To what extent do pre-trained language models grasp semantic knowledge regarding the phenomenon of distributivity? In this paper, we introduce DistNLI, a new diagnostic dataset for natural language inference that targets the semantic…

Spoken language understanding (SLU) is an essential task for machines to understand human speech for better interactions. However, errors from the automatic speech recognizer (ASR) usually hurt the understanding performance. In reality, ASR…

Contrastive learning has become a popular approach in natural language processing, particularly for the learning of sentence embeddings. However, the discrete nature of natural language makes it difficult to ensure the quality of positive…

Pre-trained language models have proven their unique powers in capturing implicit language features. However, most pre-training approaches focus on the word-level training objective, while sentence-level objectives are rarely studied. In…

Recent studies demonstrated that large language models (LLMs) can excel in many tasks via in-context learning (ICL). However, recent works show that ICL-prompted models tend to produce inaccurate results when presented with adversarial…

Natural Language Inference (NLI) has been an important task for evaluating language models for Natural Language Understanding, but the logical properties of the task are poorly understood and often mischaracterized. Understanding the notion…

Unsupervised sentence embedding aims to obtain the most appropriate embedding for a sentence to reflect its semantic. Contrastive learning has been attracting developing attention. For a sentence, current models utilize diverse data…

Contrastive learning has been the dominant approach to train state-of-the-art sentence embeddings. Previous studies have typically learned sentence embeddings either through the use of human-annotated natural language inference (NLI) data…

Natural Language Inference (NLI) evaluation is crucial for assessing language understanding models; however, popular datasets suffer from systematic spurious correlations that artificially inflate actual model performance. To address this,…

Ensuring the realism of computer-generated synthetic images is crucial to deep neural network (DNN) training. Due to different semantic distributions between synthetic and real-world captured datasets, there exists semantic mismatch between…