Related papers: Focused Contrastive Training for Test-based Consti…

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…

Learning semantically meaningful sentence embeddings is an open problem in natural language processing. In this work, we propose a sentence embedding learning approach that exploits both visual and textual information via a multimodal…

Although pre-trained language models show good performance on various natural language processing tasks, they often rely on non-causal features and patterns to determine the outcome. For natural language inference tasks, previous results…

We study cross-lingual stance detection, which aims to leverage labeled data in one language to identify the relative perspective (or stance) of a given document with respect to a claim in a different target language. In particular, we…

Neural dialogue response generation has gained much popularity in recent years. Maximum Likelihood Estimation (MLE) objective is widely adopted in existing dialogue model learning. However, models trained with MLE objective function are…

Framing involves the positive or negative presentation of an argument or issue depending on the audience and goal of the speaker (Entman 1983). Differences in lexical framing, the focus of our work, can have large effects on peoples'…

We propose and study a novel supervised approach to learning statistical semantic relatedness models from subjectively annotated training examples. The proposed semantic model consists of parameterized co-occurrence statistics associated…

Several recent studies have tested the use of transformer language model representations to infer prosodic features for text-to-speech synthesis (TTS). While these studies have explored prosody in general, in this work, we look specifically…

Learning sentence embeddings in an unsupervised manner is fundamental in natural language processing. Recent common practice is to couple pre-trained language models with unsupervised contrastive learning, whose success relies on augmenting…

Scientific articles are long text documents organized into sections, each describing aspects of the research. Analyzing scientific production has become progressively challenging due to the increase in the number of available articles.…

Better disentanglement of speech representation is essential to improve the quality of voice conversion. Recently contrastive learning is applied to voice conversion successfully based on speaker labels. However, the performance of model…

Self-supervised learning is a machine learning approach that generates implicit labels by learning underlined patterns and extracting discriminative features from unlabeled data without manual labelling. Contrastive learning introduces the…

Contrastive learning is a family of self-supervised methods where a model is trained to solve a classification task constructed from unlabeled data. It has recently emerged as one of the leading learning paradigms in the absence of labels…

The recent success of SimCSE has greatly advanced state-of-the-art sentence representations. However, the original formulation of SimCSE does not fully exploit the potential of hard negative samples in contrastive learning. This study…

Although BERT and its variants have reshaped the NLP landscape, it still remains unclear how best to derive sentence embeddings from such pre-trained Transformers. In this work, we propose a contrastive learning method that utilizes…

The task of multi-step ahead prediction in language models is challenging considering the discrepancy between training and testing. At test time, a language model is required to make predictions given past predictions as input, instead of…

The generation of toxic content by large language models (LLMs) remains a critical challenge for the safe deployment of language technology. We propose a novel framework for implicit knowledge editing and controlled text generation by…

Factual inconsistencies in generated summaries severely limit the practical applications of abstractive dialogue summarization. Although significant progress has been achieved by using pre-trained models, substantial amounts of hallucinated…

Large language models benefit from training with a large amount of unlabeled text, which gives them increasingly fluent and diverse generation capabilities. However, using these models for text generation that takes into account target…

It has always been an important yet challenging problem to control language models to avoid generating texts with undesirable attributes, such as toxic language and unnatural repetition. We introduce Click for controllable text generation,…