Related papers: Group-wise Contrastive Learning for Neural Dialogu…

Generating personalized responses is one of the major challenges in natural human-robot interaction. Current researches in this field mainly focus on generating responses consistent with the robot's pre-assigned persona, while ignoring the…

Multi-intent natural language understanding (NLU) presents a formidable challenge due to the model confusion arising from multiple intents within a single utterance. While previous works train the model contrastively to increase the margin…

In neutrino physics, analyses often depend on large simulated datasets, making it essential for models to generalise effectively to real-world detector data. Contrastive learning, a well-established technique in deep learning, offers a…

Natural language understanding (NLU) and natural language generation (NLG) are two fundamental and related tasks in building task-oriented dialogue systems with opposite objectives: NLU tackles the transformation from natural language to…

Contrastive learning has revolutionized self-supervised image representation learning field, and recently been adapted to video domain. One of the greatest advantages of contrastive learning is that it allows us to flexibly define powerful…

Cross-language pre-trained models such as multilingual BERT (mBERT) have achieved significant performance in various cross-lingual downstream NLP tasks. This paper proposes a multi-level contrastive learning (ML-CTL) framework to further…

Recently, contrastive learning approaches (e.g., CLIP (Radford et al., 2021)) have received huge success in multimodal learning, where the model tries to minimize the distance between the representations of different views (e.g., image and…

Current state-of-the-art neural dialogue systems are mainly data-driven and are trained on human-generated responses. However, due to the subjectivity and open-ended nature of human conversations, the complexity of training dialogues varies…

Learning from preference feedback is a common practice for aligning large language models~(LLMs) with human value. Conventionally, preference data is learned and encoded into a scalar reward model that connects a value head with an LLM to…

Prevailing methods for training Large Language Models (LLMs) as text encoders rely on contrastive losses that treat the model as a black box function, discarding its generative and reasoning capabilities in favor of static embeddings. We…

Visual Dialog aims to answer multi-round, interactive questions based on the dialog history and image content. Existing methods either consider answer ranking and generating individually or only weakly capture the relation across the two…

In this paper, we present a framework for contrastive learning for audio representations, in a self supervised frame work without access to any ground truth labels. The core idea in self supervised contrastive learning is to map an audio…

Improving the emotional awareness of pre-trained language models is an emerging important problem for dialogue generation tasks. Although prior studies have introduced methods to improve empathetic dialogue generation, few have discussed…

Recent years have witnessed astonishing advances in the field of multimodal representation learning, with contrastive learning being the cornerstone for major breakthroughs. Latest works delivered further improvements by incorporating…

Data artifacts incentivize machine learning models to learn non-transferable generalizations by taking advantage of shortcuts in the data, and there is growing evidence that data artifacts play a role for the strong results that deep…

Generating qualitative responses has always been a challenge for human-computer dialogue systems. Existing dialogue systems generally derive from either retrieval-based or generative-based approaches, both of which have their own pros and…

Retrieval-augmented Neural Machine Translation models have been successful in many translation scenarios. Different from previous works that make use of mutually similar but redundant translation memories~(TMs), we propose a new…

Contrastive learning has been shown to produce generalizable representations of audio and visual data by maximizing the lower bound on the mutual information (MI) between different views of an instance. However, obtaining a tight lower…

Recent representation learning approaches enhance neural topic models by optimizing the weighted linear combination of the evidence lower bound (ELBO) of the log-likelihood and the contrastive learning objective that contrasts pairs of…

Models for Visual Question Answering (VQA) often rely on the spurious correlations, i.e., the language priors, that appear in the biased samples of training set, which make them brittle against the out-of-distribution (OOD) test data.…