Related papers: Beyond Contrastive Learning: A Variational Generat…

We present ReMatch, a framework that leverages the generative strength of MLLMs for multimodal retrieval. Previous approaches treated an MLLM as a simple encoder, ignoring its generative nature, and under-utilising its compositional…

This work exploits translation data as a source of semantically relevant learning signal for models of word representation. In particular, we exploit equivalence through translation as a form of distributed context and jointly learn how to…

Different word embedding models capture different aspects of linguistic properties. This inspired us to propose a model (M-MaxLSTM-CNN) for employing multiple sets of word embeddings for evaluating sentence similarity/relation. Representing…

Contrastive learning is a discriminative approach that aims at grouping similar samples closer and diverse samples far from each other. It it an efficient technique to train an encoder generating distinguishable and informative…

Most sentence embedding techniques heavily rely on expensive human-annotated sentence pairs as the supervised signals. Despite the use of large-scale unlabeled data, the performance of unsupervised methods typically lags far behind that of…

Retrieval-augmented generation improves large language models by grounding outputs in external knowledge sources, reducing hallucinations and addressing knowledge cutoffs. However, standard embedding-based retrieval fails to capture the…

While static word embedding models are known to represent linguistic analogies as parallel lines in high-dimensional space, the underlying mechanism as to why they result in such geometric structures remains obscure. We find that an…

Contrastive learning is an approach to representation learning that utilizes naturally occurring similar and dissimilar pairs of data points to find useful embeddings of data. In the context of document classification under topic modeling…

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…

Recent pre-trained language models (PLMs) achieved great success on many natural language processing tasks through learning linguistic features and contextualized sentence representation. Since attributes captured in stacked layers of PLMs…

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.…

Recognizing semantically similar sentences or paragraphs across languages is beneficial for many tasks, ranging from cross-lingual information retrieval and plagiarism detection to machine translation. Recently proposed methods for…

Most of the existing works for dialogue generation are data-driven models trained directly on corpora crawled from websites. They mainly focus on improving the model architecture to produce better responses but pay little attention to…

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…

Generative retrieval constitutes an innovative approach in information retrieval, leveraging generative language models (LM) to generate a ranked list of document identifiers (docid) for a given query. It simplifies the retrieval pipeline…

Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack principled guarantees on coverage…

Massively multilingual sentence representation models, e.g., LASER, SBERT-distill, and LaBSE, help significantly improve cross-lingual downstream tasks. However, the use of a large amount of data or inefficient model architectures results…

Contrastive Learning has emerged as a powerful representation learning method and facilitates various downstream tasks especially when supervised data is limited. How to construct efficient contrastive samples through data augmentation is…

Exemplar-Guided Paraphrase Generation (EGPG) aims to generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence. In this paper, we propose a new method…

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…