Related papers: Pre-training Intent-Aware Encoders for Zero- and F…

Entailment has been recognized as an important metric for evaluating natural language understanding (NLU) models, and recent studies have found that entailment pretraining benefits weakly supervised fine-tuning. In this work, we design a…

Recent research demonstrates the effectiveness of using pretrained language models (PLM) to improve dense retrieval and multilingual dense retrieval. In this work, we present a simple but effective monolingual pretraining task called…

Recent advances in vision-language models have combined contrastive approaches with generative methods to achieve state-of-the-art (SOTA) on downstream inference tasks like zero-shot image classification. However, a persistent issue of…

Sentence encoders have indeed been shown to achieve superior performances for many downstream text-mining tasks and, thus, claimed to be fairly general. Inspired by this, we performed a detailed study on how to leverage these sentence…

Pre-trained text encoders such as BERT and its variants have recently achieved state-of-the-art performances on many NLP tasks. While being effective, these pre-training methods typically demand massive computation resources. To accelerate…

Recent achievements in language models have showcased their extraordinary capabilities in bridging visual information with semantic language understanding. This leads us to a novel question: can language models connect textual semantics…

Pretrained multilingual encoder models can directly perform zero-shot multilingual tasks or linguistic probing by reformulating the input examples into cloze-style prompts. This is accomplished by predicting the probabilities of the label…

Direct speech-to-text translation systems encounter an important drawback in data scarcity. A common solution consists on pretraining the encoder on automatic speech recognition, hence losing efficiency in the training process. In this…

Semantic segmentation, which aims to acquire a detailed understanding of images, is an essential issue in computer vision. However, in practical scenarios, new categories that are different from the categories in training usually appear.…

Modern classification models tend to struggle when the amount of annotated data is scarce. To overcome this issue, several neural few-shot classification models have emerged, yielding significant progress over time, both in Computer Vision…

Intent classification is a task in spoken language understanding. An intent classification system is usually implemented as a pipeline process, with a speech recognition module followed by text processing that classifies the intents. There…

Cross encoders (CEs) are trained with sentence pairs to detect relatedness. As CEs require sentence pairs at inference, the prevailing view is that they can only be used as re-rankers in information retrieval pipelines. Dual encoders (DEs)…

Task-oriented dialog(TOD) aims to assist users in achieving specific goals through multi-turn conversation. Recently, good results have been obtained based on large pre-trained models. However, the labeled-data scarcity hinders the…

Video-and-language pre-training has shown promising improvements on various downstream tasks. Most previous methods capture cross-modal interactions with a transformer-based multimodal encoder, not fully addressing the misalignment between…

Accent classification or AC is a task to predict the accent type of an input utterance, and it can be used as a preliminary step toward accented speech recognition and accent conversion. Existing studies have often achieved such…

Audio-Language models jointly learn multimodal text and audio representations that enable Zero-Shot inference. Models rely on the encoders to create powerful representations of the input and generalize to multiple tasks ranging from sounds,…

Video prediction models often combine three components: an encoder from pixel space to a small latent space, a latent space prediction model, and a generative model back to pixel space. However, the large and unpredictable pixel space makes…

Contrastive learning has become a popular technique to pre-train image encoders, which could be used to build various downstream classification models in an efficient way. This process requires a large amount of data and computation…

Citations in scientific papers not only help us trace the intellectual lineage but also are a useful indicator of the scientific significance of the work. Citation intents prove beneficial as they specify the role of the citation in a given…

Large pre-trained vision-language models have shown great prominence in transferring pre-acquired knowledge to various domains and downstream tasks with appropriate prompting or tuning. Existing prevalent tuning methods can be generally…