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

The lack of annotated data in many languages is a well-known challenge within the field of multilingual natural language processing (NLP). Therefore, many recent studies focus on zero-shot transfer learning and joint training across…

Contrastive learning pre-trains an image encoder using a large amount of unlabeled data such that the image encoder can be used as a general-purpose feature extractor for various downstream tasks. In this work, we propose PoisonedEncoder, a…

Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates only a few learnable tokens, and differently, In-Context…

This paper presents E5, a family of state-of-the-art text embeddings that transfer well to a wide range of tasks. The model is trained in a contrastive manner with weak supervision signals from our curated large-scale text pair dataset…

For many use-cases, it is often important to explain the prediction of a black-box model by identifying the most influential training data samples. Existing approaches lack customization for user intent and often provide a homogeneous set…

CLIP (Contrastive Language-Image Pre-training) has attained great success in pattern recognition and computer vision. Transferring CLIP to downstream tasks (e.g. zero- or few-shot classification) is a hot topic in multimodal learning.…

In this work, we investigate the positional encoding methods used in language pre-training (e.g., BERT) and identify several problems in the existing formulations. First, we show that in the absolute positional encoding, the addition…

Detecting out-of-scope user utterances is essential for task-oriented dialogues and intent classification. Current methodologies face difficulties with the unpredictable distribution of outliers and often rely on assumptions about data…

Few-shot Intent Classification (FSIC) is one of the key challenges in modular task-oriented dialog systems. While advanced FSIC methods are similar in using pretrained language models to encode texts and nearest neighbour-based inference…

Pre-trained vision-language models have notably accelerated progress of open-world concept recognition. Their impressive zero-shot ability has recently been transferred to multi-label image classification via prompt tuning, enabling to…

In this paper, we introduce the use of Semantic Hashing as embedding for the task of Intent Classification and achieve state-of-the-art performance on three frequently used benchmarks. Intent Classification on a small dataset is a…

State-of-the-art pre-trained image models predominantly adopt a two-stage approach: initial unsupervised pre-training on large-scale datasets followed by task-specific fine-tuning using Cross-Entropy loss~(CE). However, it has been…

Human infant learning happens during exploration of the environment, by interaction with objects, and by listening to and repeating utterances casually, which is analogous to unsupervised learning. Only occasionally, a learning infant would…

Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Existing works usually tackle this task using adversarial learning and visual concept reward based on reinforcement…

Modern task-oriented dialog systems need to reliably understand users' intents. Intent detection is most challenging when moving to new domains or new languages, since there is little annotated data. To address this challenge, we present a…

Zero-shot inference, where pre-trained models perform tasks without specific training data, is an exciting emergent ability of large models like CLIP. Although there has been considerable exploration into enhancing zero-shot abilities in…

In this paper we explore the use of meta-knowledge embedded in intent identifiers to improve intent recognition in conversational systems. As evidenced by the analysis of thousands of real-world chatbots and in interviews with professional…

While instruction-tuned language models have demonstrated impressive zero-shot generalization, these models often struggle to generate accurate responses when faced with instructions that fall outside their training set. This paper presents…

We propose a novel word embedding pre-training approach that exploits writing errors in learners' scripts. We compare our method to previous models that tune the embeddings based on script scores and the discrimination between correct and…

Modern supervised semantic segmentation methods are usually finetuned based on the supervised or self-supervised models pre-trained on ImageNet. Recent work shows that transferring the knowledge from CLIP to semantic segmentation via prompt…