Related papers: Exploring Description-Augmented Dataless Intent Cl…
The recent advances in transfer learning techniques and pre-training of large contextualized encoders foster innovation in real-life applications, including dialog assistants. Practical needs of intent recognition require effective data…
We propose an approach to semantic segmentation that achieves state-of-the-art supervised performance when applied in a zero-shot setting. It thus achieves results equivalent to those of the supervised methods, on each of the major semantic…
Training accurate intent classifiers requires labeled data, which can be costly to obtain. Data augmentation methods may ameliorate this issue, but the quality of the generated data varies significantly across techniques. We study the…
We address the task of unsupervised Semantic Textual Similarity (STS) by ensembling diverse pre-trained sentence encoders into sentence meta-embeddings. We apply, extend and evaluate different meta-embedding methods from the word embedding…
Supervised learning methods can solve the given problem in the presence of a large set of labeled data. However, the acquisition of a dataset covering all the target classes typically requires manual labeling which is expensive and…
Zero-shot point cloud segmentation aims to make deep models capable of recognizing novel objects in point cloud that are unseen in the training phase. Recent trends favor the pipeline which transfers knowledge from seen classes with labels…
Practical sequence classification tasks in natural language processing often suffer from low training data availability for target classes. Recent works towards mitigating this problem have focused on transfer learning using embeddings…
Contextualised word embeddings is a powerful tool to detect contextual synonyms. However, most of the current state-of-the-art (SOTA) deep learning concept extraction methods remain supervised and underexploit the potential of the context.…
We present a contrasting learning approach with data augmentation techniques to learn document representations in an unsupervised manner. Inspired by recent contrastive self-supervised learning algorithms used for image and NLP pretraining,…
Insufficient or even unavailable training data of emerging classes is a big challenge of many classification tasks, including text classification. Recognising text documents of classes that have never been seen in the learning stage,…
It is expensive and difficult to obtain the large number of sentence-level intent and token-level slot label annotations required to train neural network (NN)-based Natural Language Understanding (NLU) components of task-oriented dialog…
Dataless text classification is capable of classifying documents into previously unseen labels by assigning a score to any document paired with a label description. While promising, it crucially relies on accurate descriptions of the label…
This paper contributes a new State Of The Art (SOTA) for Semantic Textual Similarity (STS). We compare and combine a number of recently proposed sentence embedding methods for STS, and propose a novel and simple ensemble knowledge…
Zero-shot entity and relation classification models leverage available external information of unseen classes -- e.g., textual descriptions -- to annotate input text data. Thanks to the minimum data requirement, Zero-Shot Learning (ZSL)…
Recently, large-scale pre-trained Vision and Language (VL) models have set a new state-of-the-art (SOTA) in zero-shot visual classification enabling open-vocabulary recognition of potentially unlimited set of categories defined as simple…
Zero-shot intent classification is a vital and challenging task in dialogue systems, which aims to deal with numerous fast-emerging unacquainted intents without annotated training data. To obtain more satisfactory performance, the crucial…
Text classification of unseen classes is a challenging Natural Language Processing task and is mainly attempted using two different types of approaches. Similarity-based approaches attempt to classify instances based on similarities between…
Data augmentation is a widely employed technique to alleviate the problem of data scarcity. In this work, we propose a prompting-based approach to generate labelled training data for intent classification with off-the-shelf language models…
In this short paper we propose a data augmentation method for intent detection in zero-resource domains. Existing data augmentation methods rely on few labelled examples for each intent category, which can be expensive in settings with many…
This paper addresses the task of zero-shot image classification. The key contribution of the proposed approach is to control the semantic embedding of images -- one of the main ingredients of zero-shot learning -- by formulating it as a…