Related papers: Zero-Shot Fact-Checking with Semantic Triples and …

An effective method for cross-lingual transfer is to fine-tune a bilingual or multilingual model on a supervised dataset in one language and evaluating it on another language in a zero-shot manner. Translating examples at training time or…

State-of-the-art semantic parsers rely on auto-regressive decoding, emitting one symbol at a time. When tested against complex databases that are unobserved at training time (zero-shot), the parser often struggles to select the correct set…

Data-driven semantic communication is based on superficial statistical patterns, thereby lacking interpretability and generalization, especially for applications with the presence of unseen data. To address these challenges, we propose a…

The number of categories for action recognition is growing rapidly. It is thus becoming increasingly hard to collect sufficient training data to learn conventional models for each category. This issue may be ameliorated by the increasingly…

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…

Parameter-efficient fine-tuning (PEFT) using labeled task data can significantly improve the performance of large language models (LLMs) on the downstream task. However, there are 7000 languages in the world and many of these languages lack…

Zero-shot audio classification aims to recognize and classify a sound class that the model has never seen during training. This paper presents a novel approach for zero-shot audio classification using automatically generated sound attribute…

Zero-shot entity retrieval, aiming to link mentions to candidate entities under the zero-shot setting, is vital for many tasks in Natural Language Processing. Most existing methods represent mentions/entities via the sentence embeddings of…

Historical text normalization often relies on small training datasets. Recent work has shown that multi-task learning can lead to significant improvements by exploiting synergies with related datasets, but there has been no systematic study…

Dialogue disentanglement aims to group utterances in a long and multi-participant dialogue into threads. This is useful for discourse analysis and downstream applications such as dialogue response selection, where it can be the first step…

In this paper, we leverage large language models (LMs) to perform zero-shot text style transfer. We present a prompting method that we call augmented zero-shot learning, which frames style transfer as a sentence rewriting task and requires…

Music classification and tagging is conducted through categorical supervised learning with a fixed set of labels. In principle, this cannot make predictions on unseen labels. Zero-shot learning is an approach to solve the problem by using…

Hashing has shown its efficiency and effectiveness in facilitating large-scale multimedia applications. Supervised knowledge e.g. semantic labels or pair-wise relationship) associated to data is capable of significantly improving the…

Concept erasure in text-to-image diffusion models is crucial for mitigating harmful content, yet existing methods often compromise generative quality. We introduce Semantic Surgery, a novel training-free, zero-shot framework for concept…

Textual explanations make image classifier decisions transparent by describing the prediction rationale in natural language. Large vision-language models can generate captions but are designed for general visual understanding, not…

Deep learning models have the ability to extract rich knowledge from large-scale datasets. However, the sharing of data has become increasingly challenging due to concerns regarding data copyright and privacy. Consequently, this hampers the…

Zero-shot learning deals with the ability to recognize objects without any visual training sample. To counterbalance this lack of visual data, each class to recognize is associated with a semantic prototype that reflects the essential…

Evidence plays a crucial role in automated fact-checking. When verifying real-world claims, existing fact-checking systems either assume the evidence sentences are given or use the search snippets returned by the search engine. Such methods…

We study the zero-shot Composed Image Retrieval (ZS-CIR) task, which is to retrieve the target image given a reference image and a description without training on the triplet datasets. Previous works generate pseudo-word tokens by…

The core problem in zero-shot open vocabulary detection is how to align visual and text features, so that the detector performs well on unseen classes. Previous approaches train the feature pyramid and detection head from scratch, which…