Related papers: Hierarchical Neural Data Synthesis for Semantic Pa…

Adversarial training has been shown effective at endowing the learned representations with stronger generalization ability. However, it typically requires expensive computation to determine the direction of the injected perturbations. In…

The ability to quickly recognize and learn new visual concepts from limited samples enables humans to swiftly adapt to new environments. This ability is enabled by semantic associations of novel concepts with those that have already been…

The performance of neural network models is often limited by the availability of big data sets. To treat this problem, we survey and develop novel synthetic data generation and augmentation techniques for enhancing low/zero-sample learning…

The information retrieval community has recently witnessed a revolution due to large pretrained transformer models. Another key ingredient for this revolution was the MS MARCO dataset, whose scale and diversity has enabled zero-shot…

This paper introduces "Semantic Scaling," a novel method for ideal point estimation from text. I leverage large language models to classify documents based on their expressed stances and extract survey-like data. I then use item response…

End-to-end automatic speech recognition often degrades on domain-specific data due to scarce in-domain resources. We propose a synthetic-data-based domain adaptation framework with two contributions: (1) a large language model (LLM)-based…

Techniques to learn hash codes which can store and retrieve large dimensional multimedia data efficiently have attracted broad research interests in the recent years. With rapid explosion of newly emerged concepts and online data, existing…

Exploiting cross-lingual resources is an effective way to compensate for data scarcity of low resource languages. Recently, a novel multilingual model fusion technique has been proposed where a model is trained to learn cross-lingual…

Recently, dataset-generation-based zero-shot learning has shown promising results by training a task-specific model with a dataset synthesized from large pre-trained language models (PLMs). The final task-specific model often achieves…

Although Deep Convolutional Neural Networks trained with strong pixel-level annotations have significantly pushed the performance in semantic segmentation, annotation efforts required for the creation of training data remains a roadblock…

Semantic segmentation models are limited in their ability to scale to large numbers of object classes. In this paper, we introduce the new task of zero-shot semantic segmentation: learning pixel-wise classifiers for never-seen object…

Existing studies on semantic parsing mainly focus on the in-domain setting. We formulate cross-domain semantic parsing as a domain adaptation problem: train a semantic parser on some source domains and then adapt it to the target domain.…

The task of Semantic Parsing can be approximated as a transformation of an utterance into a logical form graph where edges represent semantic roles and nodes represent word senses. The resulting representation should be capture the meaning…

In neural machine translation (NMT), monolingual data in the target language are usually exploited through a method so-called "back-translation" to synthesize additional training parallel data. The synthetic data have been shown helpful to…

We analyze the process of creating word embedding feature representations designed for a learning task when annotated data is scarce, for example, in depressive language detection from Tweets. We start with a rich word embedding pre-trained…

Adapting keyphrase generation models to new domains typically involves few-shot fine-tuning with in-domain labeled data. However, annotating documents with keyphrases is often prohibitively expensive and impractical, requiring expert…

Deep learning generates state-of-the-art semantic segmentation provided that a large number of images together with pixel-wise annotations are available. To alleviate the expensive data collection process, we propose a semi-supervised…

Although convolutional neural networks have been proven to be an effective tool to generate high quality maps from remote sensing images, their performance significantly deteriorates when there exists a large domain shift between training…

We evaluate the character-level translation method for neural semantic parsing on a large corpus of sentences annotated with Abstract Meaning Representations (AMRs). Using a sequence-to-sequence model, and some trivial preprocessing and…

The state of the art in semantic segmentation is steadily increasing in performance, resulting in more precise and reliable segmentations in many different applications. However, progress is limited by the cost of generating labels for…