Related papers: Few-Shot Domain Adaptation for Grammatical Error C…
We explore and improve the capabilities of LLMs to generate data for grammatical error correction (GEC). When merely producing parallel sentences, their patterns are too simplistic to be valuable as a corpus. To address this issue, we…
Meta-learning has emerged as a trending technique to tackle few-shot text classification and achieve state-of-the-art performance. However, the performance of existing approaches heavily depends on the inter-class variance of the support…
Most few-shot learning techniques are pre-trained on a large, labeled "base dataset". In problem domains where such large labeled datasets are not available for pre-training (e.g., X-ray, satellite images), one must resort to pre-training…
Although Graph Neural Networks (GNNs) have been successful in node classification tasks, their performance heavily relies on the availability of a sufficient number of labeled nodes per class. In real-world situations, not all classes have…
Few-shot learning aims to generalize to novel classes with only a few samples with class labels. Research in few-shot learning has borrowed techniques from transfer learning, metric learning, meta-learning, and Bayesian methods. These…
Few-shot learning focuses on learning a new visual concept with very limited labelled examples. A successful approach to tackle this problem is to compare the similarity between examples in a learned metric space based on convolutional…
Few-shot learning aims at rapidly adapting to novel categories with only a handful of samples at test time, which has been predominantly tackled with the idea of meta-learning. However, meta-learning approaches essentially learn across a…
Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples. This paper proposes an adaptive margin principle to improve…
Multi-source unsupervised domain adaptation aims to leverage labeled data from multiple source domains for training a machine learning model to generalize well on a target domain without labels. Source domain selection plays a crucial role…
A Grammatical Error Correction (GEC) system produces a sequence of edits to correct an erroneous sentence. The quality of these edits is typically evaluated against human annotations. However, a sentence may admit multiple valid…
Few-shot slot tagging is an emerging research topic in the field of Natural Language Understanding (NLU). With sufficient annotated data from source domains, the key challenge is how to train and adapt the model to another target domain…
Resources for Grammatical Error Correction (GEC) in non-English languages are scarce, while available spellcheckers in these languages are mostly limited to simple corrections and rules. In this paper we introduce a first GEC corpus for…
Due to the lack of parallel data in current Grammatical Error Correction (GEC) task, models based on Sequence to Sequence framework cannot be adequately trained to obtain higher performance. We propose two data synthesis methods which can…
Grammatical error correction (GEC) is the task of detecting and correcting grammatical errors in texts written by second language learners. The statistical machine translation (SMT) approach to GEC, in which sentences written by second…
Can small language models achieve strong tool-use performance without complex adaptation mechanisms? This paper investigates this question through Meta-Tool, a controlled empirical study comparing hypernetwork-based LoRA adaptation against…
Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label…
Grammatical error correction (GEC) aims to improve text quality and readability. Previous work on the task focused primarily on high-resource languages, while low-resource languages lack robust tools. To address this shortcoming, we present…
In this work, we investigate the problems of semantic parsing in a few-shot learning setting. In this setting, we are provided with utterance-logical form pairs per new predicate. The state-of-the-art neural semantic parsers achieve less…
General translation models often still struggle to generate accurate translations in specialized domains. To guide machine translation practitioners and characterize the effectiveness of domain adaptation methods under different data…
Few-shot image generation aims to effectively adapt a source generative model to a target domain using very few training images. Most existing approaches introduce consistency constraints-typically through instance-level or…