Related papers: Learning to Adapt to Low-Resource Paraphrase Gener…
Paraphrase generation is a longstanding NLP task that has diverse applications for downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised…
Transfer learning techniques are particularly useful in NLP tasks where a sizable amount of high-quality annotated data is difficult to obtain. Current approaches directly adapt a pre-trained language model (LM) on in-domain text before…
Paraphrase generation strives to generate high-quality and diverse expressions of a given text, a domain where diffusion models excel. Though SOTA diffusion generation reconciles generation quality and diversity, textual diffusion suffers…
Although the advancements of pre-trained Large Language Models have significantly accelerated recent progress in NLP, their ever-increasing size poses significant challenges for conventional fine-tuning, especially in memory-intensive…
Paraphrase generation has benefited extensively from recent progress in the designing of training objectives and model architectures. However, previous explorations have largely focused on supervised methods, which require a large amount of…
Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks. We apply model-agnostic meta-learning (MAML) to the task of…
Paraphrases are texts that convey the same meaning while using different words or sentence structures. It can be used as an automatic data augmentation tool for many Natural Language Processing tasks, especially when dealing with…
Natural language generation (NLG) is an essential component of task-oriented dialogue systems. Despite the recent success of neural approaches for NLG, they are typically developed for particular domains with rich annotated training…
The practical success of much of NLP depends on the availability of training data. However, in real-world scenarios, training data is often scarce, not least because many application domains are restricted and specific. In this work, we…
Paraphrase generation is a long-standing task in natural language processing (NLP). Supervised paraphrase generation models, which rely on human-annotated paraphrase pairs, are cost-inefficient and hard to scale up. On the other hand,…
Over the past year, the field of Natural Language Generation (NLG) has experienced an exponential surge, largely due to the introduction of Large Language Models (LLMs). These models have exhibited the most effective performance in a range…
Controlling the generative model to adapt a new domain with limited samples is a difficult challenge and it is receiving increasing attention. Recently, methods based on meta-learning have shown promising results for few-shot domain…
Pre-trained language models (PLMs) have achieved remarkable success on various natural language understanding tasks. Simple fine-tuning of PLMs, on the other hand, might be suboptimal for domain-specific tasks because they cannot possibly…
Topic modeling plays a vital role in uncovering hidden semantic structures within text corpora, but existing models struggle in low-resource settings where limited target-domain data leads to unstable and incoherent topic inference. We…
Real-world applications of natural language processing (NLP) are challenging. NLP models rely heavily on supervised machine learning and require large amounts of annotated data. These resources are often based on language data available in…
State-of-the-art abstractive summarization models generally rely on extensive labeled data, which lowers their generalization ability on domains where such data are not available. In this paper, we present a study of domain adaptation for…
Language models pretrained on text from a wide variety of sources form the foundation of today's NLP. In light of the success of these broad-coverage models, we investigate whether it is still helpful to tailor a pretrained model to the…
Large language models (LLM) have achieved remarkable success in natural language generation but lesser focus has been given to their applicability in decision making tasks such as classification. We show that LLMs like LLaMa can achieve…
Neural Transfer Learning (TL) is becoming ubiquitous in Natural Language Processing (NLP), thanks to its high performance on many tasks, especially in low-resourced scenarios. Notably, TL is widely used for neural domain adaptation to…
Natural language processing (NLP) algorithms are rapidly improving but often struggle when applied to out-of-distribution examples. A prominent approach to mitigate the domain gap is domain adaptation, where a model trained on a source…