Related papers: Cross-Domain Content Generation with Domain-Specif…

Cross-domain text classification aims to adapt models to a target domain that lacks labeled data. It leverages or reuses rich labeled data from the different but related source domain(s) and unlabeled data from the target domain. To this…

Despite recent advancements in domain adaptation techniques for large language models, these methods remain computationally intensive, and the resulting models can still exhibit hallucination issues. Most existing adaptation methods do not…

Open-retrieval question answering systems are generally trained and tested on large datasets in well-established domains. However, low-resource settings such as new and emerging domains would especially benefit from reliable question…

We systematically study how three large language models with code capabilities - CodeT5, Codex, and ChatGPT - generalize to out-of-domain data. We consider two fundamental applications - code summarization, and code generation. We split…

Cross-Domain Sequential Recommendation (CDSR) aims to mine and transfer users' sequential preferences across different domains to alleviate the long-standing cold-start issue. Traditional CDSR models capture collaborative information…

Domain adaptive pretraining, i.e. the continued unsupervised pretraining of a language model on domain-specific text, improves the modelling of text for downstream tasks within the domain. Numerous real-world applications are based on…

Recent work has shown that self-supervised dialog-specific pretraining on large conversational datasets yields substantial gains over traditional language modeling (LM) pretraining in downstream task-oriented dialog (TOD). These approaches,…

Providing plausible responses to why questions is a challenging but critical goal for language based human-machine interaction. Explanations are challenging in that they require many different forms of abstract knowledge and reasoning.…

We propose a simple but effective multi-source domain generalization technique based on deep neural networks by incorporating optimized normalization layers that are specific to individual domains. Our approach employs multiple…

Tokenization -- the process of decomposing a given text into a sequence of subwords called tokens -- is one of the key components in the development of language models. Particularly, auto-regressive language models generate texts token by…

Pre-trained large text-to-image (T2I) models with an appropriate text prompt has attracted growing interests in customized images generation field. However, catastrophic forgetting issue make it hard to continually synthesize new…

Domain dependence and annotation subjectivity pose challenges for supervised keyword extraction. Based on the premises that second-order keyness patterns are existent at the community level and learnable from annotated keyword extraction…

High accuracy speech recognition requires a large amount of transcribed data for supervised training. In the absence of such data, domain adaptation of a well-trained acoustic model can be performed, but even here, high accuracy usually…

Large language models (LLMs) offer promise for dynamic game content generation, but they face critical barriers, including narrative incoherence and high operational costs. Due to their large size, they are often accessed in the cloud,…

We study the problem of generating keyphrases that summarize the key points for a given document. While sequence-to-sequence (seq2seq) models have achieved remarkable performance on this task (Meng et al., 2017), model training often relies…

Recent instruction-finetuned large language models (LMs) have achieved notable performances in various tasks, such as question-answering (QA). However, despite their ability to memorize a vast amount of general knowledge across diverse…

This survey reviews how large language models (LLMs) are transforming synthetic training data generation in both natural language and code domains. By producing artificial but task-relevant examples, these models can significantly augment…

Current state-of-the-art automatic speech recognition systems are trained to work in specific `domains', defined based on factors like application, sampling rate and codec. When such recognizers are used in conditions that do not match the…

Recent research efforts have shown that neural architectures can be effective in conventional information extraction tasks such as named entity recognition, yielding state-of-the-art results on standard newswire datasets. However, despite…

The scarcity of domain-specific dialogue datasets limits the development of dialogue systems across applications. Existing research is constrained by general or niche datasets that lack sufficient scale for training dialogue systems. To…