Related papers: PTab: Using the Pre-trained Language Model for Mod…

Existing audio-language task-specific predictive approaches focus on building complicated late-fusion mechanisms. However, these models are facing challenges of overfitting with limited labels and low model generalization abilities. In this…

Tabular data have been playing a mostly important role in diverse real-world fields, such as healthcare, engineering, finance, etc. The recent success of deep learning has fostered many deep networks (e.g., Transformer, ResNet) based…

We consider the problem of learning to map from natural language instructions to state transitions (actions) in a data-efficient manner. Our method takes inspiration from the idea that it should be easier to ground language to concepts that…

Sequential tabular data is one of the most commonly used data types in real-world applications. Different from conventional tabular data, where rows in a table are independent, sequential tabular data contains rich contextual and sequential…

We consider the use of automated supervised learning systems for data tables that not only contain numeric/categorical columns, but one or more text fields as well. Here we assemble 18 multimodal data tables that each contain some text…

Language models have demonstrated remarkable performance in solving reasoning tasks; however, even the strongest models still occasionally make reasoning mistakes. Recently, there has been active research aimed at improving reasoning…

Tabular data synthesis is crucial for addressing privacy and security concerns in industries reliant on tabular data. While recent advancements adopt large language models (LLMs) for realistic tabular data generation, their long training…

In this work, we aim at equipping pre-trained language models with structured knowledge. We present two self-supervised tasks learning over raw text with the guidance from knowledge graphs. Building upon entity-level masked language models,…

Results in interpretability suggest that large vision and language models learn implicit linear encodings when models are biased by in-context prompting. However, the existence of similar linear representations in more general adaptation…

Tabular data is the foundation of many applications in fields such as finance and healthcare. Although DNNs tailored for tabular data achieve competitive predictive performance, they are blackboxes with little interpretability. We introduce…

For fine-grained generation and recognition tasks such as minimally-supervised text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), the intermediate representations extracted from speech should serve as a…

Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities across modalities such as images and text. However, tabular data, despite being a critical real-world modality, remains relatively underexplored in…

Recent research has explored how Language Models (LMs) can be used for feature representation and prediction in tabular machine learning tasks. This involves employing text serialization and supervised fine-tuning (SFT) techniques. Despite…

Recent development in large language models (LLMs) has demonstrated impressive domain proficiency on unstructured textual or multi-modal tasks. However, despite with intrinsic world knowledge, their application on structured tabular data…

Pre-training on large models is prevalent and emerging with the ever-growing user-generated content in many machine learning application categories. It has been recognized that learning contextual knowledge from the datasets depicting…

Pretrained language models have achieved a new state of the art on many NLP tasks, but there are still many open questions about how and why they work so well. We investigate the contextualization of words in BERT. We quantify the amount of…

Pretrained contextualized representations offer great success for many downstream tasks, including document ranking. The multilingual versions of such pretrained representations provide a possibility of jointly learning many languages with…

The ability to acquire latent semantics is one of the key properties that determines the performance of language models. One convenient approach to invoke this ability is to prepend metadata (e.g. URLs, domains, and styles) at the beginning…

Recently, the development of pre-trained language models has brought natural language processing (NLP) tasks to the new state-of-the-art. In this paper we explore the efficiency of various pre-trained language models. We pre-train a list of…

Monolingual data has been demonstrated to be helpful in improving the translation quality of neural machine translation (NMT). The current methods stay at the usage of word-level knowledge, such as generating synthetic parallel data or…