Related papers: Knowledge-Aware Procedural Text Understanding with…

Traditional knowledge distillation adopts a two-stage training process in which a teacher model is pre-trained and then transfers the knowledge to a compact student model. To overcome the limitation, online knowledge distillation is…

With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the performance gains of…

Writing is a complex non-linear process that begins with a mental model of intent, and progresses through an outline of ideas, to words on paper (and their subsequent refinement). Despite past research in understanding writing, Web-scale…

Deep learning has become the workhorse for a wide range of natural language processing applications. But much of the success of deep learning relies on annotated examples. Annotation is time-consuming and expensive to produce at scale. Here…

Comprehending procedural text, e.g., a paragraph describing photosynthesis, requires modeling actions and the state changes they produce, so that questions about entities at different timepoints can be answered. Although several recent…

Fine-tuning large language models (LLMs) with high-quality knowledge has been shown to enhance their performance effectively. However, there is a paucity of research on the depth of domain-specific knowledge comprehension by LLMs and the…

We introduce a novel large language model (LLM)-driven agent framework, which iteratively refines queries and filters contextual evidence by leveraging dynamically evolving knowledge. A defining feature of the system is its decoupling of…

Multi-task learning (MTL) aims at improving the generalization performance of several related tasks by leveraging useful information contained in them. However, in industrial scenarios, interpretability is always demanded, and the data of…

Rule-based machine translation is a machine translation paradigm where linguistic knowledge is encoded by an expert in the form of rules that translate text from source to target language. While this approach grants extensive control over…

The new generation of state-of-the-art computer vision systems are trained from natural language supervision, ranging from simple object category names to descriptive captions. This form of supervision ensures high generality and usability…

The open-ended question answering task of Text-VQA often requires reading and reasoning about rarely seen or completely unseen scene-text content of an image. We address this zero-shot nature of the problem by proposing the generalized use…

We propose, in this paper, a model of continuous use of corporate collaborative KMS. Companies do not always have the guaranty that their KMS will be continuously used. This statement can constitute an important obstacle for knowledge…

KEPLMs are pre-trained models that utilize external knowledge to enhance language understanding. Previous language models facilitated knowledge acquisition by incorporating knowledge-related pre-training tasks learned from relation triples…

In this work we present Knowledge Module Learning (KML) to understand and reason over procedural tasks that requires models to learn structured and compositional procedural knowledge. KML is a neurosymbolic framework that learns relation…

Large language models (LLMs) have achieved substantial advances in logical reasoning, yet they continue to lag behind human-level performance. In-context learning provides a viable solution that boosts the model's performance via prompting…

Video-and-language pre-training has shown promising results for learning generalizable representations. Most existing approaches usually model video and text in an implicit manner, without considering explicit structural representations of…

This paper presents a complete explainable system that interprets a set of data, abstracts the underlying features and describes them in a natural language of choice. The system relies on two crucial stages: (i) identifying emerging…

As the development of the encoder-decoder architecture, researchers are able to study the text generation tasks with broader types of data. Among them, KB-to-text aims at converting a set of knowledge triples into human readable sentences.…

Neural semantic parsing has achieved impressive results in recent years, yet its success relies on the availability of large amounts of supervised data. Our goal is to learn a neural semantic parser when only prior knowledge about a limited…

Dynamically integrating new or rapidly evolving information after (Large) Language Model pre-training remains challenging, particularly in low-data scenarios or when dealing with private and specialized documents. In-context learning and…