Related papers: Knowledge-Aware Procedural Text Understanding with…
Reinforcement Learning (RL) provides a framework in which agents can be trained, via trial and error, to solve complex decision-making problems. Learning with little supervision causes RL methods to require large amounts of data, rendering…
We present Knowledge Distillation with Meta Learning (MetaDistil), a simple yet effective alternative to traditional knowledge distillation (KD) methods where the teacher model is fixed during training. We show the teacher network can learn…
Autonomous agents often face the challenge of interpreting uncertain natural language instructions for planning tasks. Representing these instructions as Linear Temporal Logic (LTL) enables planners to synthesize actionable plans. We…
The ability to sequence unordered events is an essential skill to comprehend and reason about real world task procedures, which often requires thorough understanding of temporal common sense and multimodal information, as these procedures…
Machine reading comprehension (MRC) requires reasoning about both the knowledge involved in a document and knowledge about the world. However, existing datasets are typically dominated by questions that can be well solved by context…
We define multilevel text normalization as sequence-to-sequence processing that transforms naturally noisy text into a sequence of normalized units of meaning (morphemes) in three steps: 1) writing normalization, 2) lemmatization, 3)…
Large language models (LLMs) acquire vast knowledge from large text corpora, but this information can become outdated or inaccurate. Since retraining is computationally expensive, knowledge editing offers an efficient alternative --…
We study the problem of incorporating prior knowledge into a deep Transformer-based model,i.e.,Bidirectional Encoder Representations from Transformers (BERT), to enhance its performance on semantic textual matching tasks. By probing and…
Active learning can be defined as iterations of data labeling, model training, and data acquisition, until sufficient labels are acquired. A traditional view of data acquisition is that, through iterations, knowledge from human labels and…
Pre-trained language models are still far from human performance in tasks that need understanding of properties (e.g. appearance, measurable quantity) and affordances of everyday objects in the real world since the text lacks such…
Contextualized entity representations learned by state-of-the-art transformer-based language models (TLMs) like BERT, GPT, T5, etc., leverage the attention mechanism to learn the data context from training data corpus. However, these models…
We present a method to represent input texts by contextualizing them jointly with dynamically retrieved textual encyclopedic background knowledge from multiple documents. We apply our method to reading comprehension tasks by encoding…
Following the global COVID-19 pandemic, the number of scientific papers studying the virus has grown massively, leading to increased interest in automated literate review. We present a clinical text mining system that improves on previous…
Text-to-SQL converts natural language questions into executable SQL queries, enabling non-technical users to access relational databases for analytics and intelligent data services. In real-world scenarios, performance is often constrained…
Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintaining interpretability…
The web is full of guidance on a wide variety of tasks, from changing the oil in your car to baking an apple pie. However, as content is created independently, a single task could have thousands of corresponding procedural texts. This makes…
Procedural activity assistants potentially support humans in a variety of settings, from our daily lives, e.g., cooking or assembling flat-pack furniture, to professional situations, e.g., manufacturing or biological experiments. Despite…
This paper proposes a knowledge-based legal document assembly method that uses a machine-readable representation of knowledge of legal professionals. This knowledgebase has two components - the formal knowledge of legal norms represented as…
Recent approaches in literature have exploited the multi-modal information in documents (text, layout, image) to serve specific downstream document tasks. However, they are limited by their - (i) inability to learn cross-modal…
Methods for Visual Question Anwering (VQA) are notorious for leveraging dataset biases rather than performing reasoning, hindering generalization. It has been recently shown that better reasoning patterns emerge in attention layers of a…