Related papers: Learning to Select External Knowledge with Multi-S…

The extraction of structured information from raw text is a fundamental component of many NLP applications, including document retrieval, ranking, and relevance estimation. High-quality extractions often require domain-specific accuracy,…

Incorporating external knowledge into dialogue generation has been proven to benefit the performance of an open-domain Dialogue System (DS), such as generating informative or stylized responses, controlling conversation topics. In this…

Loading models pre-trained on the large-scale corpus in the general domain and fine-tuning them on specific downstream tasks is gradually becoming a paradigm in Natural Language Processing. Previous investigations prove that introducing a…

In large-scale domain classification, an utterance can be handled by multiple domains with overlapped capabilities. However, only a limited number of ground-truth domains are provided for each training utterance in practice while knowing as…

Event Extraction bridges the gap between text and event signals. Based on the assumption of trigger-argument dependency, existing approaches have achieved state-of-the-art performance with expert-designed templates or complicated decoding…

How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans. To handle this problem, memory networks are usually a great choice and a promising way. However,…

The feedback that AI systems (e.g., recommender systems, chatbots) collect from user interactions is a crucial source of training data. While short-term feedback (e.g., clicks, engagement) is widely used for training, there is ample…

We participate in the DSTC9 Interactive Dialogue Evaluation Track (Gunasekara et al. 2020) sub-task 1 (Knowledge Grounded Dialogue) and sub-task 2 (Interactive Dialogue). In sub-task 1, we employ a pre-trained language model to generate…

Learning control policies offline from pre-recorded datasets is a promising avenue for solving challenging real-world problems. However, available datasets are typically of mixed quality, with a limited number of the trajectories that we…

Large Language Models (LLMs) have demonstrated strong performance across a wide range of NLP tasks. However, they often exhibit suboptimal behaviors and inconsistencies when exposed to unfamiliar external information, underscoring their…

In recent years, many explanation methods have been proposed to explain individual classifications of deep neural networks. However, how to leverage the created explanations to improve the learning process has been less explored. As the…

Outside-knowledge visual question answering is a challenging task that requires both the acquisition and the use of open-ended real-world knowledge. Some existing solutions draw external knowledge into the cross-modality space which…

It is often observed in knowledge-centric tasks (e.g., common sense question and answering, relation classification) that the integration of external knowledge such as entity representation into language models can help provide useful…

This paper discusses our approaches for task-oriented conversational modelling using subjective knowledge, with a particular emphasis on response generation. Our methodology was shaped by an extensive data analysis that evaluated key…

Generating natural and informative texts has been a long-standing problem in NLP. Much effort has been dedicated into incorporating pre-trained language models (PLMs) with various open-world knowledge, such as knowledge graphs or wiki…

Traditionally, training neural networks to perform semantic segmentation required expensive human-made annotations. But more recently, advances in the field of unsupervised learning have made significant progress on this issue and towards…

Task-specific word identification aims to choose the task-related words that best describe a short text. Existing approaches require well-defined seed words or lexical dictionaries (e.g., WordNet), which are often unavailable for many…

Natural language understanding involves reading between the lines with implicit background knowledge. Current systems either rely on pre-trained language models as the sole implicit source of world knowledge, or resort to external knowledge…

The recent history of machine learning research has taught us that machine learning methods can be most effective when they are provided with very large, high-capacity models, and trained on very large and diverse datasets. This has spurred…

We propose a new Reject Option Classification technique to identify and remove regions of uncertainty in the decision space for a given neural classifier and dataset. Such existing formulations employ a learned rejection (remove)/selection…