Related papers: Improving the Robustness of Knowledge-Grounded Dia…
Multilingual knowledge graph (KG) embeddings provide latent semantic representations of entities and structured knowledge with cross-lingual inferences, which benefit various knowledge-driven cross-lingual NLP tasks. However, precisely…
Machine-Generated Text (MGT) detection, a task that discriminates MGT from Human-Written Text (HWT), plays a crucial role in preventing misuse of text generative models, which excel in mimicking human writing style recently. Latest proposed…
Speech enhancement deep learning systems usually require large amounts of training data to operate in broad conditions or real applications. This makes the adaptability of those systems into new, low resource environments an important…
Commonsense knowledge is crucial to many natural language processing tasks. Existing works usually incorporate graph knowledge with conventional graph neural networks (GNNs), resulting in a sequential pipeline that compartmentalizes the…
Large Language Models (LLMs) demonstrate remarkable capabilities, yet struggle with hallucination and outdated knowledge when tasked with complex knowledge reasoning, resulting in factually incorrect outputs. Previous studies have attempted…
This paper improves contrastive learning for sentence embeddings from two perspectives: handling dropout noise and addressing feature corruption. Specifically, for the first perspective, we identify that the dropout noise from negative…
Knowledge distillation is a popular approach for enhancing the performance of ''student'' models, with lower representational capacity, by taking advantage of more powerful ''teacher'' models. Despite its apparent simplicity and widespread…
Knowledge graphs (KGs) have helped neural models improve performance on various knowledge-intensive tasks, like question answering and item recommendation. By using attention over the KG, such KG-augmented models can also "explain" which KG…
We present GLM-Dialog, a large-scale language model (LLM) with 10B parameters capable of knowledge-grounded conversation in Chinese using a search engine to access the Internet knowledge. GLM-Dialog offers a series of applicable techniques…
We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user and a surface realiser). We study its…
This paper addresses the persistent challenge in Keyword Spotting (KWS), a fundamental component in speech technology, regarding the acquisition of substantial labeled data for training. Given the difficulty in obtaining large quantities of…
We propose a method to make natural language understanding models more parameter efficient by storing knowledge in an external knowledge graph (KG) and retrieving from this KG using a dense index. Given (possibly multilingual) downstream…
Narrative reasoning relies on the understanding of eventualities in story contexts, which requires a wealth of background world knowledge. To help machines leverage such knowledge, existing solutions can be categorized into two groups. Some…
Responding with knowledge has been recognized as an important capability for an intelligent conversational agent. Yet knowledge-grounded dialogues, as training data for learning such a response generation model, are difficult to obtain.…
Continual learning refers to a dynamical framework in which a model receives a stream of non-stationary data over time and must adapt to new data while preserving previously acquired knowledge. Unluckily, neural networks fail to meet these…
Knowledge graph completion (KGC) aims to solve the incompleteness of knowledge graphs (KGs) by predicting missing links from known triples, numbers of knowledge graph embedding (KGE) models have been proposed to perform KGC by learning…
Incorporating external knowledge into the response generation process is essential to building more helpful and reliable dialog agents. However, collecting knowledge-grounded conversations is often costly, calling for a better pre-trained…
In neutrino physics, analyses often depend on large simulated datasets, making it essential for models to generalise effectively to real-world detector data. Contrastive learning, a well-established technique in deep learning, offers a…
In a conversational system, dynamically generating follow-up questions based on context can help users explore information and provide a better user experience. Humans are usually able to ask questions that involve some general life…
Large language models (LLMs) are becoming increasingly important for machine learning applications. However, it can be challenging to align LLMs with our intent, particularly when we want to generate content that is preferable over others…