相关论文: An Empirical Investigation of Commonsense Self-Sup…

Commonsense reasoning benchmarks have been largely solved by fine-tuning language models. The downside is that fine-tuning may cause models to overfit to task-specific data and thereby forget their knowledge gained during pre-training.…

Grasping the commonsense properties of everyday concepts is an important prerequisite to language understanding. While contextualised language models are reportedly capable of predicting such commonsense properties with human-level…

Language Models (LMs) can perform new tasks by adapting to a few in-context examples. For humans, explanations that connect examples to task principles can improve learning. We therefore investigate whether explanations of few-shot examples…

This chapter illustrates how suitable neuro-symbolic models for language understanding can enable domain generalizability and robustness in downstream tasks. Different methods for integrating neural language models and knowledge graphs are…

In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both…

Reasoning is an integral part of many tasks performed by language models (LMs). However, the effects of scaling model sizes and data on reasoning abilities at pretraining time remain understudied. To rigorously investigate this problem, we…

Grounded language models use external sources of information, such as knowledge graphs, to meet some of the general challenges associated with pre-training. By extending previous work on compositional generalization in semantic parsing, we…

Composing basic skills from simple tasks to accomplish composite tasks is crucial for modern intelligent systems. We investigate the in-context composition ability of language models to perform composite tasks that combine basic skills…

Retrieval-augmented language models have demonstrated performance comparable to much larger models while requiring fewer computational resources. The effectiveness of these models crucially depends on the overlap between query and retrieved…

Scaling existing applications and solutions to multiple human languages has traditionally proven to be difficult, mainly due to the language-dependent nature of preprocessing and feature engineering techniques employed in traditional…

Learning good representations without supervision is still an open issue in machine learning, and is particularly challenging for speech signals, which are often characterized by long sequences with a complex hierarchical structure. Some…

Despite their strong performance on many tasks, pre-trained language models have been shown to struggle on out-of-distribution compositional generalization. Meanwhile, recent work has shown considerable improvements on many NLP tasks from…

Domain adaptation aims to enable Large Language Models (LLMs) to generalize domain datasets unseen effectively during the training phase. However, factors such as the size of the model parameters and the scale of training data are general…

Compressing self-supervised models has become increasingly necessary, as self-supervised models become larger. While previous approaches have primarily focused on compressing the model size, shortening sequences is also effective in…

Pre-trained language models have shown excellent results in few-shot learning scenarios using in-context learning. Although it is impressive, the size of language models can be prohibitive to make them usable in on-device applications, such…

Language models (LMs) trained on large amounts of data have shown impressive performance on many NLP tasks under the zero-shot and few-shot setup. Here we aim to better understand the extent to which such models learn commonsense knowledge…

Large scale databases with high-quality manual annotations are scarce in audio domain. We thus explore a self-supervised graph approach to learning audio representations from highly limited labelled data. Considering each audio sample as a…

Commonsense question answering is a crucial task that requires machines to employ reasoning according to commonsense. Previous studies predominantly employ an extracting-and-modeling paradigm to harness the information in KG, which first…

Conversational question answering systems often rely on semantic parsing to enable interactive information retrieval, which involves the generation of structured database queries from a natural language input. For information-seeking…

Decoding strategies largely determine the quality of Large Language Model (LLM) outputs, yet widely used heuristics such as greedy or fixed temperature/top-p decoding are static and often task-agnostic, leading to suboptimal or inconsistent…