Related papers: Modularity in inductively-learned word pronunciati…

Several explanation methods such as Integrated Gradients (IG) can be characterised as path-based methods, as they rely on a straight line between the data and an uninformative baseline. However, when applied to language models, these…

We consider the problem of minimising the number of states in a multiplicity tree automaton over the field of rational numbers. We give a minimisation algorithm that runs in polynomial time assuming unit-cost arithmetic. We also show that a…

The development of models of human sentence processing has traditionally followed one of two paths. Either the model posited a sequence of processing modules, each with its own task-specific knowledge (e.g., syntax and semantics), or it…

We introduce a typology-aware diagnostic for multilingual masked language models that tests reliance on word order versus inflectional form. Using Universal Dependencies, we apply inference-time perturbations: full token scrambling,…

Prompt tuning has achieved great success in transferring the knowledge from large pretrained vision-language models into downstream tasks, and has dominated the performance on visual grounding (VG). However, almost all existing prompt…

Large language models (LLMs) demonstrate exceptional instruct-following ability to complete various downstream tasks. Although this impressive ability makes LLMs flexible task solvers, their performance in solving tasks also heavily relies…

It is challenging for models to understand complex, multimodal content such as television clips, and this is in part because video-language models often rely on single-modality reasoning and lack interpretability. To combat these issues we…

Tree ensembles are very popular machine learning models, known for their effectiveness in supervised classification and regression tasks. Their performance derives from aggregating predictions of multiple decision trees, which are renowned…

There are two shortages in the current Large Language Models (LLMs) era. The first is short of multilingual models, where most LLMs are English-centric and performance is limited on multilingual reasoning. The second is the place of…

Integrated interpretability without sacrificing the prediction accuracy of decision making algorithms has the potential of greatly improving their value to the user. Instead of assigning a label to an image directly, we propose to learn…

Intent classification has been widely researched on English data with deep learning approaches that are based on neural networks and word embeddings. The challenge for Chinese intent classification stems from the fact that, unlike English…

Automated interlinear gloss prediction with neural networks is a promising approach to accelerate language documentation efforts. However, while state-of-the-art models like GlossLM achieve high scores on glossing benchmarks, user studies…

We propose a novel dependency-based hybrid tree model for semantic parsing, which converts natural language utterance into machine interpretable meaning representations. Unlike previous state-of-the-art models, the semantic information is…

Circuit representations are becoming the lingua franca to express and reason about tractable generative and discriminative models. In this paper, we show how complex inference scenarios for these models that commonly arise in machine…

A longstanding question in cognitive science concerns the learning mechanisms underlying compositionality in human cognition. Humans can infer the structured relationships (e.g., grammatical rules) implicit in their sensory observations…

When we speak, write or listen, we continuously make predictions based on our knowledge of a language's grammar. Remarkably, children acquire this grammatical knowledge within just a few years, enabling them to understand and generalise to…

In conventional speech recognition, phoneme-based models outperform grapheme-based models for non-phonetic languages such as English. The performance gap between the two typically reduces as the amount of training data is increased. In this…

Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus achieving efficiency…

Current state-of-the-art models for natural language understanding require a preprocessing step to convert raw text into discrete tokens. This process known as tokenization relies on a pre-built vocabulary of words or sub-word morphemes.…

Revealing the syntactic structure of sentences in Chinese poses significant challenges for word-level parsers due to the absence of clear word boundaries. To facilitate a transition from word-level to character-level Chinese dependency…