Related papers: How Do Transformers Learn Topic Structure: Towards…

The transformer structure employed in large language models (LLMs), as a specialized category of deep neural networks (DNNs) featuring attention mechanisms, stands out for their ability to identify and highlight the most relevant aspects of…

Transformer is a ubiquitous model for natural language processing and has attracted wide attentions in computer vision. The attention maps are indispensable for a transformer model to encode the dependencies among input tokens. However,…

Distributed word representations have been demonstrated to be effective in capturing semantic and syntactic regularities. Unsupervised representation learning from large unlabeled corpora can learn similar representations for those words…

The way the words are used evolves through time, mirroring cultural or technological evolution of society. Semantic change detection is the task of detecting and analysing word evolution in textual data, even in short periods of time. In…

Open-text (or open-domain) semantic parsers are designed to interpret any statement in natural language by inferring a corresponding meaning representation (MR). Unfortunately, large scale systems cannot be easily machine-learned due to…

Representation learning is the foundation of machine reading comprehension and inference. In state-of-the-art models, character-level representations have been broadly adopted to alleviate the problem of effectively representing rare or…

In this work, we study the representation space of contextualized embeddings and gain insight into the hidden topology of large language models. We show there exists a network of latent states that summarize linguistic properties of…

Transformer architectures are typically described in algorithmic and statistical terms, leaving their internal mechanics without a familiar structural language for researchers trained in physical theories. To bridge this gap, we develop a…

Large language models (LLMs) can produce long, coherent passages of text, suggesting that LLMs, although trained on next-word prediction, must represent the latent structure that characterizes a document. Prior work has found that internal…

The process by which Large Language Models (LLMs) acquire complex capabilities during training remains a key open question in mechanistic interpretability. This project investigates whether these learning dynamics can be characterized…

Pre-trained transformer language models have shown remarkable performance on a variety of NLP tasks. However, recent research has suggested that phrase-level representations in these models reflect heavy influences of lexical content, but…

The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…

The long-distance agreement, evidence for syntactic structure, is increasingly used to assess the syntactic generalization of Neural Language Models. Much work has shown that transformers are capable of high accuracy in varied agreement…

We investigate how word meanings are represented in the transformer language models. Specifically, we focus on whether transformer models employ something analogous to a lexical store - where each word has an entry that contains semantic…

Contextual word representations derived from pre-trained bidirectional language models (biLMs) have recently been shown to provide significant improvements to the state of the art for a wide range of NLP tasks. However, many questions…

Despite the growing use of transformer models in computer vision, a mechanistic understanding of these networks is still needed. This work introduces a method to reverse-engineer Vision Transformers trained to solve image classification…

The transformer is the most popular neural architecture for language modeling. The cornerstone of the transformer is its global attention mechanism, which lets the model aggregate information from all preceding tokens before generating the…

Attention mechanisms have become a popular component in deep neural networks, yet there has been little examination of how different influencing factors and methods for computing attention from these factors affect performance. Toward a…

Document network embedding aims at learning representations for a structured text corpus i.e. when documents are linked to each other. Recent algorithms extend network embedding approaches by incorporating the text content associated with…

Recent work has shown that the encoder-decoder attention mechanisms in neural machine translation (NMT) are different from the word alignment in statistical machine translation. In this paper, we focus on analyzing encoder-decoder attention…