Related papers: Abstraction via exemplars? A representational case…
We use paraphrases as a unique source of data to analyze contextualized embeddings, with a particular focus on BERT. Because paraphrases naturally encode consistent word and phrase semantics, they provide a unique lens for investigating…
We describe a procedure for explaining neurons in deep representations by identifying compositional logical concepts that closely approximate neuron behavior. Compared to prior work that uses atomic labels as explanations, analyzing neurons…
An advantage of seq2seq abstractive summarization models is that they generate text in a free-form manner, but this flexibility makes it difficult to interpret model behavior. In this work, we analyze summarization decoders in both blackbox…
Uniform coloured Petri nets can be abstracted to their skeleton, the place/transition net that simply turns the coloured tokens into black tokens. A coloured net and its skeleton are related by a net morphism. For the application of the…
In the last few years, neural networks have been intensively used to develop meaningful distributed representations of words and contexts around them. When these representations, also known as "embeddings", are learned from unsupervised…
State-of-the-art NLP methods achieve human-like performance on many tasks, but make errors nevertheless. Characterizing these errors in easily interpretable terms gives insight into whether a classifier is prone to making systematic errors,…
We investigate the extent to which verb alternation classes, as described by Levin (1993), are encoded in the embeddings of Large Pre-trained Language Models (PLMs) such as BERT, RoBERTa, ELECTRA, and DeBERTa using selectively constructed…
Token embeddings in multilingual BERT (m-BERT) contain both language and semantic information. We find that the representation of a language can be obtained by simply averaging the embeddings of the tokens of the language. Given this…
Neural networks often learn task-specific latent representations that fail to generalize to novel settings or tasks. Conversely, humans learn discrete representations (i.e., concepts or words) at a variety of abstraction levels (e.g.,…
Mechanistic interpretability aims to reverse engineer neural networks by uncovering which high-level algorithms they implement. Causal abstraction provides a precise notion of when a network implements an algorithm, i.e., a causal model of…
The impressive performance of recent language models across a wide range of tasks suggests that they possess a degree of abstract reasoning skills. Are these skills general and transferable, or specialized to specific tasks seen during…
Neural networks are becoming a popular tool for solving many real-world problems such as object recognition and machine translation, thanks to its exceptional performance as an end-to-end solution. However, neural networks are complex…
The BERT model has arisen as a popular state-of-the-art machine learning model in the recent years that is able to cope with multiple NLP tasks such as supervised text classification without human supervision. Its flexibility to cope with…
We propose a process for investigating the extent to which sentence representations arising from neural machine translation (NMT) systems encode distinct semantic phenomena. We use these representations as features to train a natural…
We evaluate whether BERT, a widely used neural network for sentence processing, acquires an inductive bias towards forming structural generalizations through pretraining on raw data. We conduct four experiments testing its preference for…
Large scale neural models show impressive performance across a wide array of linguistic tasks. Despite this they remain, largely, black-boxes - inducing vector-representations of their input that prove difficult to interpret. This limits…
Contextual word representations derived from large-scale neural language models are successful across a diverse set of NLP tasks, suggesting that they encode useful and transferable features of language. To shed light on the linguistic…
Contextualized embeddings such as BERT can serve as strong input representations to NLP tasks, outperforming their static embeddings counterparts such as skip-gram, CBOW and GloVe. However, such embeddings are dynamic, calculated according…
Pre-trained language models such as BERT have become a more common choice of natural language processing (NLP) tasks. Research in word representation shows that isotropic embeddings can significantly improve performance on downstream tasks.…
This study investigates the internal mechanisms of BERT, a transformer-based large language model, with a focus on its ability to cluster narrative content and authorial style across its layers. Using a dataset of narratives developed via…