William Timkey


2023

pdf
A Language Model with Limited Memory Capacity Captures Interference in Human Sentence Processing
William Timkey | Tal Linzen
Findings of the Association for Computational Linguistics: EMNLP 2023

Two of the central factors believed to underpin human sentence processing difficulty are expectations and retrieval from working memory. A recent attempt to create a unified cognitive model integrating these two factors have relied on the parallels between the self-attention mechanism of transformer language models and cue-based retrieval theories of working memory in human sentence processing (Ryu and Lewis 2021). While the authors show that attention patterns in specialized attention heads of GPT-2 are consistent with a key prediction of cue-based retrieval models, similarity-based interference effects, their method requires the identification of syntactically specialized attention heads, and makes an cognitively implausible implicit assumption that hundreds of memory retrieval operations take place in parallel. In the present work, we develop a recurrent neural language model with a single self-attention head, which more closely parallels the memory system assumed by cognitive theories. We show that our model’s single attention head can capture semantic and syntactic interference effects observed in human experiments.

2021

pdf
To Point or Not to Point: Understanding How Abstractive Summarizers Paraphrase Text
Matt Wilber | William Timkey | Marten van Schijndel
Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

pdf
All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality
William Timkey | Marten van Schijndel
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Similarity measures are a vital tool for understanding how language models represent and process language. Standard representational similarity measures such as cosine similarity and Euclidean distance have been successfully used in static word embedding models to understand how words cluster in semantic space. Recently, these measures have been applied to embeddings from contextualized models such as BERT and GPT-2. In this work, we call into question the informativity of such measures for contextualized language models. We find that a small number of rogue dimensions, often just 1-3, dominate these measures. Moreover, we find a striking mismatch between the dimensions that dominate similarity measures and those which are important to the behavior of the model. We show that simple postprocessing techniques such as standardization are able to correct for rogue dimensions and reveal underlying representational quality. We argue that accounting for rogue dimensions is essential for any similarity-based analysis of contextual language models.