Brian W. Dillon

Also published as: Brian Dillon


2022

pdf
How Much Do Modifications to Transformer Language Models Affect Their Ability to Learn Linguistic Knowledge?
Simeng Sun | Brian Dillon | Mohit Iyyer
Proceedings of the Third Workshop on Insights from Negative Results in NLP

Recent progress in large pretrained language models (LMs) has led to a growth of analyses examining what kinds of linguistic knowledge are encoded by these models. Due to computational constraints, existing analyses are mostly conducted on publicly-released LM checkpoints, which makes it difficult to study how various factors during training affect the models’ acquisition of linguistic knowledge. In this paper, we train a suite of small-scale Transformer LMs that differ from each other with respect to architectural decisions (e.g., self-attention configuration) or training objectives (e.g., multi-tasking, focal loss). We evaluate these LMs on BLiMP, a targeted evaluation benchmark of multiple English linguistic phenomena. Our experiments show that while none of these modifications yields significant improvements on aggregate, changes to the loss function result in promising improvements on several subcategories (e.g., detecting adjunct islands, correctly scoping negative polarity items). We hope our work offers useful insights for future research into designing Transformer LMs that more effectively learn linguistic knowledge.

pdf
Syntactic Surprisal From Neural Models Predicts, But Underestimates, Human Processing Difficulty From Syntactic Ambiguities
Suhas Arehalli | Brian Dillon | Tal Linzen
Proceedings of the 26th Conference on Computational Natural Language Learning (CoNLL)

Humans exhibit garden path effects: When reading sentences that are temporarily structurally ambiguous, they slow down when the structure is disambiguated in favor of the less preferred alternative. Surprisal theory (Hale, 2001; Levy, 2008), a prominent explanation of this finding, proposes that these slowdowns are due to the unpredictability of each of the words that occur in these sentences. Challenging this hypothesis, van Schijndel and Linzen (2021) find that estimates of the cost of word predictability derived from language models severely underestimate the magnitude of human garden path effects. In this work, we consider whether this underestimation is due to the fact that humans weight syntactic factors in their predictions more highly than language models do. We propose a method for estimating syntactic predictability from a language model, allowing us to weigh the cost of lexical and syntactic predictability independently. We find that treating syntactic predictability independently from lexical predictability indeed results in larger estimates of garden path. At the same time, even when syntactic predictability is independently weighted, surprisal still greatly underestimate the magnitude of human garden path effects. Our results support the hypothesis that predictability is not the only factor responsible for the processing cost associated with garden path sentences.

2019

pdf
Guess Who’s Coming (and Who’s Going): Bringing Perspective to the Rational Speech Acts Framework
Carolyn Jane Anderson | Brian W. Dillon
Proceedings of the Society for Computation in Linguistics (SCiL) 2019

2018

pdf
Evaluating Grammaticality in Seq2seq Models with a Broad Coverage HPSG Grammar: A Case Study on Machine Translation
Johnny Wei | Khiem Pham | Brendan O’Connor | Brian Dillon
Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP

Sequence to sequence (seq2seq) models are often employed in settings where the target output is natural language. However, the syntactic properties of the language generated from these models are not well understood. We explore whether such output belongs to a formal and realistic grammar, by employing the English Resource Grammar (ERG), a broad coverage, linguistically precise HPSG-based grammar of English. From a French to English parallel corpus, we analyze the parseability and grammatical constructions occurring in output from a seq2seq translation model. Over 93% of the model translations are parseable, suggesting that it learns to generate conforming to a grammar. The model has trouble learning the distribution of rarer syntactic rules, and we pinpoint several constructions that differentiate translations between the references and our model.