Probing Linguistic Systematicity

Goodwin, Emily; Sinha, Koustuv; O’Donnell, Timothy J.

doi:10.18653/v1/2020.acl-main.177

Cited by 46 publications

(39 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Defining disjoint train/test splits is enough to foil truly unsystematic models (e.g., simple look-up tables). However, building on much previous work (Lake and Baroni, 2018;Hupkes et al, 2019;Yanaka et al, 2020;Bahdanau et al, 2018;Goodwin et al, 2020;Geiger et al, 2019), we contend that a randomly constructed disjoint train/test split only diag-noses the most basic level of systematicity. More difficult systematic generalization tasks will only be solved by models exhibiting more complex compositional structures.…”

Section: A Systematic Generalization Taskmentioning

confidence: 92%

See 1 more Smart Citation

Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation

Geiger¹,

Richardson²,

Potts³

2020

Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP

View full text Add to dashboard Cite

We address whether neural models for Natural Language Inference (NLI) can learn the compositional interactions between lexical entailment and negation, using four methods: the behavioral evaluation methods of (1) challenge test sets and (2) systematic generalization tasks, and the structural evaluation methods of (3) probes and ( 4) interventions. To facilitate this holistic evaluation, we present Monotonicity NLI (MoNLI), a new naturalistic dataset focused on lexical entailment and negation. In our behavioral evaluations, we find that models trained on general-purpose NLI datasets fail systematically on MoNLI examples containing negation, but that MoNLI fine-tuning addresses this failure. In our structural evaluations, we look for evidence that our top-performing BERT-based model has learned to implement the monotonicity algorithm behind MoNLI. Probes yield evidence consistent with this conclusion, and our intervention experiments bolster this, showing that the causal dynamics of the model mirror the causal dynamics of this algorithm on subsets of MoNLI. This suggests that the BERT model at least partially embeds a theory of lexical entailment and negation at an algorithmic level.

show abstract

Section: A Systematic Generalization Taskmentioning

confidence: 92%

“…There are often strong intuitions that certain generalization tasks are only solved by models with systematic structures. These tasks are referred to as systematic generalization tasks (Lake and Baroni, 2018;Hupkes et al, 2019;Yanaka et al, 2020;Bahdanau et al, 2018;Geiger et al, 2019;Goodwin et al, 2020).…”

Section: Related Workmentioning

confidence: 99%

Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation

Geiger¹,

Richardson²,

Potts³

2020

Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP

View full text Add to dashboard Cite

show abstract

“…There is also a lively debate in cognitive science as to how important rule-based reasoning is for human cognition (Politzer, 2007). Yanaka et al (2020); Goodwin et al (2020) are concurrent studies of systematicity in PLMs. The first shows that monotonicity inference is feasible for syntactic structures close to the ones observed during training.…”

Section: Limitationsmentioning

confidence: 99%

Are Pretrained Language Models Symbolic Reasoners over Knowledge?

Kassner¹,

Krojer²,

Schütze³

2020

Proceedings of the 24th Conference on Computational Natural Language Learning

View full text Add to dashboard Cite

How can pretrained language models (PLMs) learn factual knowledge from the training set? We investigate the two most important mechanisms: reasoning and memorization. Prior work has attempted to quantify the number of facts PLMs learn, but we present, using synthetic data, the first study that investigates the causal relation between facts present in training and facts learned by the PLM. For reasoning, we show that PLMs seem to learn to apply some symbolic reasoning rules correctly but struggle with others, including two-hop reasoning. Further analysis suggests that even the application of learned reasoning rules is flawed. For memorization, we identify schema conformity (facts systematically supported by other facts) and frequency as key factors for its success.

show abstract

“…Our work builds upon a large body of research intended to probe which aspects of language and meaning are being captured by large LMs. Most closely related is work that assesses whether models can perform symbolic reasoning about language e.g., quantifiers or negation (Talmor et al, 2020;Ettinger, 2020;Wang et al, 2018) or by measuring the systematicity of models' inferences (Goodwin et al, 2020;Kim and Linzen, 2020;Yanaka et al, 2020;Warstadt et al, 2019). Such work has tended to find that LMs reason primarily contextually as opposed to abstractly.…”

Section: Related Workmentioning

confidence: 99%

AND does not mean OR: Using Formal Languages to Study Language Models’ Representations

Traylor¹,

Feiman²,

Pavlick³

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

A current open question in natural language processing is to what extent language models, which are trained with access only to the form of language, are able to capture the meaning of language. In many cases, meaning constrains form in consistent ways. This raises the possibility that some kinds of information about form might reflect meaning more transparently than others. The goal of this study is to investigate under what conditions we can expect meaning and form to covary sufficiently, such that a language model with access only to form might nonetheless succeed in emulating meaning. Focusing on propositional logic, we generate training corpora using a variety of motivated constraints, and measure a distributional language model's ability to differentiate logical symbols (¬, ∧, ∨). Our findings are largely negative: none of our simulated training corpora result in models which definitively differentiate meaningfully different symbols (e.g., ∧ vs. ∨), suggesting a limitation to the types of semantic signals that current models are able to exploit.

show abstract

Probing Linguistic Systematicity

Cited by 46 publications

References 44 publications

Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation

Neural Natural Language Inference Models Partially Embed Theories of Lexical Entailment and Negation

Are Pretrained Language Models Symbolic Reasoners over Knowledge?

AND does not mean OR: Using Formal Languages to Study Language Models’ Representations

Contact Info

Product

Resources

About