Attribution Analysis of Grammatical Dependencies in LSTMs
LSTM language models have been shown to capture syntax-sensitive grammatical dependencies such as subject-verb agreement with a high degree of accuracy (Linzen et al., 2016, inter alia). However, questions remain regarding whether they do so using spurious correlations, or whether they are truly able to match verbs with their subjects. This paper argues for the latter hypothesis. Using layer-wise relevance propagation (Bach et al., 2015), a technique that quantifies the contributions of input features to model behavior, we show that LSTM performance on number agreement is directly correlated with the model's ability to distinguish subjects from other nouns. Our results suggest that LSTM language models are able to infer robust representations of syntactic dependencies.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies
The success of long short-term memory (LSTM) neural networks in language processing is typically attributed to their ability to capture long-distance statistical regularities. Linguistic regularities are often sensitive …
Language ModelingLanguage ModellingSubregular Complexity and Deep Learning
This paper argues that the judicial use of formal language theory and grammatical inference are invaluable tools in understanding how deep neural networks can and cannot represent and learn long-term dependencies in temp…
Deep LearningTemporal SequencesDo LSTMs See Gender? Probing the Ability of LSTMs to Learn Abstract Syntactic Rules
LSTMs trained on next-word prediction can accurately perform linguistic tasks that require tracking long-distance syntactic dependencies. Notably, model accuracy approaches human performance on number agreement tasks (Gu…
ArticlesHow much complexity does an RNN architecture need to learn syntax-sensitive dependencies?
Long short-term memory (LSTM) networks and their variants are capable of encapsulating long-range dependencies, which is evident from their performance on a variety of linguistic tasks. On the other hand, simple recurren…
Language ModelingLanguage ModellingSentenceCLaC at SemEval-2020 Task 5: Muli-task Stacked Bi-LSTMs
We consider detection of the span of antecedents and consequents in argumentative prose a structural, grammatical task. Our system comprises a set of stacked Bi-LSTMs trained on two complementary linguistic annotations. …
Multi-Task LearningPOSWord Embeddings