Neural Language Models as Psycholinguistic Subjects: Representations of Syntactic State
This research addresses the problem of understanding syntactic representations in AI models for linguists and AI researchers, but it is incremental as it builds on existing psycholinguistic methods.
The study investigated whether neural network language models represent syntactic state incrementally by testing them on artificial sentences with complex structures, finding that LSTMs trained on large datasets show comparable syntactic state representation to an RNNG, while an LSTM trained on a small dataset does not.
We deploy the methods of controlled psycholinguistic experimentation to shed light on the extent to which the behavior of neural network language models reflects incremental representations of syntactic state. To do so, we examine model behavior on artificial sentences containing a variety of syntactically complex structures. We test four models: two publicly available LSTM sequence models of English (Jozefowicz et al., 2016; Gulordava et al., 2018) trained on large datasets; an RNNG (Dyer et al., 2016) trained on a small, parsed dataset; and an LSTM trained on the same small corpus as the RNNG. We find evidence that the LSTMs trained on large datasets represent syntactic state over large spans of text in a way that is comparable to the RNNG, while the LSTM trained on the small dataset does not or does so only weakly.