Can RNNs trained on harder subject-verb agreement instances still perform well on easier ones?

Previous work suggests that RNNs trained on natural language corpora can capture number agreement well for simple sentences but perform less well when sentences contain agreement attractors: intervening nouns between the verb and the main subject with grammatical number opposite to the latter. This suggests these models may not learn the actual syntax of agreement, but rather infer shallower heuristics such as `agree with the recent noun'. In this work, we investigate RNN models with varying inductive biases trained on selectively chosen `hard' agreement instances, i.e., sentences with at least one agreement attractor. For these the verb number cannot be predicted using a simple linear heuristic, and hence they might help provide the model additional cues for hierarchical syntax. If RNNs can learn the underlying agreement rules when trained on such hard instances, then they should generalize well to other sentences, including simpler ones. However, we observe that several RNN types, including the ONLSTM which has a soft structural inductive bias, surprisingly fail to perform well on sentences without attractors when trained solely on sentences with attractors. We analyze how these selectively trained RNNs compare to the baseline (training on a natural distribution of agreement attractors) along the dimensions of number agreement accuracy, representational similarity, and performance across different syntactic constructions. Our findings suggest that RNNs trained on our hard agreement instances still do not capture the underlying syntax of agreement, but rather tend to overfit the training distribution in a way which leads them to perform poorly on `easy' out-of-distribution instances. Thus, while RNNs are powerful models which can pick up non-trivial dependency patterns, inducing them to do so at the level of syntax rather than surface remains a challenge.