Syntactic parsers have dominated natural language understanding for decades. Yet, their syntactic interpretations are losing centrality in downstream tasks due to the success of large-scale textual representation learners. In this paper, we propose KERMIT (Kernelinspired Encoder with Recursive Mechanism for Interpretable Trees) to embed symbolic syntactic parse trees into artificial neural networks and to visualize how syntax is used in inference. We experimented with KERMIT paired with two state-of-the-art transformerbased universal sentence encoders (BERT and XLNet) and we showed that KERMIT can indeed boost their performance by effectively embedding human-coded universal syntactic representations in neural networks.

Pre-trained Transformers are challenging human performances in many natural language processing tasks. The gigantic datasets used for pre-training seem to be the key for their success on existing tasks. In this paper, we explore how a range of pre-trained natural language understanding models perform on truly novel and unexplored data, provided by classification tasks over a DarkNet corpus. Surprisingly, results show that syntactic and lexical neural networks largely outperform pre-trained Transformers. This seems to suggest that pre-trained Transformers have serious difficulties in adapting to radically novel texts.

The dazzling success of neural networks over natural language processing systems is imposing an urgent need to control their behavior with simpler, more direct declarative rules. In this paper, we propose Pat-in-the-Loop as a model to control a specific class of syntax-oriented neural networks by adding declarative rules. In Pat-in-the-Loop, distributed tree encoders allow to exploit parse trees in neural networks, heat parse trees visualize activation of parse trees, and parse subtrees are used as declarative rules in the neural network. Hence, Pat-in-the-Loop is a model to include human control in specific natural language processing (NLP)-neural network (NN) systems that exploit syntactic information, which we will generically call Pat. A pilot study on question classification showed that declarative rules representing human knowledge, injected by Pat, can be effectively used in these neural networks to ensure correctness, relevance, and cost-effective.

Masked language modeling (MLM) pre-training methods such as BERT corrupt the input by replacing some tokens with [MASK] and then train a model to reconstruct the original tokens. While they produce good results when transferred to downstream NLP tasks, they generally require large amounts of compute to be effective. As an alternative, we propose a more sample-efficient pre-training task called replaced token detection. Instead of masking the input, our approach corrupts it by replacing some tokens with plausible alternatives sampled from a small generator network. Then, instead of training a model that predicts the original identities of the corrupted tokens, we train a discriminative model that predicts whether each token in the corrupted input was replaced by a generator sample or not. Thorough experiments demonstrate this new pre-training task is more efficient than MLM because the task is defined over all input tokens rather than just the small subset that was masked out. As a result, the contextual representations learned by our approach substantially outperform the ones learned by BERT given the same model size, data, and compute. The gains are particularly strong for small models; for example, we train a model on one GPU for 4 days that outperforms GPT (trained using 30x more compute) on the GLUE natural language understanding benchmark. Our approach also works well at scale, where it performs comparably to RoBERTa and XLNet while using less than 1/4 of their compute and outperforms them when using the same amount of compute.