When Are Tree Structures Necessary for Deep Learning of Representations?
This work addresses the problem of when syntactic parse trees are necessary for deep learning in NLP, providing insights for researchers and practitioners, but it is incremental as it builds on existing model comparisons.
The paper benchmarks recursive neural models against recurrent models on four NLP tasks to determine when tree structures are beneficial, finding they help mainly on tasks requiring long-distance headword association, such as semantic relation extraction on long sequences, and proposes a method for recurrent models to match performance by processing clause-like units separately.
Recursive neural models, which use syntactic parse trees to recursively generate representations bottom-up, are a popular architecture. But there have not been rigorous evaluations showing for exactly which tasks this syntax-based method is appropriate. In this paper we benchmark {\bf recursive} neural models against sequential {\bf recurrent} neural models (simple recurrent and LSTM models), enforcing apples-to-apples comparison as much as possible. We investigate 4 tasks: (1) sentiment classification at the sentence level and phrase level; (2) matching questions to answer-phrases; (3) discourse parsing; (4) semantic relation extraction (e.g., {\em component-whole} between nouns). Our goal is to understand better when, and why, recursive models can outperform simpler models. We find that recursive models help mainly on tasks (like semantic relation extraction) that require associating headwords across a long distance, particularly on very long sequences. We then introduce a method for allowing recurrent models to achieve similar performance: breaking long sentences into clause-like units at punctuation and processing them separately before combining. Our results thus help understand the limitations of both classes of models, and suggest directions for improving recurrent models.