Natural language is hierarchically structured: smaller units (eg, phrases) are nested within
larger units (eg, clauses). When a larger constituent ends, all of the smaller constituents that …

Abstract Aspect-based Sentiment Analysis (ABSA) is a subclass of sentiment analysis, which
aims to identify the sentiment polarity such as positive, negative, or neutral for specific …

By introducing a small set of additional parameters, a probe learns to solve specific linguistic
tasks (eg, dependency parsing) in a supervised manner using feature representations (eg …

Recurrent neural network grammars (RNNG) are generative models of language which
jointly model syntax and surface structure by incrementally generating a syntax tree and …

Despite their empirical success, neural networks still have difficulty capturing compositional
aspects of natural language. This work proposes a simple data augmentation approach to …

Code summarization (aka comment generation) provides a high-level natural language
description of the function performed by code, which can benefit the software maintenance …

Abstract Binary Balanced Tree Recursive Neural Networks (BBT-RvNNs) enforce sequence
composition according to a preset balanced binary tree structure. Thus, their non-linear …

We present the Visually Grounded Neural Syntax Learner (VG-NSL), an approach for
learning syntactic representations and structures without any explicit supervision. The model …

Data augmentation is an effective approach to tackle over-fitting. Many previous works have
proposed different data augmentations strategies for NLP, such as noise injection, word …

Abstract Syntax parse trees are a method of representing sentence structure and are often
used to provide models with syntax information and enhance downstream task performance …