The goal of compositional generalization benchmarks is to evaluate how well models
generalize to new complex linguistic expressions. Existing benchmarks often focus on …

Recombining known primitive concepts into larger novel combinations is a quintessentially
human cognitive capability. Whether large neural models in NLP can acquire this ability …

This paper is an attempt to bridge the gap between deep learning and grammatical
inference. Indeed, it provides an algorithm to extract a (stochastic) formal language from any …

Recent work in NLP shows that LSTM language models capture hierarchical structure in
language data. In contrast to existing work, we consider the\textit {learning} process that …

Natural language processing techniques contribute more and more in analyzing legal
documents recently, which supports the implementation of laws and rules using computers …

Interpretability methods for neural networks are difficult to evaluate because we do not
understand the black-box models typically used to test them. This paper proposes a …

The importance of cues in language learning has long been established and it is clear that
cues are an essential part of both first language (L1) and second/additional language (L2/A) …

Long Short-Term Memory recurrent neural network (LSTM) is widely used and known to
capture informative long-term syntactic dependencies. However, how such information are …

Image captioning is a challenging task that requires a computer vision system to generate
natural language descriptions for images. The aim is to build a model that can comprehend …

Recombining known primitive concepts into larger novel combinations is a quintessentially
human cognitive capability. Whether large neural models in NLP can acquire this ability …