Mounica Maddela

TL;DR: This paper proposed a neural CRF alignment model which not only leverages the sequential nature of sentences in parallel documents, but also utilizes a neural sentence pair model to capture semantic similarity for text simplification.

TL;DR: This work creates a human-rated word-complexity lexicon of 15,000 English words and proposes a novel neural readability ranking model with a Gaussian-based feature vectorization layer that utilizes these human ratings to measure the complexity of any given word or phrase.

TL;DR: A novel hybrid approach is proposed that leverages linguistically-motivated rules for splitting and deletion, and couples them with a neural paraphrasing model to produce varied rewriting styles and establishes a new state-of-the-art for the task.

TL;DR: GEM as discussed by the authors is a living benchmark for natural language generation (NLG), its Evaluation and Metrics, which provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested.

TL;DR: A new named entity recognition (NER) corpus for the computer programming domain is introduced, consisting of 15,372 sentences annotated with 20 fine-grained entity types, and the SoftNER model is presented, which incorporates a context-independent code token classifier with corpus-level features to improve the BERT-based tagging model.