We present KGConv, a large, conversational corpus of 71k conversations w...
To date, most work on text simplification has focused on sentence-level
...
A key feature of neural models is that they can produce semantic vector
...
In human conversations, ellipsis and coreference are commonly occurring
...
Generating factual, long-form text such as Wikipedia articles raises thr...
Generating text from structured data is challenging because it requires
...
Various machine learning tasks can benefit from access to external
infor...
Recent graph-to-text models generate text from graph-based data using ei...
Work on summarization has explored both reinforcement learning (RL)
opti...
Query-based open-domain NLP tasks require information synthesis from lon...
Generating text from graph-based data, such as Abstract Meaning
Represen...
Seq2seq models based on Recurrent Neural Networks (RNNs) have recently
r...
We propose a new sentence simplification task (Split-and-Rephrase) where...
Recently, several data-sets associating data to text have been created t...
We present a novel approach to sentence simplification which departs fro...