The increasing versatility of language models LMs has given rise to a ne...
The field of text generation suffers from a severe shortage of labeled d...
Applying language models to natural language processing tasks typically
...
Research on neural networks has largely focused on understanding a singl...
Attribute-controlled text rewriting, also known as text style-transfer, ...
Pretraining has been shown to scale well with compute, data size and dat...
We present nBIIG, a neural Business Intelligence (BI) Insights Generatio...
Previous studies observed that finetuned models may be better base model...
Recent advances in large pretrained language models have increased atten...
Getting the most out of limited resources allows advances in natural lan...
Text classification can be useful in many real-world scenarios, saving a...
Public trust in medical information is crucial for successful applicatio...
The COVID-19 pandemic has made a huge global impact and cost millions of...
Generating natural language statements to convey information from tabula...
Targeted Sentiment Analysis (TSA) is a central task for generating insig...
Pretrained models are the standard starting point for training. This app...
Many organizations require their customer-care agents to manually summar...
Paraphrase generation has been widely used in various downstream tasks. ...
In real-world scenarios, a text classification task often begins with a ...
In recent years, pretrained language models have revolutionized the NLP
...
We describe the 2021 Key Point Analysis (KPA-2021) shared task on key po...
Project Debater was revealed in 2019 as the first AI system that can deb...
Previous work on review summarization focused on measuring the sentiment...
Sentiment analysis research has shifted over the years from the analysis...
Approaching new data can be quite deterrent; you do not know how your
ca...
The growing interest in argument mining and computational argumentation
...
Argument generation is a challenging task whose research is timely
consi...
When summarizing a collection of views, arguments or opinions on some to...
One of the most impressive human endeavors of the past two decades is th...
Generating a concise summary from a large collection of arguments on a g...
An educated and informed consumption of media content has become a chall...
Identifying the quality of free-text arguments has become an important t...
One of the main tasks in argument mining is the retrieval of argumentati...
We explore the task of automatic assessment of argument quality. To that...
In Natural Language Understanding, the task of response generation is us...
Competitive debaters often find themselves facing a challenging task -- ...
With the growing interest in social applications of Natural Language
Pro...
Wikification of large corpora is beneficial for various NLP applications...
Engaging in a live debate requires, among other things, the ability to
e...
With the advancement in argument detection, we suggest to pay more atten...
The field of Grammatical Error Correction (GEC) has produced various sys...
Nearest neighbors in word embedding models are commonly observed to be
s...
We introduce a weakly supervised approach for inferring the property of
...
We describe a large, high-quality benchmark for the evaluation of Mentio...
This paper describes an audio and textual dataset of debating speeches, ...
The Information bottleneck method is an unsupervised non-parametric data...
We address the practical problems of estimating the information relation...