The increasing versatility of language models LMs has given rise to a ne...
Transfer learning - i.e., further fine-tuning a pre-trained model on a
d...
We propose a novel methodology (namely, MuLER) that transforms any
refer...
Transformer-based language models (LMs) create hidden representations of...
Research on neural networks has largely focused on understanding a singl...
We present the call for papers for the BabyLM Challenge: Sample-efficien...
Pretraining has been shown to scale well with compute, data size and dat...
Question answering models commonly have access to two sources of "knowle...
Previous studies observed that finetuned models may be better base model...
Applying Reinforcement learning (RL) following maximum likelihood estima...
Text classification can be useful in many real-world scenarios, saving a...
We present the task of PreQuEL, Pre-(Quality-Estimation) Learning. A Pre...
In Grammatical Error Correction, systems are evaluated by the number of
...
Pretrained models are the standard starting point for training. This app...
In real-world scenarios, a text classification task often begins with a ...
The integration of syntactic structures into Transformer machine transla...
To gain insight into the role neurons play, we study the activation patt...
The learning trajectories of linguistic phenomena provide insight into t...
We present ComSum, a data set of 7 million commit messages for text
summ...
In this research paper, I will elaborate on a method to evaluate machine...
Neural knowledge-grounded generative models for dialogue often produce
c...
Probing neural models for the ability to perform downstream tasks using ...
Data exploration is an important step of every data science and machine
...
SERRANT is a system and code for automatic classification of English
gra...
While a number of works showed gains from incorporating source-side symb...
We present a method for classifying syntactic errors in learner language...
Approaching new data can be quite deterrent; you do not know how your
ca...
One of the main tasks in argument mining is the retrieval of argumentati...
We show that the state of the art Transformer Machine Translation(MT) mo...
We show that the state-of-the-art Transformer MT model is not biased tow...
With the advancement in argument detection, we suggest to pay more atten...
Reinforcement learning (RL) is frequently used to increase performance i...
The field of Grammatical Error Correction (GEC) has produced various sys...
The non-indexed parts of the Internet (the Darknet) have become a haven ...
We present the SemEval 2019 shared task on UCCA parsing in English, Germ...
We announce a shared task on UCCA parsing in English, German and French,...
The prevalent use of too few references for evaluating text-to-text
gene...
Metric validation in Grammatical Error Correction (GEC) is currently don...
Exploration is a fundamental aspect of Reinforcement Learning, typically...
We propose USim, a semantic measure for Grammatical Error Correction
(G...