Before deploying a language model (LM) within a given domain, it is impo...
We propose a novel methodology (namely, MuLER) that transforms any
refer...
Machine translation (MT) requires a wide range of linguistic capabilitie...
We present a large, multilingual study into how vision constrains lingui...
For applications that require processing large amounts of text at infere...
Text Simplification (TS) is the task of converting a text into a form th...
Question answering models commonly have access to two sources of "knowle...
The task of topical segmentation is well studied, but previous work has
...
Applying Reinforcement learning (RL) following maximum likelihood estima...
We present the task of PreQuEL, Pre-(Quality-Estimation) Learning. A Pre...
Recent advances in self-supervised modeling of text and images open new
...
In Grammatical Error Correction, systems are evaluated by the number of
...
Huge language models (LMs) have ushered in a new era for AI, serving as ...
The integration of syntactic structures into Transformer machine transla...
We explore the link between the extent to which syntactic relations are
...
To gain insight into the role neurons play, we study the activation patt...
We present a method for exploring regions around individual points in a
...
While corpora of child speech and child-directed speech (CDS) have enabl...
The learning trajectories of linguistic phenomena provide insight into t...
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 ...
SERRANT is a system and code for automatic classification of English
gra...
While a number of works showed gains from incorporating source-side symb...
This is the annotation manual for Universal Conceptual Cognitive Annotat...
Building robust natural language understanding systems will require a cl...
We present a method for classifying syntactic errors in learner language...
Masking tokens uniformly at random constitutes a common flaw in the
pret...
The patterns in which the syntax of different languages converges and
di...
While natural language understanding (NLU) is advancing rapidly, today's...
Universal Conceptual Cognitive Annotation (UCCA; Abend and Rappoport, 20...
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...
Reinforcement learning (RL) is frequently used to increase performance i...
We propose a coreference annotation scheme as a layer on top of the Univ...
The non-indexed parts of the Internet (the Darknet) have become a haven ...
Syntactic analysis plays an important role in semantic parsing, but the
...
We present the SemEval 2019 shared task on UCCA parsing in English, Germ...
BLEU is widely considered to be an informative metric for text-to-text
g...
Sentence splitting is a major simplification operator. Here we present a...
Current measures for evaluating text simplification systems focus on
eva...
This paper presents our experiments with applying TUPA to the CoNLL 2018...
We announce a shared task on UCCA parsing in English, German and French,...
Semantic relations are often signaled with prepositional or possessive
m...
The ability to consolidate information of different types is at the core...
Metric validation in Grammatical Error Correction (GEC) is currently don...
We propose USim, a semantic measure for Grammatical Error Correction
(G...
This document describes an inventory of 50 semantic labels designed to
c...
We present the first parser for UCCA, a cross-linguistically applicable
...
Human evaluation of machine translation normally uses sentence-level mea...