Despite the remarkable ability of large language models (LMs) to compreh...
Language models (LMs) compute the probability of a text by sequentially
...
Natural-language-to-code models learn to generate a code snippet given a...
While there has been a recent burgeoning of applications at the intersec...
Large language models (LMs) of code have recently shown tremendous promi...
Retrieval-based language models (R-LM) model the probability of natural
...
Structural locality is a ubiquitous feature of real-world datasets, wher...
While most neural generative models generate outputs in a single pass, t...
A great part of software development involves conceptualizing or
communi...
Procedural knowledge, which we define as concrete information about the
...
Document categorization, which aims to assign a topic label to each docu...
Open-domain code generation aims to generate code in a general-purpose
p...
Recent work has presented intriguing results examining the knowledge
con...
GitHub has become an important platform for code sharing and scientific
...
Blind people frequently encounter inaccessible dynamic touchscreens in t...
Diversity is a crucial criterion in many ranking and mining tasks. In th...
Extracting entities and their relations from text is an important task f...
Extracting entities and their relations from text is an important task f...
LocatedNear relation describes two typically co-located objects, which i...
Automatic relation extraction (RE) for types of interest is of great
imp...
Linguistic sequence labeling is a general modeling approach that encompa...