Reasoning presents a significant and challenging issue for Large Languag...
Graphic design is an effective language for visual communication. Using
...
Creating layouts is a fundamental step in graphic design. In this work, ...
Content Warning: This work contains examples that potentially implicate
...
With the popularity of automatic code generation tools, such as Copilot,...
Hybrid Question-Answering (HQA), which targets reasoning over tables and...
In-Context learning is the paradigm that adapts large language models to...
Compositional generalization–understanding unseen combinations of seen
p...
Automated debugging techniques have the potential to reduce developer ef...
The task of repository-level code completion is to continue writing the
...
Creating graphic layouts is a fundamental step in graphic designs. In th...
Abstraction is a desirable capability for deep learning models, which me...
In this paper, we study the problem of knowledge-intensive text-to-SQL, ...
Text-to-SQL semantic parsing is an important NLP task, which greatly
fac...
The robustness of Text-to-SQL parsers against adversarial perturbations ...
The task of generating code from a natural language description, or NL2C...
The task of text-to-SQL is to convert a natural language question to its...
With the rapid development of pre-training techniques, a number of langu...
To satisfy various user needs, different subtasks of graphic layout
gene...
The task of generating code solutions for a given programming problem ca...
Code generation is a longstanding challenge, aiming to generate a code
s...
Large language models such as GPT-3 and PaLM have shown remarkable
perfo...
Building unified conversational agents has been a long-standing goal of ...
We present LogiGAN, an unsupervised adversarial pre-training framework f...
Due to high data demands of current methods, attention to zero-shot
cros...
With the development of pre-trained language models, remarkable success ...
Existing text-to-SQL semantic parsers are typically designed for particu...
Recently the prompt-tuning paradigm has attracted significant attention....
Reasoning over natural language is a long-standing goal for the research...
Language-based environment manipulation requires agents to manipulate th...
We study the problem of quantitative facts extraction for text with
perc...
Recent years pretrained language models (PLMs) hit a success on several
...
Tables are often created with hierarchies, but existing works on table
r...
Recent years pre-trained language models hit a success on modeling natur...
Neural sequence models exhibit limited compositional generalization abil...
Neural semantic parsers usually fail to parse long and complex utterance...
Human intelligence exhibits compositional generalization (i.e., the capa...
In Natural Language Interfaces to Databases systems, the text-to-SQL
tec...
We formalize human language understanding as a structured prediction tas...
Recent years the task of incomplete utterance rewriting has raised a lar...
Infographic is a data visualization technique which combines graphic and...
Prior works in cross-lingual named entity recognition (NER) with no/litt...
Compositional generalization is a basic but essential intellective capab...
To better tackle the named entity recognition (NER) problem on languages...
Despite the continuing efforts to improve the engagingness and consisten...
Recently semantic parsing in context has received a considerable attenti...
This paper presents a novel approach to translating natural language
que...
This paper presents a novel approach to translating natural language
que...
Context-dependent semantic parsing has proven to be an important yet
cha...
Recommendation models mainly deal with categorical variables, such as
us...