The striking ability of unsupervised word translation has been demonstra...
Interactive semantic parsing based on natural language (NL) feedback, wh...
The advent of large language models trained on code (code LLMs) has led ...
Sampling diverse programs from a code language model and reranking with ...
Generative models of code, pretrained on large corpora of programs, have...
Mined bitexts can contain imperfect translations that yield unreliable
t...
Existing work in language grounding typically study single environments....
Bilingual lexicons map words in one language to their translations in
an...
We propose Grounded Adaptation for Zero-shot Executable Semantic Parsing...
Our goal is to create a convenient natural language interface for perfor...
Data noising is an effective technique for regularizing neural network
m...
We introduce a new language learning setting relevant to building adapti...
Mixture modeling is a general technique for making any simple model more...
We propose a relaxation-based approximate inference algorithm that sampl...