Abstract Knowledge graph reasoning is the fundamental component to support machine
learning applications such as information extraction, information retrieval, and …

We have long envisioned that one day computers will understand natural language and
anticipate what we need, when and where we need it, and proactively complete tasks on our …

We present a neural approach called IRNet for complex and cross-domain Text-to-SQL.
IRNet aims to address two challenges: 1) the mismatch between intents expressed in natural …

Sequence-to-sequence models excel at handling natural language variation, but have been
shown to struggle with out-of-distribution compositional generalization. This has motivated …

Semantic parsing aims at mapping natural language to machine interpretable meaning
representations. Traditional approaches rely on high-quality lexicons, manually-built …

This paper presents a new technique for automatically synthesizing SQL queries from
natural language (NL). At the core of our technique is a new NL-based program synthesis …

Many language generation tasks require the production of text conditioned on both
structured and unstructured inputs. We present a novel neural network architecture which …

Suppose we want to build a system that answers a natural language question by
representing its semantics as a logical forxm and computing the answer given a structured …

Abstract Abstract Meaning Representation (AMR) is a semantic formalism for which a
growing set of annotated examples is available. We introduce the first approach to parse …

Generic unstructured neural networks have been shown to struggle on out-of-distribution
compositional generalization. Compositional data augmentation via example recombination …