• Publications
  • Influence
Multi-Hop Knowledge Graph Reasoning with Reward Shaping
TLDR
We propose two modeling advances to address both issues: (1) we reduce the impact of false negative supervision by adopting a pretrained one-hop embedding model to estimate the reward of unobserved facts; (2) we counter the sensitivity to spurious paths of on-policy RL by forcing the agent to explore a diverse set of paths using randomly generated edge masks. Expand
  • 83
  • 18
  • PDF
Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions
TLDR
We propose an editing-based encoder-decoder model to address the problem of context-dependent cross-domain text-to-SQL generation. Expand
  • 34
  • 12
  • PDF
Compositional Learning of Embeddings for Relation Paths in Knowledge Base and Text
TLDR
We propose the first exact dynamic programming algorithm which enables efficient incorporation of all relation paths of bounded length, while modeling both relation types and intermediate nodes in the compositional path representations. Expand
  • 110
  • 8
  • PDF
SParC: Cross-Domain Semantic Parsing in Context
TLDR
We present SParC, a dataset for cross-domainSemanticParsing inContext that consists of 4,298 coherent question sequences (12k+ individual questions annotated with SQL queries). Expand
  • 31
  • 8
  • PDF
Program Synthesis from Natural Language Using Recurrent Neural Networks
O‰entimes, a programmer may have diculty implementing a desired operation. Even when the programmer can describe her goal in English, it can be dicult to translate into code. Existing resources,Expand
  • 37
  • 6
  • PDF
CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases
TLDR
We present CoSQL, a corpus for building cross-domain, general-purpose database (DB) querying dialogue systems. Expand
  • 33
  • 6
  • PDF
Multi-Label Learning with Posterior Regularization
In many multi-label learning problems, especially as the number of labels grow, it is challenging to gather completely annotated data. This work presents a new approach for multi-label learning fromExpand
  • 9
  • 5
  • PDF
GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing
TLDR
We present GraPPa, an effective pre-training approach for table semantic parsing that learns a compositional inductive bias in the joint representations of textual and tabular data. Expand
  • 7
  • 3
  • PDF
NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System
TLDR
We present new data and semantic parsing methods for the problem of mapping English sentences to Bash commands, along with baseline methods to establish performance levels on this task. Expand
  • 45
  • 2
  • PDF
Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation
TLDR
We propose a novel debiasing technique that preserves the distributional semantics of the pre-trained word embeddings while reducing gender bias to a significantly larger degree than prior approaches. Expand
  • 8
  • 1
  • PDF