• Publications
  • Influence
DyNet: The Dynamic Neural Network Toolkit
TLDR
We describe DyNet, a toolkit for implementing neural network models based on dynamic declaration of network structure. Expand
TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
TLDR
In this paper we present TaBERT, a pretrained LM that jointly learns representations for NL sentences and (semi-)structured tables. Expand
Learning to Mine Aligned Code and Natural Language Pairs from Stack Overflow
TLDR
We propose a novel method to mine high-quality aligned data from SO using two sets of features: hand-crafted features considering the structure of the extracted snippets, and correspondence features obtained by training a probabilistic model to capture the correlation between NL and code using neural networks. Expand
TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation
TLDR
We present TRANX, a transition-based neural semantic parser that maps natural language (NL) utterances into formal meaning representations (MRs) based on the abstract syntax description language for the target MR. Expand
StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing
TLDR
We introduce StructVAE, a variational auto-encoding model for semi-supervised semantic parsing, which learns both from limited amounts of parallel data, and readily-available unlabeled NL utterances. Expand
A Tree-based Decoder for Neural Machine Translation
TLDR
We propose an NMT model that can naturally generate the topology of an arbitrary tree structure on the target side, and (2) experiment with various target tree structures. Expand
Learning to Represent Edits
TLDR
We introduce the problem of learning distributed representations of edits. Expand
High-Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
TLDR
We investigate the relationship between the frequency spectrum of image data and the generalization behavior of convolutional neural networks (CNN). Expand
Answering Questions with Complex Semantic Constraints on Open Knowledge Bases
TLDR
We present TAQA, a novel KB-QA system that is based on an nOKB and illustrate via experiments how it can answer complex questions with rich semantic constraints. Expand
Neural Enquirer: Learning to Query Tables
TLDR
We proposed Neural Enquirer as a neural network architecture to execute a SQLlike query on a knowledge-base (KB) for answers. Expand
...
1
2
3
4
5
...