• Publications
  • Influence
Neural Motifs: Scene Graph Parsing with Global Context
TLDR
This work analyzes the role of motifs: regularly appearing substructures in scene graphs and introduces Stacked Motif Networks, a new architecture designed to capture higher order motifs in scene graph graphs that improves on the previous state-of-the-art by an average of 3.6% relative improvement across evaluation settings. Expand
A Discriminative Graph-Based Parser for the Abstract Meaning Representation
TLDR
The first approach to parse sentences into meaning representation, a semantic formalism for which a grow- ing set of annotated examples is available, is introduced, providing a strong baseline for improvement. Expand
Toward Abstractive Summarization Using Semantic Representations
TLDR
This work focuses on the graph-tograph transformation that reduces the source semantic graph into a summary graph, making use of an existing AMR parser and assuming the eventual availability of an AMR-totext generator. Expand
Deep Multitask Learning for Semantic Dependency Parsing
We present a deep neural architecture that parses sentences into three semantic dependency graph formalisms. By using efficient, nearly arc-factored inference and a bidirectional-LSTM composed with aExpand
Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
TLDR
A new, efficient frame-semantic parser that labels semantic arguments to FrameNet predicates, built using an extension to the segmental RNN that emphasizes recall, achieves competitive performance without any calls to a syntactic parser. Expand
Syntactic Scaffolds for Semantic Structures
TLDR
This work introduces the syntactic scaffold, an approach to incorporating syntactic information into semantic tasks through a multitask objective, and improves over strong baselines on PropBank semantics, frame semantics, and coreference resolution. Expand
Frame-Semantic Role Labeling with Heterogeneous Annotations
TLDR
This work augments an existing model with features derived from Frame net and PropBank and with partially annotated exemplars from FrameNet with the aim of identifying and labeling the semantic arguments of a predicate that evokes a FrameNet frame. Expand
Learning Joint Semantic Parsers from Disjoint Data
TLDR
A new approach to learning a semantic parser from multiple datasets, even when the target semantic formalisms are drastically different and the underlying corpora do not overlap is presented, by treating annotations for unobserved formalisms as latent structured variables. Expand
Backpropagating through Structured Argmax using a SPIGOT
TLDR
It is shown that training with SPIGOT leads to a larger improvement on the downstream task than a modularly-trained pipeline, the straight-through estimator, and structured attention, reaching a new state of the art on semantic dependency parsing. Expand
Constrained Language Models Yield Few-Shot Semantic Parsers
TLDR
With a small amount of data and very little code to convert into English-like representations, this work provides a blueprint for rapidly bootstrapping semantic parsers and demonstrates good performance on multiple tasks. Expand
...
1
2
...