Publications (15)
Frame-Semantic Parsing with Softmax-Margin Segmental RNNs and a Syntactic Scaffold
Swabha Swayamdipta, Sam Thomson, Chris Dyer +1
We present a new, efficient frame-semantic parser that labels semantic arguments to FrameNet predicates. Built using an extension to the segmental RNN that emphasizes recall, our b…
Neural Motifs: Scene Graph Parsing with Global Context
Rowan Zellers, Mark Yatskar, Sam Thomson +1
We investigate the problem of producing structured graph representations of visual scenes. Our work analyzes the role of motifs: regularly appearing substructures in scene graphs.…
Syntactic Scaffolds for Semantic Structures
Swabha Swayamdipta, Sam Thomson, Kenton Lee +3
We introduce the syntactic scaffold, an approach to incorporating syntactic information into semantic tasks. Syntactic scaffolds avoid expensive syntactic processing at runtime, on…
Task-Oriented Dialogue as Dataflow Synthesis
Semantic Machines, Jacob Andreas, John Bufe +43
We describe an approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph. A dialogue agent maps each user utterance to a program that extends th…
When More Data Hurts: A Troubling Quirk in Developing Broad-Coverage Natural Language Understanding Systems
Elias Stengel-Eskin, Emmanouil Antonios Platanios, Adam Pauls +5
In natural language understanding (NLU) production systems, users' evolving needs necessitate the addition of new features over time, indexed by new symbols added to the meaning re…
Learning Joint Semantic Parsers from Disjoint Data
Hao Peng, Sam Thomson, Swabha Swayamdipta +1
We present a new approach to learning semantic parsers from multiple datasets, even when the target semantic formalisms are drastically different, and the underlying corpora do not…
Backpropagating through Structured Argmax using a SPIGOT
Hao Peng, Sam Thomson, Noah A. Smith
We introduce the structured projection of intermediate gradients optimization technique (SPIGOT), a new method for backpropagating through neural networks that include hard-decisio…
Deep Multitask Learning for Semantic Dependency Parsing
Hao Peng, Sam Thomson, Noah A. Smith
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-L…
Rational Recurrences
Hao Peng, Roy Schwartz, Sam Thomson +1
Despite the tremendous empirical success of neural models in natural language processing, many of them lack the strong intuitions that accompany classical machine learning approach…
Toward Abstractive Summarization Using Semantic Representations
Fei Liu, Jeffrey Flanigan, Sam Thomson +2
We present a novel abstractive summarization framework that draws on the recent development of a treebank for the Abstract Meaning Representation (AMR). In this framework, the sour…
MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools
Nishant Subramani, Jason Eisner, Justin Svegliato +3
Tool-using agents that act in the world need to be both useful and safe. Well-calibrated model confidences can be used to weigh the risk versus reward of potential actions, but pri…
Toward Interactive Dictation
Belinda Z. Li, Jason Eisner, Adam Pauls +1
Voice dictation is an increasingly important text input modality. Existing systems that allow both dictation and editing-by-voice restrict their command language to flat templates…
SoPa: Bridging CNNs, RNNs, and Weighted Finite-State Machines
Roy Schwartz, Sam Thomson, Noah A. Smith
Recurrent and convolutional neural networks comprise two distinct families of models that have proven to be useful for encoding natural language utterances. In this paper we presen…
BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing
Subhro Roy, Sam Thomson, Tongfei Chen +4
Recent work has shown that generation from a prompted or fine-tuned language model can perform well at semantic parsing when the output is constrained to be a valid semantic repres…
Constrained Language Models Yield Few-Shot Semantic Parsers
Richard Shin, Christopher H. Lin, Sam Thomson +7
We explore the use of large pretrained language models as few-shot semantic parsers. The goal in semantic parsing is to generate a structured meaning representation given a natural…