Search Results for author:
Found 29 papers, 13 papers with code
Aligning Actions Across Recipe Graphs
Recipe texts are an idiosyncratic form of instructional language that pose unique challenges for automatic understanding.
Predicting Coreference in Abstract Meaning Representations
This work addresses coreference resolution in Abstract Meaning Representation (AMR) graphs, a popular formalism for semantic parsing.
MC-Saar-Instruct: a Platform for Minecraft Instruction Giving Agents
We present a comprehensive platform to run human-computer experiments where an agent instructs a human in Minecraft, a 3D blocksworld environment.
Compositional generalization with a broad-coverage semantic parser
We show how the AM parser, a compositional semantic parser (Groschwitz et al., 2018) can solve compositional generalization on the COGS dataset.
Simple and effective data augmentation for compositional generalization
Compositional generalization, the ability to predict complex meanings from training on simpler sentences, poses challenges for powerful pretrained seq2seq models.
AutoPlanBench: Automatically generating benchmarks for LLM planners from PDDL
LLMs are being increasingly used for planning-style tasks, but their capabilities for planning and reasoning are poorly understood.
Predicting generalization performance with correctness discriminators
We present a novel model that establishes upper and lower bounds on the accuracy, without requiring gold labels for the unseen data.
ADaPT: As-Needed Decomposition and Planning with Language Models
Large Language Models (LLMs) are increasingly being used for interactive decision-making tasks requiring planning and adapting to the environment.
SLOG: A Structural Generalization Benchmark for Semantic Parsing
The goal of compositional generalization benchmarks is to evaluate how well models generalize to new complex linguistic expressions.
Closing the Curious Case of Neural Text Degeneration
We provide a theoretical explanation for the effectiveness of the truncation sampling by proving that truncation methods that discard tokens below some probability threshold (the most common type of truncation) can guarantee that all sampled tokens have nonzero true probability.
Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulation
Strong inductive biases enable learning from little data and help generalization outside of the training distribution.
Compositional Generalization without Trees using Multiset Tagging and Latent Permutations
Our model outperforms pretrained seq2seq models and prior work on realistic semantic parsing tasks that require generalization to longer examples.
What's the Meaning of Superhuman Performance in Today's NLU?
In the last five years, there has been a significant focus in Natural Language Processing (NLP) on developing larger Pretrained Language Models (PLMs) and introducing benchmarks such as SuperGLUE and SQuAD to measure their abilities in language understanding, reasoning, and reading comprehension.
We're Afraid Language Models Aren't Modeling Ambiguity
We find that the task remains extremely challenging, including for GPT-4, whose generated disambiguations are considered correct only 32% of the time in human evaluation, compared to 90% for disambiguations in our dataset.
Structural generalization is hard for sequence-to-sequence models
Sequence-to-sequence (seq2seq) models have been successful across many NLP tasks, including ones that require predicting linguistic structure.
Compositional Generalisation with Structured Reordering and Fertility Layers
Seq2seq models have been shown to struggle with compositional generalisation, i. e. generalising to new and potentially more complex structures than seen during training.
Compositional Generalization Requires Compositional Parsers
A rapidly growing body of research on compositional generalization investigates the ability of a semantic parser to dynamically recombine linguistic elements seen in training into unseen sequences.
Script Parsing with Hierarchical Sequence Modelling
A crucial step for the exploitation of script knowledge is script parsing, the task of tagging a text with the events and participants from a certain activity.
Learning compositional structures for semantic graph parsing
AM dependency parsing is a method for neural semantic graph parsing that exploits the principle of compositionality.
Story Generation with Rich Details
Automatically generated stories need to be not only coherent, but also interesting.
Generating Instructions at Different Levels of Abstraction
When generating technical instructions, it is often convenient to describe complex objects in the world at different levels of abstraction.
Fast semantic parsing with well-typedness guarantees
AM dependency parsing is a linguistically principled method for neural semantic parsing with high accuracy across multiple graphbanks.
Normalizing Compositional Structures Across Graphbanks
The emergence of a variety of graph-based meaning representations (MRs) has sparked an important conversation about how to adequately represent semantic structure.
Compositional Semantic Parsing Across Graphbanks
Most semantic parsers that map sentences to graph-based meaning representations are hand-designed for specific graphbanks.
Semantic expressive capacity with bounded memory
We investigate the capacity of mechanisms for compositional semantic parsing to describe relations between sentences and semantic representations.
Generalized chart constraints for efficient PCFG and TAG parsing
Chart constraints, which specify at which string positions a constituent may begin or end, have been shown to speed up chart parsers for PCFGs.
Discovering User Groups for Natural Language Generation
We present a model which predicts how individual users of a dialog system understand and produce utterances based on user groups.
AMR Dependency Parsing with a Typed Semantic Algebra
We present a semantic parser for Abstract Meaning Representations which learns to parse strings into tree representations of the compositional structure of an AMR graph.
