• Publications
  • Influence
Compositional Semantic Parsing on Semi-Structured Tables
TLDR
This paper proposes a logical-form driven parsing algorithm guided by strong typing constraints and shows that it obtains significant improvements over natural baselines and is made publicly available. Expand
REALM: Retrieval-Augmented Language Model Pre-Training
TLDR
The effectiveness of Retrieval-Augmented Language Model pre-training (REALM) is demonstrated by fine-tuning on the challenging task of Open-domain Question Answering (Open-QA) and is found to outperform all previous methods by a significant margin, while also providing qualitative benefits such as interpretability and modularity. Expand
From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood
TLDR
The goal is to learn a semantic parser that maps natural language utterances into executable programs when only indirect supervision is available, and a new algorithm is presented that guards against spurious programs by combining the systematic search traditionally employed in MML with the randomized exploration of RL. Expand
Simpler Context-Dependent Logical Forms via Model Projections
TLDR
This work considers the task of learning a context-dependent mapping from utterances to denotations, and performs successive projections of the full model onto simpler models that operate over equivalence classes of logical forms. Expand
Bootstrapped Self Training for Knowledge Base Population
TLDR
This work proposes bootstrapped selftraining to capture the benefits of both systems: the precision of patterns and the generalizability of trained models and shows that training on the output of patterns drastically improves performance over the patterns. Expand
Query understanding enhanced by hierarchical parsing structures
TLDR
This work extracts a set of syntactic structural features and semantic dependency features from query parse trees to enhance inference model learning and shows that augmenting sequence labeling models with linguistic knowledge can improve query understanding performance in various domains. Expand
Reinforcement Learning on Web Interfaces Using Workflow-Guided Exploration
TLDR
This work proposes to constrain exploration using demonstrations to train a novel neural policy designed to handle the semi-structured nature of websites, and shows that workflow-guided exploration improves sample efficiency over behavioral cloning by more than 100x. Expand
Macro Grammars and Holistic Triggering for Efficient Semantic Parsing
TLDR
A new online learning algorithm that searches faster as training progresses is proposed, using macro grammars to cache the abstract patterns of useful logical forms found thus far, and holistic triggering to efficiently retrieve the most relevant patterns based on sentence similarity. Expand
Asgard: A portable architecture for multilingual dialogue systems
TLDR
This work investigates the portability issue from the language understanding perspective and presents the Asgard architecture, a CRF-based (Conditional Random Fields) and crowd-sourcing-centered framework, which supports expert-free development of multilingual dialogue systems and seamless deployment to mobile platforms. Expand
...
1
2
3
...