Search Results for author:
Found 12 papers, 10 papers with code
WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agents
In the realm of web agent research, achieving both generalization and accuracy remains a challenging problem.
BYOC: Personalized Few-Shot Classification with Co-Authored Class Descriptions
As a result, it is not possible for end-users to build classifiers for themselves.
Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent
We present Chirpy Cardinal, an open-domain social chatbot.
ThingTalk: An Extensible, Executable Representation Language for Task-Oriented Dialogues
Task-oriented conversational agents rely on semantic parsers to translate natural language to formal representations.
Contextual Semantic Parsing for Multilingual Task-Oriented Dialogues
On RiSAWOZ, CrossWOZ, CrossWOZ-EN, and MultiWOZ-ZH datasets we improve the state of the art by 11%, 17%, 20%, and 0. 3% in joint goal accuracy.
Grounding Open-Domain Instructions to Automate Web Support Tasks
RUSS consists of two models: First, a BERT-LSTM with pointers parses instructions to ThingTalk, a domain-specific language we design for grounding natural language on the web.
Localizing Open-Ontology QA Semantic Parsers in a Day Using Machine Translation
We propose Semantic Parser Localizer (SPL), a toolkit that leverages Neural Machine Translation (NMT) systems to localize a semantic parser for a new language.
AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data
To demonstrate the generality of AutoQA, we also apply it to the Overnight dataset.
A Few-Shot Semantic Parser for Wizard-of-Oz Dialogues with the Precise ThingTalk Representation
Previous attempts to build effective semantic parsers for Wizard-of-Oz (WOZ) conversations suffer from the difficulty in acquiring a high-quality, manually annotated training set.
Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking
We show that data augmentation through synthesized data can improve the accuracy of zero-shot learning for both the TRADE model and the BERT-based SUMBT model on the MultiWOZ 2. 1 dataset.
Schema2QA: High-Quality and Low-Cost Q&A Agents for the Structured Web
The key concept is to cover the space of possible compound queries on the database with a large number of in-domain questions synthesized with the help of a corpus of generic query templates.
Genie: A Generator of Natural Language Semantic Parsers for Virtual Assistant Commands
We advocate formalizing the capability of virtual assistants with a Virtual Assistant Programming Language (VAPL) and using a neural semantic parser to translate natural language into VAPL code.
