• Publications
  • Influence
On Generating Characteristic-rich Question Sets for QA Evaluation
TLDR
This work is the first to generate questions with explicitly specified characteristics for QA evaluation, and it is shown that datasets constructed in this way enable finegrained analyses of QA systems. Expand
KGPT: Knowledge-Grounded Pre-Training for Data-to-Text Generation
TLDR
A knowledge-grounded pre-training (KGPT) is proposed, which consists of two parts, 1) a general knowledge-Grounded generation model to generate knowledge-enriched text and 2) a pre- training paradigm on a massive knowledge- grounded text corpus crawled from the web. Expand
DialSQL: Dialogue Based Structured Query Generation
TLDR
DialSQL is a dialogue-based structured query generation framework that leverages human intelligence to boost the performance of existing algorithms via user interaction and is capable of identifying potential errors in a generated SQL query and asking users for validation via simple multi-choice questions. Expand
Table Cell Search for Question Answering
TLDR
This work proposes a novel table cell search framework that is comparable to state-of-the-art QA systems based on knowledge bases (KBs), while on Bing queries, it outperforms other systems with a 56.7% relative gain. Expand
Building Natural Language Interfaces to Web APIs
TLDR
This work proposes the first end-to-end framework to build an NL2API for a given web API, and applies it to real-world APIs, and shows that it can collect high-quality training data at a low cost, and build NL2APIs with good performance from scratch. Expand
XL-NBT: A Cross-lingual Neural Belief Tracking Framework
TLDR
A cross-lingual state tracking framework is built that assumes that there exists a source language with dialog belief tracking annotations while the target languages have no annotated dialog data of any form, and discusses two types of common parallel resources: bilingual corpus and bilingual dictionary. Expand
Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases
TLDR
A new large-scale, high-quality dataset with 64,331 questions, GrailQA, is constructed and a novel BERT-based KBQA model is proposed, which enables the key role of pre-trained contextual embeddings like BERT in the generalization ofKBQA to be demonstrated for the first time. Expand
Cross-domain Semantic Parsing via Paraphrasing
TLDR
By converting logical forms into canonical utterances in natural language, semantic parsing is reduced to paraphrasing, and an attentive sequence-to-sequence paraphrase model is developed that is general and flexible to adapt to different domains. Expand
Improving Semantic Parsing via Answer Type Inference
TLDR
The possibility of inferring the answer type before solving a factoid question and leveraging the type information to improve semantic parsing is shown and it is observed that if the authors convert a question into a statement form, the LSTM model achieves better accuracy. Expand
Task-Oriented Dialogue as Dataflow Synthesis
TLDR
An approach to task-oriented dialogue in which dialogue state is represented as a dataflow graph, which enables the expression and manipulation of complex user intents, and explicit metacomputation makes these intents easier for learned models to predict. Expand
...
1
2
3
4
...