Search Results for author:
Found 10 papers, 8 papers with code
Query-dominant User Interest Network for Large-Scale Search Ranking
The overall historical behaviors are various but noisy while search behaviors are always sparse.
The Re-Label Method For Data-Centric Machine Learning
In industry deep learning application, our manually labeled data has a certain number of noisy data.
Ranked #1 on
Label Error Detection
on TREC-6
A Comprehensive Comparison of Pre-training Language Models
Recently, the development of pre-trained language models has brought natural language processing (NLP) tasks to the new state-of-the-art.
Learning From Human Correction
We do the experiment on our own text classification dataset, which is manually labeled, because we re-label the noisy data in our dataset for our industry application.
Predictions For Pre-training Language Models
First, We use the model fine-tuned on manually labeled dataset to predict pseudo labels for the user-generated unlabeled data.
Content Enhanced BERT-based Text-to-SQL Generation
We present a simple methods to leverage the table content for the BERT-based model to solve the text-to-SQL problem.
Ranked #1 on
Code Generation
on WikiSQL
Revisiting Semantic Representation and Tree Search for Similar Question Retrieval
We do the experiments on the semantic textual similarity dataset, Quora Question Pairs, and process the dataset for sentence ranking.
Using Database Rule for Weak Supervised Text-to-SQL Generation
We present a simple way to do the task of text-to-SQL problem with weak supervision.
Table2answer: Read the database and answer without SQL
Semantic parsing is the task of mapping natural language to logic form.
Bidirectional Attention for SQL Generation
Generating structural query language (SQL) queries from natural language is a long-standing open problem.
Ranked #8 on
Code Generation
on WikiSQL
