Search Results for author: Tong Guo

Found 10 papers, 6 papers with code

The Re-Label Method For Data-Centric Machine Learning

no code implementations9 Feb 2023 Tong Guo

In industry deep learning application, our manually labeled data has a certain number of noisy data.

Click-Through Rate Prediction object-detection +1

A Comprehensive Comparison of Pre-training Language Models

2 code implementations22 Jun 2021 Tong Guo

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

no code implementations30 Jan 2021 Tong Guo

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.

General Classification text-classification +1

Predictions For Pre-training Language Models

no code implementations18 Nov 2020 Tong Guo

First, We use the model fine-tuned on manually labeled dataset to predict pseudo labels for the user-generated unlabeled data.

Language Modelling

Content Enhanced BERT-based Text-to-SQL Generation

4 code implementations16 Oct 2019 Tong Guo, Huilin Gao

We present a simple methods to leverage the table content for the BERT-based model to solve the text-to-SQL problem.

Code Generation Semantic Parsing +2

Revisiting Semantic Representation and Tree Search for Similar Question Retrieval

1 code implementation22 Aug 2019 Tong Guo, Huilin Gao

We do the experiments on the semantic textual similarity dataset, Quora Question Pairs, and process the dataset for sentence ranking.

Information Retrieval Question Answering +5

Using Database Rule for Weak Supervised Text-to-SQL Generation

2 code implementations1 Jul 2019 Tong Guo, Huilin Gao

We present a simple way to do the task of text-to-SQL problem with weak supervision.

Text-To-SQL

Bidirectional Attention for SQL Generation

2 code implementations30 Dec 2017 Tong Guo, Huilin Gao

Generating structural query language (SQL) queries from natural language is a long-standing open problem.

Reading Comprehension

Cannot find the paper you are looking for? You can Submit a new open access paper.