Semantics

Text to SQL Baseline

A simple LSTM-based model that uses templates and slot-filing to map questions to SQL queries.

Text to SQL datasets

A collection of datasets containing questions in English paired with SQL queries for a provided database. Our version homogenises the style of the SQL and corrects errors in previous versions of the data.

Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations (Wieting et al., 2017)

With enough training data, the best vector representation of a sentence is to concatenate an average over word vectors and an average over character trigram vectors.