Deep learning has become the dominant approach in addressing various tasks in Natural
Language Processing (NLP). Although text inputs are typically represented as a sequence …

This work aims to tackle the challenging heterogeneous graph encoding problem in the text-
to-SQL task. Previous methods are typically node-centric and merely utilize different weight …

Chinese short text matching is a fundamental task in natural language processing. Existing
approaches usually take Chinese characters or words as input tokens. They have two …

Topic-based communities have gradually become a considerable medium for netizens to
disseminate and acquire knowledge. These communities consist of entities (actual objects …

Given a database schema, Text-to-SQL aims to translate a natural language question into
the corresponding SQL query. Under the setup of cross-domain, traditional semantic parsing …

Recent efforts adopt interaction-based models to construct the interaction of words between
sentences, which aim to predict whether two sentences are semantically equivalent or not in …

Short texts (STs) present in a variety of scenarios, including query, dialog, and entity names.
Most of the exciting studies in neural machine translation (NMT) are focused on tackling …

In recent years, text matching has gained increasing research focus and shown great
improvements. However, due to the long-distance dependency and polysemy, existing text …

Pre-trained text encoders have drawn sustaining attention in natural language processing
(NLP) and shown their capability in obtaining promising results in different tasks. Recent …

Chinese pre-trained language models usually process text as a sequence of characters,
while ignoring more coarse granularity, eg, words. In this work, we propose a novel pre …