Large-scale language models (LLMs) has shown remarkable capability in va...
Model ensemble has been in widespread use for Grammatical Error Correcti...
Although existing neural network approaches have achieved great success ...
Chinese Grammatical Error Correction (CGEC) aims to generate a correct
s...
For readability assessment, traditional methods mainly employ machine
le...
Today the pre-trained language models achieve great success for question...
Automatic medical question summarization can significantly help the syst...
Most of the Chinese pre-trained models adopt characters as basic units f...
Generating high quality question-answer pairs is a hard but meaningful t...
Adversarial training is a method for enhancing neural networks to improv...
Question generation (QG) is to generate natural and grammatical question...
Knowledge facts are typically represented by relational triples, while w...
Question Generation (QG) is an essential component of the automatic
inte...
We focus on the task of procedural text understanding, which aims to tra...
The answer-agnostic question generation is a significant and challenging...
Advertising is an important revenue source for many companies. However, ...
Target-Based Sentiment Analysis aims to detect the opinion aspects (aspe...
In reading comprehension, generating sentence-level distractors is a
sig...
In this paper we focus on the problem of dialog act (DA) labelling. This...
Question generation is a challenging task which aims to ask a question b...
This paper explores the task of answer-aware questions generation. Based...
Automatic article commenting is helpful in encouraging user engagement a...
How to generate human like response is one of the most challenging tasks...
In order to learn universal sentence representations, previous methods f...
Huge numbers of new words emerge every day, leading to a great need for
...
Question retrieval is a crucial subtask for community question answering...
Using low dimensional vector space to represent words has been very effe...
In this paper, we focus on the problem of answer triggering ad-dressed b...