Despite the progress we have recorded in the last few years in multiling...
Weakly supervised learning is a popular approach for training machine
le...
Product Question Answering (PQA) systems are key in e-commerce applicati...
Owing to the lack of corpora for low-resource languages, current works o...
Dense retrieval (DR) approaches based on powerful pre-trained language m...
Training deep neural networks (DNNs) with weak supervision has been a ho...
Legal judgment prediction (LJP) applies Natural Language Processing (NLP...
In conversational QA, models have to leverage information in previous tu...
Text generation aims to produce human-like natural language output for
d...
Reasoning is central to human intelligence. However, fallacious argument...
Recent research has achieved impressive progress in the session-based
re...
Given the fact of a case, Legal Judgment Prediction (LJP) involves a ser...
Code summarization aims to generate brief natural language descriptions ...
Documents as short as a single sentence may inadvertently reveal sensiti...
We propose a shared task on training instance selection for few-shot neu...
Large-scale pretrained language models have led to dramatic improvements...
For many new application domains for data-to-text generation, the main
o...
As news and social media exhibit an increasing amount of manipulative
po...
We present a lightweight annotation tool, the Data AnnotatoR Tool (DART)...
Given an image, generating its natural language description (i.e., capti...
Neural network-based sequence-to-sequence (seq2seq) models strongly suff...
The neural attention model has achieved great success in data-to-text
ge...
West African Pidgin English is a language that is significantly spoken i...
Many text generation tasks naturally contain two steps: content selectio...
Recent research has made impressive progress in single-turn dialogue
mod...
Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular...
Variational encoder-decoders (VEDs) have shown promising results in dial...
We develop a high-quality multi-turn dialog dataset, DailyDialog, which ...
Deep latent variable models have been shown to facilitate the response
g...