This paper focuses on paraphrase generation, which is a widely studied natural language
generation task in NLP. With the development of neural models, paraphrase generation …

In this paper, we first explain why human-like dialogue understanding is so difficult for
artificial intelligence (AI). We discuss various methods for testing the understanding …

Large Language Models (LLMs) have demonstrated impressive capabilities in creative tasks
such as storytelling and E-mail generation. However, as LLMs are primarily trained on final …

Paraphrase generation has been widely used in various downstream tasks. Most tasks
benefit mainly from high quality paraphrases, namely those that are semantically similar to …

In this paper we revisit automatic metrics for paraphrase evaluation and obtain two findings
that disobey conventional wisdom:(1) Reference-free metrics achieve better performance …

Text revision refers to a family of natural language generation tasks, where the source and
target sequences share moderate resemblance in surface form but differentiate in attributes …

Task-oriented dialog systems enable users to accomplish tasks using natural language.
State-of-the-art systems respond to users in the same way regardless of their personalities …

Slot filling is identifying contiguous spans of words in an utterance that correspond to certain
parameters (ie, slots) of a user request/query. Slot filling is one of the most important …

Identifying user intents from natural language utterances is a crucial step in conversational
systems that has been extensively studied as a supervised classification problem. However …

We present MCPG: a simple and effectiveapproach for controllable unsupervised
paraphrase generation, which is also flexible toadapt to specific domains without extra …