Paraphrase generation is an important problem in NLP, especially in question answering,
information retrieval, information extraction, conversation systems, to name a few. In this …

In this paper, we propose a novel neural approach for paraphrase generation. Conventional
para-phrase generation methods either leverage hand-written rules and thesauri-based …

Previous studies on lexical substitution tend to obtain substitute candidates by finding the
target word's synonyms from lexical resources (eg, WordNet) and then rank the candidates …

Given a sentence (eg,“I like mangoes”) and a constraint (eg, sentiment flip), the goal of
controlled text generation is to produce a sentence that adapts the input sentence to meet …

Paraphrase generation aims to improve the clarity of a sentence by using different wording
that convey similar meaning. For better quality of generated paraphrases, we propose a …

Although powerful pretrained language models generate high-quality output text, they bring
new concerns about the potential misuse of such models for malicious purposes. Natural …

Paraphrase generation is a fundamental and long-standing task in natural language
processing. In this paper, we concentrate on two contributions to the task:(1) we propose …

Since the inception of the S enseval series there has been a great deal of debate in the word
sense disambiguation (WSD) community on what the right sense distinctions are for …

Paraphrasing plays an important role in various natural language processing (NLP) tasks,
such as question answering, information retrieval and sentence simplification. Recently …

Voice-based virtual assistants are becoming increasingly popular. Such systems provide
frameworks to developers for building custom apps. End-users can interact with such apps …