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 …

Lexical substitution (LS) aims at finding appropriate substitutes for a target word in a
sentence. Recently, LS methods based on pretrained language models have made …

Existing lexical substitution (LS) benchmarks were collected by asking human annotators to
think of substitutes from memory, resulting in benchmarks with limited coverage and …

Lexical substitution, which aims to generate substitutes for a target word given a context, is
an important natural language processing task useful in many applications. Due to the …

We propose a new unsupervised method for lexical substitution using pre-trained language
models. Compared to previous approaches that use the generative capability of language …

Lexical substitution aims to generate a list of equivalent substitutions (ie, synonyms) to a
sentence's target word or phrase while preserving the sentence's meaning to improve …

Linking named entities occurring in text to their corresponding entity in a Knowledge Base
(KB) is challenging, especially when dealing with historical texts. In this work, we introduce …

This paper presents Text2AMR2FRED, a text-to-Knowledge Graph (KG) pipeline that
transforms multilingual natural language text into logically sound KGs. It enables at-scale …

Lexical Substitution (LS) replaces the target word or phrase with its synonym alternatives
that are equivalent in meaning. Despite the richness of the Arabic language, Arabic LS …

Causal language models such as the GPT series have achieved significant success across
various domains. However, their application to the lexical substitution task (LST) remains …