SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.18570 · ACL · 2024

Analyzing Semantic Change through Lexical Replacements

Francesco Periti, Haim Dubossarsky, Nina Tahmasebi, Pierluigi Cassotti

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
ChangeIsKey/asc-lr — 1 of 1
FunctionStatusWhere it lives
SentenceDataset Ran ChangeIsKey/asc-lr/generate_mask_replacements.py
pointer only (licence: NONE) · get_code("e47f81dfb7c35a10")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Modern language models are capable of contextualizing words based on their surrounding context. However, this capability is often compromised due to semantic change that leads to words being used in new, unexpected contexts not encountered during pre-training. In this paper, we model semantic change by studying the effect of unexpected contexts introduced by lexical replacements. We propose a replacement schema where a target word is substituted with lexical replacements of varying relatedness, thus simulating different kinds of semantic change. Furthermore, we leverage the replacement schema as a basis for a novel interpretable model for semantic change. We are also the first to evaluate the use of LLaMa for semantic change detection.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.18570")
get_code_for_paper("2404.18570")
have("2404.18570")

Connect an agent — have() is free.