Papers with English Wiktionary

4 papers
Injecting Wiktionary to improve token-level contextual representations using contrastive learning (2024.eacl-short)

Copied to clipboard

Challenge: lexical semantics tasks require contextual word embeddings that are not blind to context, despite the fact that vectors of the same meaning are too different.
Approach: They propose to fine-tune pre-trained language models by using automatically self-augmented examples to target contextual word embeddings.
Outcome: The proposed method achieves significant improvements on the original WiC test set and in two new tests.
Wiktextract: Wiktionary as Machine-Readable Structured Data (2022.lrec-1)

Copied to clipboard

Challenge: Unlike previous Wiktionary extractions, the new extractor, Wiktextract, fully interprets and expands templates and Lua modules in Wiktionaries.
Approach: They propose a machine-readable structured version of Wiktionary that interprets and expands templates and Lua modules.
Outcome: The extracted data is multilingual and includes lemmas, inflected forms, translations, etymology, usage examples, pronunciations, and various morphological, syntactic, semantic, topical, and dialectal annotations.
NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning (2026.acl-long)

Copied to clipboard

Challenge: Neologism-aware machine translation aims to translate source sentences containing neologismes into target languages.
Approach: They propose an agentic framework for neologism-aware machine translation equipped with a Wiktionary-based search toolkit.
Outcome: The proposed framework is based on a Wiktionary-based search toolkit and a dedicated dataset for neologism-aware machine translation.
Wikinflection Corpus: A (Better) Multilingual, Morpheme-Annotated Inflectional Corpus (2020.lrec-1)

Copied to clipboard

Challenge: Inflectional corpora with annotated morpheme boundaries are scarce in the NLP community . a generated, multilingual inflectional lexicon with morphological features is not as good as UniMorph's .
Approach: They evaluate a multilingual inflectional corpus with morpheme boundaries from the English Wiktionary and the UniMorph project's inflection corpus.
Outcome: The generated Wikinflection corpus is not as good as UniMorph's, but extracts significant amount of words from the intersection of the two corpora.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations