Predicting Word Similarity in Context with Referential Translation Machines

Ergun Biçici
7/7/2024
cs.CLcs.AI

No confident code implementation found for this paper.

Abstract

We identify the similarity between two words in English by casting the task as machine translation performance prediction (MTPP) between the words given the context and the distance between their similarities. We use referential translation machines (RTMs), which allows a common representation for training and test sets and stacked machine learning models. RTMs can achieve the top results in Graded Word Similarity in Context (GWSC) task.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Identifying Intensity of the Structure and Content in Tweets and the Discriminative Power of Attributes in Context with Referential Translation Machines

88% match2024

Textual Similarity as a Key Metric in Machine Translation Quality Estimation

82% match2024

In-Context Example Selection via Similarity Search Improves Low-Resource Machine Translation

81% match1 repo92024

Similarity-Distance-Magnitude Language Models

81% match2025

Going Beyond Word Matching: Syntax Improves In-context Example Selection for Machine Translation

80% match2024

Predicting Anchored Text from Translation Memories for Machine Translation Using Deep Learning Methods

80% match2024

Cite this paper

@article{biici2024predicting,
  title  = {Predicting Word Similarity in Context with Referential Translation Machines},
  author = {Ergun Biçici},
  year   = {2024},
  eprint = {2407.06230},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2407.06230v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.06230.svg)](https://codeofpaper.com/paper/2407.06230)

Discussion