Leace: Perfect linear concept erasure in closed form

N Belrose, D Schneider-Joseph… - Advances in …, 2024 - proceedings.neurips.cc
Abstract Concept erasure aims to remove specified features from a representation. It can
improve fairness (eg preventing a classifier from using gender or race) and interpretability …

Overview and challenges of machine translation for contextually appropriate translations

P Naveen, P Trojovský - Iscience, 2024 - cell.com
Machine translation facilitates cross-linguistic communication by converting text between
languages. However, producing contextually accurate translations remains a challenge …

From rule-based models to deep learning transformers architectures for natural language processing and sign language translation systems: survey, taxonomy and …

N Shahin, L Ismail - Artificial Intelligence Review, 2024 - Springer
With the growing Deaf and Hard of Hearing population worldwide and the persistent
shortage of certified sign language interpreters, there is a pressing need for an efficient …

Understanding transformer memorization recall through idioms

A Haviv, I Cohen, J Gidron, R Schuster… - arxiv preprint arxiv …, 2022 - arxiv.org
To produce accurate predictions, language models (LMs) must balance between
generalization and memorization. Yet, little is known about the mechanism by which …

Translate meanings, not just words: Idiomkb's role in optimizing idiomatic translation with language models

S Li, J Chen, S Yuan, X Wu, H Yang, S Tao… - Proceedings of the AAAI …, 2024 - ojs.aaai.org
To translate well, machine translation (MT) systems and general-purposed language models
(LMs) need a deep understanding of both source and target languages and cultures …

Do gpts produce less literal translations?

V Raunak, A Menezes, M Post, HH Awadalla - arxiv preprint arxiv …, 2023 - arxiv.org
Large Language Models (LLMs) such as GPT-3 have emerged as general-purpose
language models capable of addressing many natural language generation or …

ACES: Translation accuracy challenge sets for evaluating machine translation metrics

C Amrhein, N Moghe, L Guillou - arxiv preprint arxiv:2210.15615, 2022 - arxiv.org
As machine translation (MT) metrics improve their correlation with human judgement every
year, it is crucial to understand the limitations of such metrics at the segment level …

MIND your language: A multilingual dataset for cross-lingual news recommendation

A Iana, G Glavaš, H Paulheim - … of the 47th International ACM SIGIR …, 2024 - dl.acm.org
Digital news platforms use news recommenders as the main instrument to cater to the
individual information needs of readers. Despite an increasingly language-diverse online …

Semantics of Multiword Expressions in Transformer-Based Models: A Survey

F Miletić, SS Walde - … of the Association for Computational Linguistics, 2024 - direct.mit.edu
Multiword expressions (MWEs) are composed of multiple words and exhibit variable
degrees of compositionality. As such, their meanings are notoriously difficult to model, and it …

Neural Generative Models and the Parallel Architecture of Language: A Critical Review and Outlook

G Rambelli, E Chersoni, D Testa… - Topics in cognitive …, 2024 - Wiley Online Library
According to the parallel architecture, syntactic and semantic information processing are two
separate streams that interact selectively during language comprehension. While …