373 citations · 705 across the 32 of their papers we have counts for
38 papers
Strengthening Target-Language Features: SAE-Based Steering for Multilingual Inference
Hongsheng Wang, Philipp Koehn
Multilingual large language models exhibit substantial performance differences across languages, while existing adaptation methods often require parameter updates and considerable…
Multilingual Pixel Representations for Translation and Effective Cross-lingual Transfer
Elizabeth Salesky, Neha Verma, Philipp Koehn +1
We introduce and demonstrate how to effectively train multilingual machine translation models with pixel representations. We experiment with two different data settings with a vari…
Condensing Multilingual Knowledge with Lightweight Language-Specific Modules
Haoran Xu, Weiting Tan, Shuyue Stella Li +4
Incorporating language-specific (LS) modules is a proven method to boost performance in multilingual machine translation. This approach bears similarity to Mixture-of-Experts (MoE)…
Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport
Kelly Marchisio, Ali Saad-Eldin, Kevin Duh +2
Bilingual lexicons form a critical component of various natural language processing applications, including unsupervised and semisupervised machine translation and crosslingual inf…
IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces
Kelly Marchisio, Neha Verma, Kevin Duh +1
The ability to extract high-quality translation dictionaries from monolingual word embedding spaces depends critically on the geometric similarity of the spaces -- their degree of…
Multilingual Representation Distillation with Contrastive Learning
Weiting Tan, Kevin Heffernan, Holger Schwenk +1
Multilingual sentence representations from large models encode semantic information from two or more languages and can be used for different cross-lingual information retrieval and…