4 citations · 6 across the 8 of their papers we have counts for
9 papers
Perspectives on Cross-Lingual Consistency in LLMs for Medical Questions
Minh Duc Bui, Mario Sanz-Guerrero, Abteen Ebrahimi +4
Should multilingual LLMs answer medical questions consistently across input languages, or adapt responses to cultural cues? Existing multilingual medical benchmarks usually assume…
Model-Based Ranking of Source Languages for Zero-Shot Cross-Lingual Transfer
Abteen Ebrahimi, Adam Wiemerslage, Katharina von der Wense
We present NN-Rank, an algorithm for ranking source languages for cross-lingual transfer, which leverages hidden representations from multilingual models and unlabeled target-langu…
Academic Article Recommendation Using Multiple Perspectives
Kenneth Church, Omar Alonso, Peter Vickers +3
We argue that Content-based filtering (CBF) and Graph-based methods (GB) complement one another in Academic Search recommendations. The scientific literature can be viewed as a con…
Since the Scientific Literature Is Multilingual, Our Models Should Be Too
Abteen Ebrahimi, Kenneth Church
English has long been assumed the of scientific research, and this notion is reflected in the natural language processing (NLP) research involving scientif…
Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models
Abteen Ebrahimi, Arya D. McCarthy, Arturo Oncevay +5
Large multilingual models have inspired a new class of word alignment methods, which work well for the model's pretraining languages. However, the languages most in need of automat…
How to Adapt Your Pretrained Multilingual Model to 1600 Languages
Abteen Ebrahimi, Katharina Kann
Pretrained multilingual models (PMMs) enable zero-shot learning via cross-lingual transfer, performing best for languages seen during pretraining. While methods exist to improve pe…
AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
Abteen Ebrahimi, Manuel Mager, Arturo Oncevay +14
Pretrained multilingual models are able to perform cross-lingual transfer in a zero-shot setting, even for languages unseen during pretraining. However, prior work evaluating perfo…
Athena: Constructing Dialogues Dynamically with Discourse Constraints
Vrindavan Harrison, Juraj Juraska, Wen Cui +11
This report describes Athena, a dialogue system for spoken conversation on popular topics and current events. We develop a flexible topic-agnostic approach to dialogue management t…
Curate and Generate: A Corpus and Method for Joint Control of Semantics and Style in Neural NLG
Shereen Oraby, Vrindavan Harrison, Abteen Ebrahimi +1
Neural natural language generation (NNLG) from structured meaning representations has become increasingly popular in recent years. While we have seen progress with generating synta…