• Publications
  • Influence
How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions
TLDR
We thoroughly evaluate both supervised and unsupervised CLE models on a large number of language pairs in the BLI task and three downstream tasks, providing new insights concerning the ability of cutting-edge CLE models to support cross-lingual NLP. Expand
  • 90
  • 12
  • PDF
Unsupervised Cross-Lingual Information Retrieval Using Monolingual Data Only
TLDR
We propose a fully unsupervised framework for ad-hoc cross-lingual information retrieval (CLIR) which requires no bilingual data at all. Expand
  • 36
  • 5
  • PDF
Probing Pretrained Language Models for Lexical Semantics
TLDR
The success of large pretrained language models (LMs) such as BERT and RoBERTa has sparked interest in probing their representations, in order to unveil what types of knowledge they implicitly capture. Expand
  • 7
  • 1
  • PDF
Evaluating Resource-Lean Cross-Lingual Embedding Models in Unsupervised Retrieval
TLDR
We provide a comprehensive comparative evaluation of projection-based CLE models for both sentence-level and document-level cross-lingual Information Retrieval (CLIR). Expand
  • 9
Formal [3+3] cyclocondensations of 1,3-bis(silyloxy)-1,3-butadienes with 1-chloro-1,1-difluoro-4,4-dimethoxybut-3-en-2-one and 1,1-difluoro-4,4-dimethoxybut-3-en-2-one. Regioselective synthesis of
Abstract The TiCl4-mediated [3+3] cyclocondensation of 1,3-bis(silyloxy)-1,3-butadienes with 1-chloro-1,1-difluoro-4,4-dimethoxybut-3-en-2-one or 1,1-difluoro-4,4-dimethoxybut-3-en-2-one affordedExpand
  • 7
Towards Instance-Level Parser Selection for Cross-Lingual Transfer of Dependency Parsers
TLDR
We propose and argue for a novel cross-lingual transfer paradigm: instance-level parser selection (ILPS), and present a proof-of-concept study focused on instance- level selection in the framework of delexicalized parser transfer. Expand
Trec-CAR 2018: A Simple Unsupervised Semantic Query Expansion Model
TLDR
We present a simple and unsupervised Semantic Query Expansion model (SemQueryExp) for Complex Answer Retrieval (CAR). Expand
Process for the electropolishing of gold or platinum-containing surfaces
The invention describes a method for electropolishing of workpieces, such as jewelry, containing noble metal surfaces. The workpieces are smoothed in an aqueous electrolyte solution with a component,Expand
Evaluating Multilingual Text Encoders for Unsupervised Cross-Lingual Retrieval
TLDR
Pretrained multilingual text encoders based on neural Transformer architectures, such as multilingual BERT (mBERT) and XLM, have achieved strong performance on a myriad of supervised language understanding tasks. Expand