• Publications
  • Influence
Probing Pretrained Language Models for Lexical Semantics
TLDR
A systematic empirical analysis across six typologically diverse languages and five different lexical tasks indicates patterns and best practices that hold universally, but also point to prominent variations across languages and tasks.
XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning
TLDR
This work introduces Cross-lingual Choice of Plausible Alternatives (XCOPA), a typologically diverse multilingual dataset for causal commonsense reasoning in 11 languages, revealing that current methods based on multilingual pretraining and zero-shot fine-tuning transfer suffer from the curse of multilinguality and fall short of performance in monolingual settings by a large margin.
Adversarial Propagation and Zero-Shot Cross-Lingual Transfer of Word Vector Specialization
TLDR
This work proposes a novel approach to specializing the full distributional vocabulary by combining a standard L2-distance loss with a adversarial loss, and proposes a cross-lingual transfer method for zero-shot specialization which successfully specializes a full target distributional space without any lexical knowledge in the target language and without any bilingual data.
Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction
TLDR
The main technical contribution of this work is a novel method for injecting subword-level information into semantic word vectors, integrated into the neural language modeling training, to facilitate word-level prediction.
Visually Grounded Reasoning across Languages and Cultures
TLDR
A new protocol is devised to construct an ImageNet-style hierarchy representative of more languages and cultures, and a multilingual dataset for Multicultural Reasoning over Vision and Language (MaRVL) is created by eliciting statements from native speaker annotators about pairs of images.
Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing
TLDR
It is shown that to date, the use of information in existing typological databases has resulted in consistent but modest improvements in system performance, due to both intrinsic limitations of databases and under-employment of the typological features included in them.
Event-Related Features in Feedforward Neural Networks Contribute to Identifying Causal Relations in Discourse
TLDR
A Feedforward Neural Network is implemented with a novel set of features based on the position of event mentions and the semantics of events and participants that outperforms strong baselines on two datasets annotated with different schemes and containing examples in two languages.
Isomorphic Transfer of Syntactic Structures in Cross-Lingual NLP
TLDR
This paper introduces a source language selection procedure that facilitates effective cross-lingual parser transfer, and proposes a typologically driven method for syntactic tree processing which reduces anisomorphism, demonstrating the importance of syntactic structure compatibility for boosting cross-lingsual transfer in NLP.
Multi-SimLex: A Large-Scale Evaluation of Multilingual and Crosslingual Lexical Semantic Similarity
TLDR
The public release of Multi-SimLex data sets, their creation protocol, strong baseline results, and in-depth analyses can be helpful in guiding future developments in multilingual lexical semantics and representation learning are made available via a Web site that will encourage community effort in further expansion ofMulti-Simlex.
Emergent Communication Pretraining for Few-Shot Machine Translation
TLDR
It is shown that grounding communication on images—as a crude approximation of real-world environments—inductively biases the model towards learning natural languages, and the potential of emergent communication pretraining for both natural language processing tasks in resource-poor settings and extrinsic evaluation of artificial languages is revealed.
...
...