Related papers: Zero-Shot Cross-Lingual Dependency Parsing through…

We target the task of cross-lingual Machine Reading Comprehension (MRC) in the direct zero-shot setting, by incorporating syntactic features from Universal Dependencies (UD), and the key features we use are the syntactic relations within…

Cross-lingual semantic textual similarity systems estimate the degree of the meaning similarity between two sentences, each in a different language. State-of-the-art algorithms usually employ machine translation and combine vast amount of…

An effective method for cross-lingual transfer is to fine-tune a bilingual or multilingual model on a supervised dataset in one language and evaluating it on another language in a zero-shot manner. Translating examples at training time or…

Pretrained Language Models (PLMs) learn rich cross-lingual knowledge and can be finetuned to perform well on diverse tasks such as translation and multilingual word sense disambiguation (WSD). However, they often struggle at disambiguating…

Many data sets (e.g., reviews, forums, news, etc.) exist parallelly in multiple languages. They all cover the same content, but the linguistic differences make it impossible to use traditional, bag-of-word-based topic models. Models have to…

This paper deals with cross-lingual sentiment analysis in Czech, English and French languages. We perform zero-shot cross-lingual classification using five linear transformations combined with LSTM and CNN based classifiers. We compare the…

There has been increasing interest in building multilingual foundation models for NLP and speech research. This paper examines how to expand the speech translation capability of these models with restricted data. Whisper, a speech…

Despite the surging demands for multilingual task-oriented dialog systems (e.g., Alexa, Google Home), there has been less research done in multilingual or cross-lingual scenarios. Hence, we propose a zero-shot adaptation of task-oriented…

There has been a recent spike in interest in multi-modal Language and Vision problems. On the language side, most of these models primarily focus on English since most multi-modal datasets are monolingual. We try to bridge this gap with a…

We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus (e.g. a few hundred sentence pairs). Our method obtains word embeddings via an LSTM encoder-decoder model that…

Cross-lingual embeddings aim to represent words in multiple languages in a shared vector space by capturing semantic similarities across languages. They are a crucial component for scaling tasks to multiple languages by transferring…

Recent advances in cross-lingual word embeddings have primarily relied on mapping-based methods, which project pretrained word embeddings from different languages into a shared space through a linear transformation. However, these…

The many-to-many multilingual neural machine translation can be regarded as the process of integrating semantic features from the source sentences and linguistic features from the target sentences. To enhance zero-shot translation, models…

While neural networks have shown impressive performance on large datasets, applying these models to tasks where little data is available remains a challenging problem. In this paper we propose to use feature transfer in a zero-shot…

Cross-lingual word embeddings are becoming increasingly important in multilingual NLP. Recently, it has been shown that these embeddings can be effectively learned by aligning two disjoint monolingual vector spaces through linear…

This paper presents a new technique for creating monolingual and cross-lingual meta-embeddings. Our method integrates multiple word embeddings created from complementary techniques, textual sources, knowledge bases and languages. Existing…

Multilingual pre-trained contextual embedding models (Devlin et al., 2019) have achieved impressive performance on zero-shot cross-lingual transfer tasks. Finding the most effective fine-tuning strategy to fine-tune these models on…

Supervised learning methods can solve the given problem in the presence of a large set of labeled data. However, the acquisition of a dataset covering all the target classes typically requires manual labeling which is expensive and…

Recent approaches have shown that training deep neural networks directly on large-scale image-text pair collections enables zero-shot transfer on various recognition tasks. One central issue is how this can be generalized to object…

Crosslingual word embeddings represent lexical items from different languages in the same vector space, enabling transfer of NLP tools. However, previous attempts had expensive resource requirements, difficulty incorporating monolingual…