Related papers: Teaching a New Dog Old Tricks: Resurrecting Multil…

Most rumour detection models for social media are designed for one specific language (mostly English). There are over 40 languages on Twitter and most languages lack annotated resources to build rumour detection models. In this paper we…

Automatically classifying the relation between sentences in a discourse is a challenging task, in particular when there is no overt expression of the relation. It becomes even more challenging by the fact that annotated training data exists…

Current multimodal machine translation (MMT) systems rely on fully supervised data (i.e models are trained on sentences with their translations and accompanying images). However, this type of data is costly to collect, limiting the…

Scaling up visual category recognition to large numbers of classes remains challenging. A promising research direction is zero-shot learning, which does not require any training data to recognize new classes, but rather relies on some form…

Large language models trained primarily in a monolingual setting have demonstrated their ability to generalize to machine translation using zero- and few-shot examples with in-context learning. However, even though zero-shot translations…

Generalization and reliability of multilingual translation often highly depend on the amount of available parallel data for each language pair of interest. In this paper, we focus on zero-shot generalization---a challenging setup that tests…

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…

In this paper, we present a Bayesian multilingual document model for learning language-independent document embeddings. The model is an extension of BaySMM [Kesiraju et al 2020] to the multilingual scenario. It learns to represent the…

Large pre-trained language models have brought remarkable progress in NLP. Pre-training and Fine-tuning have given state-of-art performance across tasks in text processing. Data Augmentation techniques have also helped build state-of-art…

Zero-shot translation, translating between language pairs on which a Neural Machine Translation (NMT) system has never been trained, is an emergent property when training the system in multilingual settings. However, naive training for…

A popular approach to creating a zero-shot cross-language retrieval model is to substitute a monolingual pretrained language model in the retrieval model with a multilingual pretrained language model such as Multilingual BERT. This…

We study the application of large language models to zero-shot and few-shot classification of tabular data. We prompt the large language model with a serialization of the tabular data to a natural-language string, together with a short…

Multilingual Neural Machine Translation (MNMT) has aroused widespread interest due to its efficiency. An exciting advantage of MNMT models is that they could also translate between unsupervised (zero-shot) language directions. Language tag…

Large Language Models (LLMs) have shown impressive zero-shot performance across a variety of Natural Language Processing tasks, including document re-ranking. However, their effectiveness degrades on unseen tasks and domains, largely due to…

Large language models (LLMs) have shown impressive zero-shot capabilities in various document reranking tasks. Despite their successful implementations, there is still a gap in existing literature on their effectiveness in low-resource…

Multimodal Video Search by Examples (MVSE) investigates using video clips as the query term for information retrieval, rather than the more traditional text query. This enables far richer search modalities such as images, speaker, content,…

Zero-shot intent classification is a vital and challenging task in dialogue systems, which aims to deal with numerous fast-emerging unacquainted intents without annotated training data. To obtain more satisfactory performance, the crucial…

Cross-language entity linking grounds mentions in multiple languages to a single-language knowledge base. We propose a neural ranking architecture for this task that uses multilingual BERT representations of the mention and the context in a…

Recent approaches to multilingual open-domain question answering (MLODQA) have achieved promising results given abundant language-specific training data. However, the considerable annotation cost limits the application of these methods for…

Multilingual neural machine translation has shown the capability of directly translating between language pairs unseen in training, i.e. zero-shot translation. Despite being conceptually attractive, it often suffers from low output quality.…