Related papers: CrossAligner & Co: Zero-Shot Transfer Methods for …
Eye tracking data during reading is a useful source of information to understand the cognitive processes that take place during language comprehension processes. Different languages account for different brain triggers , however there seems…
The recent development of fact verification systems with natural logic has enhanced their explainability by aligning claims with evidence through set-theoretic operators, providing faithful justifications. Despite these advancements, such…
Reliable evaluation benchmarks designed for replicability and comprehensiveness have driven progress in machine learning. Due to the lack of a multilingual benchmark, however, vision-and-language research has mostly focused on English…
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 performance on unseen languages has largely been limited to…
Large multilingual pretrained language models such as mBERT and XLM-RoBERTa have been found to be surprisingly effective for cross-lingual transfer of syntactic parsing models (Wu and Dredze 2019), but only between related languages.…
Both grammatical error correction and text style transfer can be viewed as monolingual sequence-to-sequence transformation tasks, but the scarcity of directly annotated data for either task makes them unfeasible for most languages. We…
Current end-to-end approaches to Spoken Language Translation (SLT) rely on limited training resources, especially for multilingual settings. On the other hand, Multilingual Neural Machine Translation (MultiNMT) approaches rely on…
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…
Recent progress in self-training, self-supervised pretraining and unsupervised learning enabled well performing speech recognition systems without any labeled data. However, in many cases there is labeled data available for related…
Recent advancements in text-to-image generative models have demonstrated a remarkable ability to capture a deep semantic understanding of images. In this work, we leverage this semantic knowledge to transfer the visual appearance between…
Large multilingual language models such as mBERT or XLM-R enable zero-shot cross-lingual transfer in various IR and NLP tasks. Cao et al. (2020) proposed a data- and compute-efficient method for cross-lingual adjustment of mBERT that uses a…
Document-level neural machine translation (DocNMT) achieves coherent translations by incorporating cross-sentence context. However, for most language pairs there's a shortage of parallel documents, although parallel sentences are readily…
Cross-lingual transfer of language models trained on high-resource languages like English has been widely studied for many NLP tasks, but focus on conversational tasks has been rather limited. This is partly due to the high cost of…
Transferring information retrieval (IR) models from a high-resource language (typically English) to other languages in a zero-shot fashion has become a widely adopted approach. In this work, we show that the effectiveness of zero-shot…
Information retrieval across different languages is an increasingly important challenge in natural language processing. Recent approaches based on multilingual pre-trained language models have achieved remarkable success, yet they often…
Triangular machine translation is a special case of low-resource machine translation where the language pair of interest has limited parallel data, but both languages have abundant parallel data with a pivot language. Naturally, the key to…
In this work, we present a novel meta-learning algorithm, i.e. TTNet, that regresses model parameters for novel tasks for which no ground truth is available (zero-shot tasks). In order to adapt to novel zero-shot tasks, our meta-learner…
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…
Given new tasks with very little data$-$such as new classes in a classification problem or a domain shift in the input$-$performance of modern vision systems degrades remarkably quickly. In this work, we illustrate how the neural network…
We study the zero-shot transfer capabilities of text matching models on a massive scale, by self-supervised training on 140 source domains from community question answering forums in English. We investigate the model performances on nine…