Related papers: Entities, Dates, and Languages: Zero-Shot on Histo…
Transfer learning has led to large gains in performance for nearly all NLP tasks while making downstream models easier and faster to train. This has also been extended to low-resourced languages, with some success. We investigate the…
Named Entities (NEs) are often written with no orthographic changes across different languages that share a common alphabet. We show that this can be leveraged so as to improve named entity recognition (NER) by using unsupervised word…
The ability to automatically identify whether an entity is referenced in a future context can have multiple applications including decision making, planning and trend forecasting. This paper focuses on detecting implicit future references…
Prompt-based classifiers are an attractive approach for zero-shot classification. However, the precise choice of the prompt template and label words can largely influence performance, with semantically equivalent settings often showing…
This paper describes our submission of the WMT 2020 Shared Task on Sentence Level Direct Assessment, Quality Estimation (QE). In this study, we empirically reveal the \textit{mismatching issue} when directly adopting BERTScore to QE.…
Despite rapid progress in increasing the language coverage of automatic speech recognition, the field is still far from covering all languages with a known writing script. Recent work showed promising results with a zero-shot approach…
We study the selection of transfer languages for different Natural Language Processing tasks, specifically sentiment analysis, named entity recognition and dependency parsing. In order to select an optimal transfer language, we propose to…
Vision-language models trained on large, randomly collected data had significant impact in many areas since they appeared. But as they show great performance in various fields, such as image-text-retrieval, their inner workings are still…
Leveraging class semantic descriptions and examples of known objects, zero-shot learning makes it possible to train a recognition model for an object class whose examples are not available. In this paper, we propose a novel zero-shot…
Traditional text classification approaches often require a good amount of labeled data, which is difficult to obtain, especially in restricted domains or less widespread languages. This lack of labeled data has led to the rise of…
Zero-resource cross-lingual transfer approaches aim to apply supervised models from a source language to unlabelled target languages. In this paper we perform an in-depth study of the two main techniques employed so far for cross-lingual…
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…
This work focuses on the semantic relations between scenes and objects for visual object recognition. Semantic knowledge can be a powerful source of information especially in scenarios with few or no annotated training samples. These…
Recent breakthroughs in large language models (LLMs) have opened the door to in-depth investigation of their potential in tabular data modeling. However, effectively utilizing advanced LLMs in few-shot and even zero-shot scenarios is still…
Many previous models of named entity recognition (NER) suffer from the problem of Out-of-Entity (OOE), i.e., the tokens in the entity mentions of the test samples have not appeared in the training samples, which hinders the achievement of…
We present a multilingual Named Entity Recognition approach based on a robust and general set of features across languages and datasets. Our system combines shallow local information with clustering semi-supervised features induced on large…
Prompt-based methods have been successfully applied to multilingual pretrained language models for zero-shot cross-lingual understanding. However, most previous studies primarily focused on sentence-level classification tasks, and only a…
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…
Effective ontology transfer has been a major goal of recent work on event argument extraction (EAE). Two methods in particular -- question answering (QA) and template infilling (TI) -- have emerged as promising approaches to this problem.…
Text classification of unseen classes is a challenging Natural Language Processing task and is mainly attempted using two different types of approaches. Similarity-based approaches attempt to classify instances based on similarities between…