Related papers: Multilingual Neural Semantic Parsing for Low-Resou…
We tackle the task of automatically discriminating between human and machine translations. As opposed to most previous work, we perform experiments in a multilingual setting, considering multiple languages and multilingual pretrained…
Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages. To disengage from these dependencies, researchers have explored training…
The majority of previous researches addressing multi-lingual IE are limited to zero-shot cross-lingual single-transfer (one-to-one) setting, with high-resource languages predominantly as source training data. As a result, these works…
In this paper, we propose a novel finetuning algorithm for the recently introduced multi-way, mulitlingual neural machine translate that enables zero-resource machine translation. When used together with novel many-to-one translation…
Pre-trained vision and language models such as CLIP have witnessed remarkable success in connecting images and texts with a primary focus on English texts. Despite recent efforts to extend CLIP to support other languages, disparities in…
Text-to-SQL semantic parsing is an important NLP task, which greatly facilitates the interaction between users and the database and becomes the key component in many human-computer interaction systems. Much recent progress in text-to-SQL…
While neural methods for text-to-speech (TTS) have shown great advances in modeling multiple speakers, even in zero-shot settings, the amount of data needed for those approaches is generally not feasible for the vast majority of the world's…
What can pre-trained multilingual sequence-to-sequence models like mBART contribute to translating low-resource languages? We conduct a thorough empirical experiment in 10 languages to ascertain this, considering five factors: (1) the…
In this paper, we proposed two strategies which can be applied to a multilingual neural machine translation system in order to better tackle zero-shot scenarios despite not having any parallel corpus. The experiments show that they are…
Cross-lingual adaptation with multilingual pre-trained language models (mPTLMs) mainly consists of two lines of works: zero-shot approach and translation-based approach, which have been studied extensively on the sequence-level tasks. We…
The great majority of languages in the world are considered under-resourced for the successful application of deep learning methods. In this work, we propose a meta-learning approach to document classification in limited-resource setting…
In this work we focus on transferring supervision signals of natural language generation (NLG) tasks between multiple languages. We propose to pretrain the encoder and the decoder of a sequence-to-sequence model under both monolingual and…
This paper investigates the challenges and potential solutions for improving machine learning systems for low-resource languages. State-of-the-art models in natural language processing (NLP), text-to-speech (TTS), speech-to-text (STT), and…
Neural machine translation~(NMT) is ineffective for zero-resource languages. Recent works exploring the possibility of unsupervised neural machine translation (UNMT) with only monolingual data can achieve promising results. However, there…
Semantic role labeling is a crucial task in natural language processing, enabling better comprehension of natural language. However, the lack of annotated data in multiple languages has posed a challenge for researchers. To address this, a…
General-purpose language models have demonstrated impressive capabilities, performing on par with state-of-the-art approaches on a range of downstream natural language processing (NLP) tasks and benchmarks when inferring instructions from…
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…
Unsupervised translation has reached impressive performance on resource-rich language pairs such as English-French and English-German. However, early studies have shown that in more realistic settings involving low-resource, rare languages,…
Zero-shot cross-lingual transfer by fine-tuning multilingual pretrained models shows promise for low-resource languages, but often suffers from misalignment of internal representations between languages. We hypothesize that even when the…
State-of-the-art neural (re)rankers are notoriously data-hungry which -- given the lack of large-scale training data in languages other than English -- makes them rarely used in multilingual and cross-lingual retrieval settings. Current…