Related papers: Zero-shot Chinese Discourse Dependency Parsing via…

Localizing a semantic parser to support new languages requires effective cross-lingual generalization. Recent work has found success with machine-translation or zero-shot methods although these approaches can struggle to model how native…

Zero-shot neural machine translation is an attractive goal because of the high cost of obtaining data and building translation systems for new translation directions. However, previous papers have reported mixed success in zero-shot…

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…

We demonstrate a program that learns to pronounce Chinese text in Mandarin, without a pronunciation dictionary. From non-parallel streams of Chinese characters and Chinese pinyin syllables, it establishes a many-to-many mapping between…

Direct dependency parsing of the speech signal -- as opposed to parsing speech transcriptions -- has recently been proposed as a task (Pupier et al. 2022), as a way of incorporating prosodic information in the parsing system and bypassing…

Modern Entity Linking (EL) systems entrench a popularity bias, yet there is no dataset focusing on tail and emerging entities in languages other than English. We present Hansel, a new benchmark in Chinese that fills the vacancy of…

Recent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection. Dataset genre labels are already frequently available,…

Task-oriented Dialogue (ToD) agents are mostly limited to a few widely-spoken languages, mainly due to the high cost of acquiring training data for each language. Existing low-cost approaches that rely on cross-lingual embeddings or naive…

We present the zero-shot entity linking task, where mentions must be linked to unseen entities without in-domain labeled data. The goal is to enable robust transfer to highly specialized domains, and so no metadata or alias tables are…

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…

The scarcity of labeled training data often prohibits the internationalization of NLP models to multiple languages. Recent developments in cross-lingual understanding (XLU) has made progress in this area, trying to bridge the language…

We consider zero-shot cross-lingual transfer in legal topic classification using the recent MultiEURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual transfer, we develop a…

We introduce the task of zero-shot style transfer between different languages. Our training data includes multilingual parallel corpora, but does not contain any parallel sentences between styles, similarly to the recent previous work. We…

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…

State-of-the-art slot filling models for goal-oriented human/machine conversational language understanding systems rely on deep learning methods. While multi-task training of such models alleviates the need for large in-domain annotated…

Dialogue topic shift detection is to detect whether an ongoing topic has shifted or should shift in a dialogue, which can be divided into two categories, i.e., response-known task and response-unknown task. Currently, only a few…

Grammar competency estimation is essential for assessing linguistic proficiency in both written and spoken language; however, the spoken modality presents additional challenges due to its spontaneous, unstructured, and disfluent nature.…

Current approaches to cross-lingual sentiment analysis try to leverage the wealth of labeled English data using bilingual lexicons, bilingual vector space embeddings, or machine translation systems. Here we show that it is possible to use a…

Multilingual neural machine translation systems learn to map sentences of different languages into a common representation space. Intuitively, with a growing number of seen languages the encoder sentence representation grows more flexible…

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…