中文
相关论文

相关论文: Cross-Lingual Syntactic Transfer through Unsupervi…

200 篇论文

We describe a simple but effective method for cross-lingual syntactic transfer of dependency parsers, in the scenario where a large amount of translation data is not available. The method makes use of three steps: 1) a method for deriving…

计算与语言 · 计算机科学 2017-02-07 Mohammad Sadegh Rasooli , Michael Collins

Treebank translation is a promising method for cross-lingual transfer of syntactic dependency knowledge. The basic idea is to map dependency arcs from a source treebank to its target translation according to word alignments. This method,…

计算与语言 · 计算机科学 2019-09-06 Zhang Meishan , Zhang Yue , Fu Guohong

We describe a cross-lingual transfer method for dependency parsing that takes into account the problem of word order differences between source and target languages. Our model only relies on the Bible, a considerably smaller parallel data…

计算与语言 · 计算机科学 2019-03-15 Mohammad Sadegh Rasooli , Michael Collins

Cross-lingual dependency parsing involves transferring syntactic knowledge from one language to another. It is a crucial component for inducing dependency parsers in low-resource scenarios where no training data for a language exists. Using…

计算与语言 · 计算机科学 2019-10-18 James Barry , Joachim Wagner , Jennifer Foster

Syntactic parsing is a highly linguistic processing task whose parser requires training on treebanks from the expensive human annotation. As it is unlikely to obtain a treebank for every human language, in this work, we propose an effective…

计算与语言 · 计算机科学 2021-04-26 Kailai Sun , Zuchao Li , Hai Zhao

Cross-lingual transfer is a leading technique for parsing low-resource languages in the absence of explicit supervision. Simple `direct transfer' of a learned model based on a multilingual input encoding has provided a strong benchmark.…

计算与语言 · 计算机科学 2021-01-28 Kemal Kurniawan , Lea Frermann , Philip Schulz , Trevor Cohn

Natural Language Processing (NLP) has seen remarkable advances in recent years, particularly with the emergence of Large Language Models that have achieved unprecedented performance across many tasks. However, these developments have mainly…

计算与语言 · 计算机科学 2025-02-06 Iker García-Ferrero

In cross-lingual dependency annotation projection, information is often lost during transfer because of early decoding. We present an end-to-end graph-based neural network dependency parser that can be trained to reproduce matrices of edge…

计算与语言 · 计算机科学 2017-01-09 Michael Sejr Schlichtkrull , Anders Søgaard

Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-resource language, whereby parallel corpora provide a bridge to a high-resource language and its associated annotated corpora. However,…

计算与语言 · 计算机科学 2017-05-02 Meng Fang , Trevor Cohn

Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem…

计算与语言 · 计算机科学 2018-09-12 Ruochen Xu , Yiming Yang , Naoki Otani , Yuexin Wu

Cross lingual projection of linguistic annotation suffers from many sources of bias and noise, leading to unreliable annotations that cannot be used directly. In this paper, we introduce a novel approach to sequence tagging that learns to…

计算与语言 · 计算机科学 2016-07-06 Meng Fang , Trevor Cohn

Due to the scarcity of part-of-speech annotated data, existing studies on low-resource languages typically adopt unsupervised approaches for POS tagging. Among these, POS tag projection with word alignment method transfers POS tags from a…

计算与语言 · 计算机科学 2026-02-11 Jianyu Zheng

We describe a transfer method based on annotation projection to develop a dependency-based semantic role labeling system for languages for which no supervised linguistic information other than parallel data is available. Unlike previous…

计算与语言 · 计算机科学 2019-04-09 Maryam Aminian , Mohammad Sadegh Rasooli , Mona Diab

Despite the impressive growth of the abilities of multilingual language models, such as XLM-R and mT5, it has been shown that they still face difficulties when tackling typologically-distant languages, particularly in the low-resource…

计算与语言 · 计算机科学 2023-10-23 Ofir Arviv , Dmitry Nikolaev , Taelin Karidi , Omri Abend

Zero-shot cross-lingual transfer utilizing multilingual LLMs has become a popular learning paradigm for low-resource languages with no labeled training data. However, for NLP tasks that involve fine-grained predictions on words and phrases,…

计算与语言 · 计算机科学 2024-02-06 Duong Minh Le , Yang Chen , Alan Ritter , Wei Xu

Unsupervised learning of syntactic structure is typically performed using generative models with discrete latent variables and multinomial parameters. In most cases, these models have not leveraged continuous word representations. In this…

计算与语言 · 计算机科学 2018-08-29 Junxian He , Graham Neubig , Taylor Berg-Kirkpatrick

Providing technologies to communities or domains where training data is scarce or protected e.g., for privacy reasons, is becoming increasingly important. To that end, we generalise methods for unsupervised transfer from multiple input…

计算与语言 · 计算机科学 2021-10-11 Kemal Kurniawan , Lea Frermann , Philip Schulz , Trevor Cohn

We describe a method for developing broad-coverage semantic dependency parsers for languages for which no semantically annotated resource is available. We leverage a multitask learning framework coupled with an annotation projection method.…

计算与语言 · 计算机科学 2020-05-01 Maryam Aminian , Mohammad Sadegh Rasooli , Mona Diab

Current methods of cross-lingual parser transfer focus on predicting the best parser for a low-resource target language globally, that is, "at treebank level". In this work, we propose and argue for a novel cross-lingual transfer paradigm:…

计算与语言 · 计算机科学 2020-04-17 Robert Litschko , Ivan Vulić , Željko Agić , Goran Glavaš

Cross-lingual transfer learning has become an important weapon to battle the unavailability of annotated resources for low-resource languages. One of the fundamental techniques to transfer across languages is learning…

计算与语言 · 计算机科学 2019-09-23 Wasi Uddin Ahmad , Zhisong Zhang , Xuezhe Ma , Kai-Wei Chang , Nanyun Peng
‹ 上一页 1 2 3 10 下一页 ›