A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
A Teacher-Student Framework for Zero-Resource Neural Machine Translation
[article]
2017
arXiv
pre-print
While end-to-end neural machine translation (NMT) has made remarkable progress recently, it still suffers from the data scarcity problem for low-resource language pairs and domains. ...
In this paper, we propose a method for zero-resource NMT by assuming that parallel sentences have close probabilities of generating a sentence in a third language. ...
In this paper, we propose a new method for zero-resource neural machine translation. ...
arXiv:1705.00753v1
fatcat:3euadliqfjao5n2dg7bqlwpgcq
A Teacher-Student Framework for Zero-Resource Neural Machine Translation
2017
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
While end-to-end neural machine translation (NMT) has made remarkable progress recently, it still suffers from the data scarcity problem for low-resource language pairs and domains. ...
In this paper, we propose a method for zero-resource NMT by assuming that parallel sentences have close probabilities of generating a sentence in a third language. ...
In this paper, we propose a new method for zero-resource neural machine translation. ...
doi:10.18653/v1/p17-1176
dblp:conf/acl/ChenLCL17
fatcat:l5omxvfwdvaffncjpwphaj4vi4
UM4: Unified Multilingual Multiple Teacher-Student Model for Zero-Resource Neural Machine Translation
[article]
2022
arXiv
pre-print
Our method unifies source-teacher, target-teacher, and pivot-teacher models to guide the student model for the zero-resource translation. ...
In this paper, we propose a novel method, named as Unified Multilingual Multiple teacher-student Model for NMT (UM4). ...
Related Work Zero-Resource NMT Zero-resource neural machine translation (NMT) is a challenging task since the source-target parallel corpus is not available. ...
arXiv:2207.04900v1
fatcat:3v7p74euw5h33a2xqemanlhcxq
Zero-Shot Cross-Lingual Abstractive Sentence Summarization through Teaching Generation and Attention
2019
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
This teaching process is along with a back-translation process which simulates source-summary pairs. ...
We propose to solve this zero-shot problem by using resource-rich monolingual AS-SUM system to teach zero-shot cross-lingual ASSUM system on both summary word generation and attention. ...
Acknowledgments The authors would like to thank the anonymous reviewers for the helpful comments. ...
doi:10.18653/v1/p19-1305
dblp:conf/acl/DuanYZCL19
fatcat:fugwbh5lvbegnhi4c2ykise5ce
Zero-Resource Neural Machine Translation with Multi-Agent Communication Game
2018
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
To tackle this problem, we propose an interactive multimodal framework for zero-resource neural machine translation. ...
While end-to-end neural machine translation (NMT) has achieved notable success in the past years in translating a handful of resource-rich language pairs, it still suffers from the data scarcity problem ...
Below we formally define the game, which is a general learning framework for training zero-resource machine translation model with monolingual multimodal documents only. ...
doi:10.1609/aaai.v32i1.11976
fatcat:pj2thmmjgjglbgxyswuuxum55q
Zero-Resource Neural Machine Translation with Multi-Agent Communication Game
[article]
2018
arXiv
pre-print
To tackle this problem, we propose an interactive multimodal framework for zero-resource neural machine translation. ...
While end-to-end neural machine translation (NMT) has achieved notable success in the past years in translating a handful of resource-rich language pairs, it still suffers from the data scarcity problem ...
Below we formally define the game, which is a general learning framework for training zero-resource machine translation model with monolingual multimodal documents only. ...
arXiv:1802.03116v1
fatcat:is4dmgiooreolchiwauu3tsiqm
XL-NBT: A Cross-lingual Neural Belief Tracking Framework
[article]
2018
arXiv
pre-print
Then, we pre-train a state tracker for the source language as a teacher, which is able to exploit easy-to-access parallel data. ...
In order to bypass the expensive human annotation and achieve the first step towards the ultimate goal of building a universal dialog system, we set out to build a cross-lingual state tracking framework ...
Acknowledgement We are gratefully supported by a Tencent AI Lab Rhino-Bird Gift Fund. ...
arXiv:1808.06244v2
fatcat:ousmc2ltlndrvjyx73l6rbpdva
A Brief Survey of Multilingual Neural Machine Translation
[article]
2020
arXiv
pre-print
We present a survey on multilingual neural machine translation (MNMT), which has gained a lot of traction in the recent years. ...
We hope this paper will serve as a starting point for researchers and engineers interested in MNMT. ...
These bilingual models are used as teacher models to train a single student model for all language pairs. ...
arXiv:1905.05395v3
fatcat:cyufmt3y65bhjofvt5zeljahz4
Translate-Distill: Learning Cross-Language Dense Retrieval by Translation and Distillation
[article]
2024
arXiv
pre-print
This richer design space enables the teacher model to perform inference in an optimized setting, while training the student model directly for CLIR. ...
Prior work on English monolingual retrieval has shown that a cross-encoder trained using a large number of relevance judgments for query-document pairs can be used as a teacher to train more efficient, ...
Our framework combines Translate-Train with cross-encoder distillation to train a CLIR dual-encoder model without additional data resources. ...
arXiv:2401.04810v1
fatcat:vpbb5onwc5cl3hnywhmmc3zvwm
Realistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification
[article]
2022
arXiv
pre-print
We also develop a bilingual teacher-student zero-shot transfer approach, which exploits additional unlabeled documents of the target language and performs better than a model fine-tuned directly on labeled ...
We use it to show that translation-based methods vastly outperform cross-lingual fine-tuning of multilingually pre-trained models, the best previous zero-shot transfer method for MultiEURLEX. ...
This suggests that exploiting modern Neural Machine Translation (NMT) systems is a much better zero-shot cross-lingual transfer strategy in real life, at least for legal topic classification. • We develop ...
arXiv:2206.03785v1
fatcat:ux6j4cmlr5hlvadvswk55z4rwa
FreeTransfer-X: Safe and Label-Free Cross-Lingual Transfer from Off-the-Shelf Models
[article]
2022
arXiv
pre-print
The significant improvement over strong neural machine translation (NMT) baselines demonstrates the effectiveness of the proposed method. ...
Instead of pursuing the original labels, a workaround for CLT is to transfer knowledge from the off-the-shelf models without labels. ...
Baselines Translate-Test (Conneau et al., 2018 ) is a machine translation based method. ...
arXiv:2206.06586v1
fatcat:ixmluws4inhizl446xs2sofzk4
Cross-lingual Machine Reading Comprehension with Language Branch Knowledge Distillation
[article]
2020
arXiv
pre-print
Then, we devise a multilingual distillation approach to amalgamate knowledge from multiple language branch models to a single model for all target languages. ...
Many previous approaches use translation data by translating from a rich-source language, such as English, to low-source languages as auxiliary supervision. ...
We further propose a novel multilingual multi-teacher distillation framework. ...
arXiv:2010.14271v1
fatcat:vb3tpz5xbrefdj5qabrqfgegyq
Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents
[article]
2022
arXiv
pre-print
Document-level neural machine translation (DocNMT) achieves coherent translations by incorporating cross-sentence context. ...
We focus on the scenario of zero-shot transfer from teacher languages with document level data to student languages with no documents but sentence level data, and for the first time treat document-level ...
We would also like to thank the Google Translate team for their constructive discussions and comments. ...
arXiv:2109.10341v2
fatcat:jymnbdc7ujeuple6ffauyr754a
XL-NBT: A Cross-lingual Neural Belief Tracking Framework
2018
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
Then, we pre-train a state tracker for the source language as a teacher, which is able to exploit easy-to-access parallel data. ...
In order to bypass the expensive human annotation and achieve the first step towards the ultimate goal of building a universal dialog system, we set out to build a cross-lingual state tracking framework ...
Acknowledgement We are gratefully supported by a Tencent AI Lab Rhino-Bird Gift Fund. ...
doi:10.18653/v1/d18-1038
dblp:conf/emnlp/ChenCSWYYW18
fatcat:6r6bo2ezbbe5hjymr7aos3igu4
Cross-lingual Knowledge Transfer via Distillation for Multilingual Information Retrieval
[article]
2023
arXiv
pre-print
The second model is a cross-encoder re-ranker trained on multilingual retrieval data generated using neural machine translation. ...
According to the MIRACL leaderboard, our approach ranks 8th for the Test-A set and 2nd for the Test-B set among the 16 known languages. ...
We are grateful for their efforts in hosting a superb competition and providing top-notch datasets. ...
arXiv:2302.13400v1
fatcat:cvrbpsqdjjbh5favubd2fxouiq
« Previous
Showing results 1 — 15 out of 3,778 results