Filters








364 Hits in 4.2 sec

Cross-lingual Entity Alignment with Incidental Supervision [article]

Muhao Chen, Weijia Shi, Ben Zhou, Dan Roth
2021 arXiv   pre-print
Therefore, we propose an incidentally supervised model, JEANS , which jointly represents multilingual KGs and text corpora in a shared embedding scheme, and seeks to improve entity alignment with incidental  ...  Experiments on benchmark datasets show that JEANS leads to promising improvement on entity alignment with incidental supervision, and significantly outperforms state-of-the-art methods that solely rely  ...  As they focus on a monolingual and supervised scenario, they are essentially different from our goal to help cross-lingual KG alignment with incidental supervision from unparalleled corpora.  ... 
arXiv:2005.00171v2 fatcat:xr7rs2y6vvakjkyz7we7xzckyy

Cross-lingual Entity Alignment with Incidental Supervision

Muhao Chen, Weijia Shi, Ben Zhou, Dan Roth
2021 Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume   unpublished
Therefore, we propose an incidentally supervised model, JEANS , which jointly represents multilingual KGs and text corpora in a shared embedding scheme, and seeks to improve entity alignment with incidental  ...  Experiments on benchmark datasets show that JEANS leads to promising improvement on entity alignment with incidental supervision, and significantly outperforms state-of-the-art methods that solely rely  ...  As they focus on a monolingual and supervised scenario, they are essentially different from our goal to help cross-lingual KG alignment with incidental supervision from unparalleled corpora.  ... 
doi:10.18653/v1/2021.eacl-main.53 fatcat:c7ibvv435vaidp4lnr5iwbx26e

Incidental Supervision: Moving beyond Supervised Learning

Dan Roth
2017 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
discuss (i) esponse Driven Learning of models, a learning protocol that supports inducing meaning representations simply by observing the model's behavior in its environment, (ii) the exploitation of Incidental  ...  to support global decisions where joint supervision is not available.  ...  As pointed out above, with the additional incidental supervision signal provided by the cross-lingual links, documents in multiple languages can be Wikified into the English Wikipedia (Tsai and Roth 2016b  ... 
doi:10.1609/aaai.v31i1.11146 fatcat:ag665ep3rzdxlon5zmqbunp7om

Incidental Supervision: Moving beyond Supervised Learning [article]

Dan Roth
2020 arXiv   pre-print
This paper describes several learning paradigms that are designed to alleviate the supervision bottleneck.  ...  However, learning models for these tasks is difficult partly because generating the necessary supervision signals for it is costly and does not scale.  ...  As pointed out above, with the additional incidental supervision signal provided by the cross-lingual links, documents in multiple languages can be Wikified into the English Wikipedia (Tsai and Roth 2016b  ... 
arXiv:2005.12339v1 fatcat:6quvmq7ezzff3c5jnyhiznnrru

"Wikily" Supervised Neural Translation Tailored to Cross-Lingual Tasks [article]

Mohammad Sadegh Rasooli, Chris Callison-Burch, Derry Tanti Wijaya
2021 arXiv   pre-print
Moreover, we tailor our wikily supervised translation models to unsupervised image captioning, and cross-lingual dependency parser transfer.  ...  We show that first sentences and titles of linked Wikipedia pages, as well as cross-lingual image captions, are strong signals for a seed parallel data to extract bilingual dictionaries and cross-lingual  ...  This work is supported in part by the DARPA HR001118S0044 (the LwLL program), and the Department of the Air Force FA8750-19-2-3334 (Semi-supervised Learning of Multimodal Representations). The U.S.  ... 
arXiv:2104.08384v2 fatcat:vswaqg27mve4fpepwuxqzougru

Foreseeing the Benefits of Incidental Supervision [article]

Hangfeng He, Mingyuan Zhang, Qiang Ning, Dan Roth
2021 arXiv   pre-print
These could include partial labels, noisy labels, knowledge-based constraints, and cross-domain or cross-task annotations -- all having statistical associations with gold annotations but not exactly the  ...  Real-world applications often require improved models by leveraging a range of cheap incidental supervision signals.  ...  A.5 More Examples with Incidental Signals In this subsection, we show more examples with incidental signals, including within-sentence constraints, cross-sentence constraints, auxiliary labels, cross-lingual  ... 
arXiv:2006.05500v2 fatcat:e4yj4zu3ozfylibouota64mdhi

Probabilistic topic modeling in multilingual settings: An overview of its methodology and applications

Ivan Vulić, Wim De Smet, Jie Tang, Marie-Francine Moens
2015 Information Processing & Management  
cross-lingual semantic similarity, and (4) cross-lingual information retrieval.  ...  tasks involving different languages, without any external language pair dependent translation resource: (1) cross-lingual event-centered news clustering, (2) cross-lingual document classification, (3)  ...  Cross-lingual entity linking (Zhang, Liu, & Zhao, 2013) . Given an entity mention, the goal of the task is to link the mention of an entity to some given knowledge base (e.g., Wikipedia).  ... 
doi:10.1016/j.ipm.2014.08.003 fatcat:vpa5wdjc5ja5lchaoocctciqui

Distributional Correspondence Indexing for Cross-Lingual and Cross-Domain Sentiment Classification

Alejandro Moreo Fernández, Andrea Esuli, Fabrizio Sebastiani
2016 The Journal of Artificial Intelligence Research  
Experiments show that DCI obtains better performance than current state-of-the-art techniques for cross-lingual and cross-domain sentiment classification.  ...  As a final contribution, we discuss a more challenging formulation of the domain adaptation problem, in which both the cross-domain and cross-lingual dimensions are tackled simultaneously.  ...  One important bottleneck that supervised machine learning methods have to deal with has to do with their dependence on high-quality annotated examples in order for the model to be trained.  ... 
doi:10.1613/jair.4762 fatcat:tng7o2e4dvchnkbvfxkuddqmmu

Generalized Funnelling: Ensemble Learning and Heterogeneous Document Embeddings for Cross-Lingual Text Classification [article]

Alejandro Moreo, Andrea Pedrotti, Fabrizio Sebastiani
2022 arXiv   pre-print
Funnelling (Fun) is a recently proposed method for cross-lingual text classification (CLTC) based on a two-tier learning ensemble for heterogeneous transfer learning (HTL).  ...  In this ensemble method, 1st-tier classifiers, each working on a different and language-dependent feature space, return a vector of calibrated posterior probabilities (with one dimension for each class  ...  The first examples of cross-lingual representations were proposed during the '90s.  ... 
arXiv:2110.14764v2 fatcat:4mm6n6crtvgf3ktwmizllw77ci

A Survey of Code-switched Speech and Language Processing [article]

Sunayana Sitaram, Khyathi Raghavi Chandu, Sai Krishna Rallabandi, Alan W Black
2020 arXiv   pre-print
We conclude with future directions and open problems in the field.  ...  We motivate why processing code-switched text and speech is essential for building intelligent agents and systems that interact with users in multilingual communities.  ...  Improving cross-lingual models Recently, code-switched text has been used to improve the performance of cross-lingual systems.  ... 
arXiv:1904.00784v3 fatcat:r5tsg4kdnfbtnndae523c32pta

MLSUM: The Multilingual Summarization Corpus [article]

Thomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski, Jacopo Staiano
2020 arXiv   pre-print
We report cross-lingual comparative analyses based on state-of-the-art systems. These highlight existing biases which motivate the use of a multi-lingual dataset.  ...  Together with English newspapers from the popular CNN/Daily mail dataset, the collected data form a large scale multilingual dataset which can enable new research directions for the text summarization  ...  Mlqa: Evaluating cross-lingual extractive question answering. arXiv preprint arXiv:1910.07475.  ... 
arXiv:2004.14900v1 fatcat:vwiennfr4zbstprtrvc3rxf2rm

Bridging the Data Gap between Training and Inference for Unsupervised Neural Machine Translation [article]

Zhiwei He, Xing Wang, Rui Wang, Shuming Shi, Zhaopeng Tu
2022 arXiv   pre-print
A UNMT model is trained on the pseudo parallel data with translated source, and translates natural source sentences in inference.  ...  corpora only, unsupervised cross-lingual embedding mappings had been well studied by Zhang et al. (2017); Artetxe et al. (2017, 2018a); Conneau et al. (2018).  ...  These methods try to align the word embedding spaces of two languages with- out parallel data and thus can be exploited for unsu- Table 15 : 15 SacreBLEU results of Table2.  ... 
arXiv:2203.08394v4 fatcat:34unavaoijf5petzrbbfj4qgwq

Microplate Fixation without Maxillomandibular Fixation in Double Mandibular Fractures

Seung Wook Song, Jin Sik Burm, Won Yong Yang, Sang Yoon Kang
2014 Archives of Craniofacial Surgery  
For bony fixations, we used microplates with or without wire. After reduction, each fracture site was fixed at two or three points to maintain anatomical alignment of the mandible.  ...  Methods: Thirty-four patients with double mandibular fractures were treated with open reduction and internal fixation without MMF. Both fracture sites were surgically treated.  ...  A cross-section of the mandible looks like a long curved trapezoid or triangle with round edges.  ... 
doi:10.7181/acfs.2014.15.2.53 pmid:28913191 pmcid:PMC5556814 fatcat:o2ie7ez6pbed3enlyfuxyr7u4e

Effective and practical neural ranking

Sean MacAvaney
2021 SIGIR Forum  
I find that this approach is neither limited to the task of ad-hoc ranking (as demonstrated by ranking clinical reports) nor English content (as shown by training effective cross-lingual neural rankers  ...  Supervised machine learning methods that use neural networks ("deep learning") have yielded substantial improvements to a multitude of Natural Language Processing (NLP) tasks in the past decade.  ...  CLEF also hosted multiple cross-lingual ad-hoc retrieval tasks from 2000 to 2009 [15] .  ... 
doi:10.1145/3476415.3476432 fatcat:fdjy53sggvhgxo5fa5hzpede2i

On the Effects of Low-Quality Training Data on Information Extraction from Clinical Reports

Diego Marcheggiani, Fabrizio Sebastiani
2017 Journal of Data and Information Quality  
Most of this literature is about methods based on supervised learning, i.e., methods for training an information extraction system from manually annotated examples.  ...  We do this by comparing the accuracy deriving from training data annotated by the authoritative coder (i.e., the one who has also annotated the test data, and by whose judgment we must abide), with the  ...  classified) and cross-lingual classification (which denotes a variant of text classification which exploits synergies between training data expressed in different languages).  ... 
doi:10.1145/3106235 dblp:journals/jdiq/MarcheggianiS17 fatcat:tqz6srfggbguhdx2xvrwx3dh5m
« Previous Showing results 1 — 15 out of 364 results