Filters








1,836 Hits in 10.4 sec

How Can Cross-lingual Knowledge Contribute Better to Fine-Grained Entity Typing?

Hailong Jin, Tiansi Dong, Lei Hou, Juanzi Li, Hui Chen, Zelin Dai, Qu Yincen
2022 Findings of the Association for Computational Linguistics: ACL 2022   unpublished
Cross-lingual Entity Typing (CLET) aims at improving the quality of entity type prediction by transferring semantic knowledge learned from rich-resourced languages to low-resourced languages.  ...  predict types of unseen entities in new languages.  ...  Related Work Fine-grained Entity Typing.  ... 
doi:10.18653/v1/2022.findings-acl.243 fatcat:mjgkbmkyovbxvh3ogvgt3ty5qe

Collective Learning From Diverse Datasets for Entity Typing in the Wild [article]

Abhishek Abhishek and Amar Prakash Azad and Balaji Ganesan and Ashish Anand and Amit Awekar
2019 arXiv   pre-print
Entity typing (ET) is the problem of assigning labels to given entity mentions in a sentence. Existing works for ET require knowledge about the domain and target label set for a given test instance.  ...  We hypothesize that the solution to this problem is to build supervised models that generalize better on the ET task as a whole, rather than a specific dataset.  ...  In our work, we provide a principled approach where multiple datasets can contribute to fine-grained labels.  ... 
arXiv:1810.08782v3 fatcat:whkv6s6zdjaj5lovhba4zk7tr4

Entity Type Prediction Leveraging Graph Walks and Entity Descriptions [article]

Russa Biswas, Jan Portisch, Heiko Paulheim, Harald Sack, Mehwish Alam
2022 arXiv   pre-print
The entity type information in Knowledge Graphs (KGs) such as DBpedia, Freebase, etc. is often incomplete due to automated generation or human curation.  ...  The proposed approach outperforms the baseline approaches on the benchmark datasets DBpedia and FIGER for entity typing in KGs for both fine-grained and coarse-grained classes.  ...  Impact of RDF2vec variants on Fine-Grained Entity Typing.  ... 
arXiv:2207.14094v2 fatcat:kpgg5el65zd4blkznubqejhn2q

Fine-grained Entity Recognition with Reduced False Negatives and Large Type Coverage [article]

Abhishek Abhishek, Sanya Bathla Taneja, Garima Malik, Ashish Anand, Amit Awekar
2019 arXiv   pre-print
Fine-grained Entity Recognition (FgER) is the task of detecting and classifying entity mentions to a large set of types spanning diverse domains such as biomedical, finance and sports.  ...  Using HAnDS framework, we create two datasets, one suitable for building FgER systems recognizing up to 118 entity types based on the FIGER type hierarchy and another for up to 1115 entity types based  ...  We also thank Nitin Nair for his help with code to convert data from brat annotation tool to different formats.  ... 
arXiv:1904.13178v1 fatcat:vehug6uoefcshen6iguqvqj6ju

DeepType: Multilingual Entity Linking by Neural Type System Evolution [article]

Jonathan Raiman, Olivier Raiman
2018 arXiv   pre-print
We apply DeepType to the problem of Entity Linking on three standard datasets (i.e.  ...  First we construct a type system, and second, we use it to constrain the outputs of a neural network to respect the symbolic structure.  ...  . . . , t k can then be combined to rank entities according to how predicted they were by both the entity prediction model and the type system.  ... 
arXiv:1802.01021v1 fatcat:bbdsdnczcbbq3piadbc7qopv5u

"What Are You Trying to Do?" Semantic Typing of Event Processes [article]

Muhao Chen, Hongming Zhang, Haoyu Wang, Dan Roth
2020 arXiv   pre-print
We develop a large dataset containing over 60k event processes, featuring ultra fine-grained typing on both the action and object type axes with very large (10^3∼ 10^4) label vocabularies.  ...  made by the process and (ii) the type of object the process seeks to affect.  ...  The event process typing task seeks to retrieve ultra fine-grained type information to summarize the goal and intention of the associated events.  ... 
arXiv:2010.06724v1 fatcat:lalkges7ejfktbf4h4wrs4ajqq

Effective Transfer Learning for Low-Resource Natural Language Understanding [article]

Zihan Liu
2022 arXiv   pre-print
can better address the domain discrepancy issue in the task knowledge transfer.  ...  Finally, we introduce a coarse-to-fine framework, Coach, and a cross-lingual and cross-domain parsing framework, X2Parser.  ...  In this way, latent variables of different slot types are encouraged to disentangle from each other, leading to a better alignment of cross-lingual representations.  ... 
arXiv:2208.09180v1 fatcat:oei6zn54jbalnixugigs42skue

Cross-lingual Name Tagging and Linking for 282 Languages

Xiaoman Pan, Boliang Zhang, Jonathan May, Joel Nothman, Kevin Knight, Heng Ji
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
Given a document in any of these languages, our framework is able to identify name mentions, assign a coarse-grained or fine-grained type to each mention, and link it to an English Knowledge Base (KB)  ...  The ambitious goal of this work is to develop a cross-lingual name tagging and linking framework for 282 languages that exist in Wikipedia.  ...  Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on.  ... 
doi:10.18653/v1/p17-1178 dblp:conf/acl/PanZMNKJ17 fatcat:sdo4vpvxk5haxkql3554v4alqa

XLM-K: Improving Cross-Lingual Language Model Pre-training with Multilingual Knowledge

Xiaoze Jiang, Yaobo Liang, Weizhu Chen, Nan Duan
2022 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
The results on MLQA and NER exhibit the superiority of XLM-K in knowledge related tasks. The success in XNLI shows a better cross-lingual transferability obtained in XLM-K.  ...  In this paper, we propose XLM-K, a cross-lingual language model incorporating multilingual knowledge in pre-training.  ...  This can introduce a huge amount of alignment data to learn a better cross-lingual representation (Cao et al. 2018a) .  ... 
doi:10.1609/aaai.v36i10.21330 fatcat:vvnpih7yfjatjbmf3gbq2dvyzm

XLM-K: Improving Cross-Lingual Language Model Pre-training with Multilingual Knowledge [article]

Xiaoze Jiang, Yaobo Liang, Weizhu Chen, Nan Duan
2022 arXiv   pre-print
The results on MLQA and NER exhibit the superiority of XLM-K in knowledge related tasks. The success in XNLI shows a better cross-lingual transferability obtained in XLM-K.  ...  In this paper, we propose XLM-K, a cross-lingual language model incorporating multilingual knowledge in pre-training.  ...  It can help our model learn more fine-grained knowledge. Word Embedding and KB Joint Learning Many works leverage word embedding from text corpus to generate better KB embedding.  ... 
arXiv:2109.12573v3 fatcat:q3wara4cbfeh5ambbghiua3zkm

Prix-LM: Pretraining for Multilingual Knowledge Base Construction [article]

Wenxuan Zhou, Fangyu Liu, Ivan Vulić, Nigel Collier, Muhao Chen
2022 arXiv   pre-print
We leverage two types of knowledge, monolingual triples and cross-lingual links, extracted from existing multilingual KBs, and tune a multilingual language encoder XLM-R via a causal language modeling  ...  Experiments on standard entity-related tasks, such as link prediction in multiple languages, cross-lingual entity linking and bilingual lexicon induction, demonstrate its effectiveness, with gains reported  ...  BLI aims to find a counterpart word or phrase in a target language. Similar to XEL, BLI can also evaluate how well a model can align a cross-lingual (entity) space. Task Setup.  ... 
arXiv:2110.08443v2 fatcat:m3ks6ejqxnh7nmhexqdqcyiqyy

X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing [article]

Zihan Liu, Genta Indra Winata, Peng Xu, Pascale Fung
2021 arXiv   pre-print
Experimental results illustrate that our model can significantly outperform existing strong baselines in cross-lingual and cross-domain settings, and our model can also achieve a good generalization ability  ...  In this paper, we present X2Parser, a transferable Cross-lingual and Cross-domain Parser for TCSP.  ...  Acknowledgement We want to say thanks to the anonymous reviewers for the insightful reviews and constructive feedback.  ... 
arXiv:2106.03777v1 fatcat:n6u7ngezr5dt3hvoszy7axzrri

XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation [article]

Sebastian Ruder, Noah Constant, Jan Botha, Aditya Siddhant, Orhan Firat, Jinlan Fu, Pengfei Liu, Junjie Hu, Dan Garrette, Graham Neubig, Melvin Johnson
2021 arXiv   pre-print
In addition, we provide a massively multilingual diagnostic suite (MultiCheckList) and fine-grained multi-dataset evaluation capabilities through an interactive public leaderboard to gain a better understanding  ...  This paper analyzes the current state of cross-lingual transfer learning and summarizes some lessons learned.  ...  We are grateful to Laura Rimell and Jon Clark for valuable feedback on drafts of this paper, and to Dan Gillick for feedback on the Mewsli-X dataset design.  ... 
arXiv:2104.07412v2 fatcat:vut2vpo4pngkfihznfjzbewcou

Few-Shot Cross-lingual Transfer for Coarse-grained De-identification of Code-Mixed Clinical Texts [article]

Saadullah Amin, Noon Pokaratsiri Goldstein, Morgan Kelly Wixted, Alejandro García-Rudolph, Catalina Martínez-Costa, Günter Neumann
2022 arXiv   pre-print
In this work, we empirically show the few-shot cross-lingual transfer property of LMs for named entity recognition (NER) and apply it to solve a low-resource and real-world challenge of code-mixed (Spanish-Catalan  ...  our few-shot cross-lingual target corpus.  ...  We avoid releasing our dataset due to presence of real PHI information. We will consider replacing the real PHI with synthetic ones, similar to MEDDOCAN, for a GDPR-compliant release.  ... 
arXiv:2204.04775v1 fatcat:ai5t6ulki5anpm3kp4vxyt64he

A Comparison of Word Embeddings for English and Cross-Lingual Chinese Word Sense Disambiguation [article]

Hong Jin Kang, Tao Chen, Muthu Kumar Chandrasekaran, Min-Yen Kan
2017 arXiv   pre-print
Thus we have also applied word embeddings to the novel task of cross-lingual WSD for Chinese and provide a public dataset for further benchmarking.  ...  Cross-Lingual WSD - where the word senses of a word in a source language e come from a separate target translation language f - can also assist in language learning; for example, when providing translations  ...  WSD systems can be evaluated using either fine-grained scoring or coarse-grained scoring. Under fine-grained scoring, every sense is equally distinct from each other, and answers must exactly match.  ... 
arXiv:1611.02956v3 fatcat:3qqtyd3flvgtxdiwvvm3narwhq
« Previous Showing results 1 — 15 out of 1,836 results