Language and Domain Independent Entity Linking with Quantified Collective Validation

Wang, Han; Zheng, Jin; Ma, Xiaogang; Fox, Peter; Ji, Heng

doi:10.18653/v1/d15-1081

Cited by 34 publications

(28 citation statements)

References 15 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Without frequency statistics and meta-data, the task becomes substantially more challenging. Some prior works have pointed out the importance of building entity linking systems that can generalize to unseen entity sets (Sil et al, 2012;Wang et al, 2015), but adopt an additional set of assumptions.…”

Section: Testmentioning

confidence: 99%

Zero-Shot Entity Linking by Reading Entity Descriptions

Logeswaran

Chang

Lee

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

192

288

View full text Add to dashboard Cite

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 assumed. In this setting, entities are only identified by text descriptions, and models must rely strictly on language understanding to resolve the new entities. First, we show that strong reading comprehension models pre-trained on large unlabeled data can be used to generalize to unseen entities. Second, we propose a simple and effective adaptive pre-training strategy, which we term domainadaptive pre-training (DAP), to address the domain shift problem associated with linking unseen entities in a new domain. We present experiments on a new dataset that we construct for this task and show that DAP improves over strong pre-training baselines, including BERT. The data and code are available at https: //github.com/lajanugen/zeshel. 1

show abstract

Section: Testmentioning

confidence: 99%

Zero-Shot Entity Linking by Reading Entity Descriptions

Logeswaran

Chang

Lee

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

192

288

View full text Add to dashboard Cite

show abstract

“…They also do not attempt to learn a disambiguation model but directly train their system to replicate noisy projected annotations. Wang et al (2015) refer to their approach as unsupervised, as they do not use unlabeled data. However, their method does not involve any learning and relies on matching heuristics.…”

Section: Related Workmentioning

confidence: 99%

Boosting Entity Linking Performance by Leveraging Unlabeled Documents

Le¹,

Titov²

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Modern entity linking systems rely on large collections of documents specifically annotated for the task (e.g., AIDA CoNLL). In contrast, we propose an approach which exploits only naturally occurring information: unlabeled documents and Wikipedia. Our approach consists of two stages. First, we construct a high recall list of candidate entities for each mention in an unlabeled document. Second, we use the candidate lists as weak supervision to constrain our document-level entity linking model. The model treats entities as latent variables and, when estimated on a collection of unlabelled texts, learns to choose entities relying both on local context of each mention and on coherence with other entities in the document. The resulting approach rivals fully-supervised state-of-the-art systems on standard test sets. It also approaches their performance in the very challenging setting: when tested on a test set sampled from the data used to estimate the supervised systems. By comparing to Wikipedia-only training of our model, we demonstrate that modeling unlabeled documents is beneficial. 1 The best reported in-domain scores are 93.1% F1 (Le and Titov, 2018), whereas the best previous out-of-domain score is only 85.7% F1 (Guo and Barbosa, 2016) (an average over 5 standard out-of-domain test sets, Table 1).

show abstract

“…The approach developed in this paper makes significantly simpler assumptions on the availability of such resources, and therefore can scale also to lowerresource languages, while doing very well also on high-resource languages. Wang et al (2015) proposed an unsupervised method which matches a knowledge graph with a graph constructed from mentions and the corre-sponding candidates of the query document. This approach performs well on the Chinese dataset of TAC'13, but falls into the category (1).…”

Section: Related Workmentioning

confidence: 99%

Cross-lingual Wikification Using Multilingual Embeddings

Tsai¹,

Roth²

2016

Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

132

View full text Add to dashboard Cite

Cross-lingual Wikification is the task of grounding mentions written in non-English documents to entries in the English Wikipedia. This task involves the problem of comparing textual clues across languages, which requires developing a notion of similarity between text snippets across languages. In this paper, we address this problem by jointly training multilingual embeddings for words and Wikipedia titles. The proposed method can be applied to all languages represented in Wikipedia, including those for which no machine translation technology is available. We create a challenging dataset in 12 languages and show that our proposed approach outperforms various baselines. Moreover, our model compares favorably with the best systems on the TAC KBP2015 Entity Linking task including those that relied on the availability of translation from the target language to English.

show abstract

Language and Domain Independent Entity Linking with Quantified Collective Validation

Cited by 34 publications

References 15 publications

Zero-Shot Entity Linking by Reading Entity Descriptions

Zero-Shot Entity Linking by Reading Entity Descriptions

Boosting Entity Linking Performance by Leveraging Unlabeled Documents

Cross-lingual Wikification Using Multilingual Embeddings

Contact Info

Product

Resources

About