Named Entity Disambiguation for Noisy Text

06/28/2017
by   Yotam Eshel, et al.
0

We address the task of Named Entity Disambiguation (NED) for noisy text. We present WikilinksNED, a large-scale NED dataset of text fragments from the web, which is significantly noisier and more challenging than existing news-based datasets. To capture the limited and noisy local context surrounding each mention, we design a neural model and train it with a novel method for sampling informative negative examples. We also describe a new way of initializing word and entity embeddings that significantly improves performance. Our model significantly outperforms existing state-of-the-art methods on WikilinksNED while achieving comparable performance on a smaller newswire dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/15/2019

Robust Named Entity Recognition with Truecasing Pretraining

Although modern named entity recognition (NER) systems show impressive p...
research
07/05/2023

Named Entity Inclusion in Abstractive Text Summarization

We address the named entity omission - the drawback of many current abst...
research
03/15/2017

Sparse Named Entity Classification using Factorization Machines

Named entity classification is the task of classifying text-based elemen...
research
08/07/2018

Design Challenges in Named Entity Transliteration

We analyze some of the fundamental design challenges that impact the dev...
research
11/13/2019

Robustness to Capitalization Errors in Named Entity Recognition

Robustness to capitalization errors is a highly desirable characteristic...
research
02/03/2017

Named Entity Evolution Recognition on the Blogosphere

Advancements in technology and culture lead to changes in our language. ...

Please sign up or login with your details

Forgot password? Click here to reset