Named Entity Disambiguation for Noisy Text

By Yotam Eshel, Noam Cohen, Kira Radinsky, Shaul Markovitch, Ikuya Yamada, Omer Levy. 2017

101 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Natural Language Processing, Information Extraction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Information Extraction

Citations in the corpus

Learning Dense Representations for Entity Retrieval (2019, neutral): “Most recent work on entity resolution has focused on training neural network models for the candidate reranking stage (Francis-Landau et al., 2016; Eshel et al., 2017; Yamada et al., 2017a; Gupta et al., 2017; Sil et al., 2018).”
Zero-shot Entity Linking with Dense Entity Retrieval (2019, background): “Onoe and Durrett (2019) from the original WikilinksNED dataset (Eshel et al., 2017), which contains a diverse set of ambiguous entities spanning a variety of domains.”
Scalable Zero-shot Entity Linking with Dense Entity Retrieval (2019, methodology): “WikilinksNED Unseen-Mentions was created by Onoe and Durrett (2019) from the original WikilinksNED dataset (Eshel et al., 2017), which contains a diverse set of ambiguous entities spanning a variety of domains.”
LambdaNet: Probabilistic Type Inference using Graph Neural Networks (2020, methodology): “…might involve looking at object attributes (Farhadi et al., 2017) or label similarity Wang et al. (2018); for natu-ral language, similar techniques are applied to generalize across semantic properties of utterances (Dauphin et al., 2013), entities (Eshel et al., 2017), or labels (Ren et al., 2016).”
From Word to Sense Embeddings: A Survey on Vector Representations of Meaning (2018, methodology): “…for which the embeddings can be used as initialization in the embedding layer on a neural network architecture (Fang, Zhang, Wang, Chen, & Li, 2016; Eshel, Cohen, Radinsky, Markovitch, Yamada, & Levy, 2017) or used directly as a knowledge-based disambiguation system exploiting semantic similarity…”
Fine-Grained Entity Typing for Domain Independent Entity Linking (2019, methodology): “We also test our approach in a harder setting derived from the WikilinksNED dataset (Eshel et al. 2017) where all the mention-entity pairs are unseen during test time.”
Mention and Entity Description Co-Attention for Entity Disambiguation (2018, methodology): “(Ganea and Hofmann 2017) and (Eshel, Cohen, and Radinsky 2017) apply the local attention of contexts side with neural network based methods.”