Open Named Entity Modeling from Embedding Distribution

Abstract

In this paper, we report our discovery on named entity distribution in a general word embedding space, which helps an open definition on multilingual named entity definition rather than previous closed and constraint definition on named entities through a named entity dictionary, which is usually derived from human labor and replies on schedule update. Our initial visualization of monolingual word embeddings indicates named entities tend to gather together despite of named entity types and language difference, which enable us to model all named entities using a specific geometric structure inside embedding space, namely, the named entity hypersphere. For monolingual cases, the proposed named entity model gives an open description of diverse named entity types and different languages. For cross-lingual cases, mapping the proposed named entity model provides a novel way to build a named entity dataset for resource-poor languages. At last, the proposed named entity model may be shown as a handy clue to enhance state-of-the-art named entity recognition systems generally.

arXiv commentThe early version accepted by IEEE Transactions on Knowledge and Data Engineering (TKDE)

References in corpus (9)

• Distributed Representations of Words and Phrases and their Compositionality
• Exploiting Similarities among Languages for Machine Translation
• A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings
• Word Translation Without Parallel Data
• Empower Sequence Labeling with Task-Aware Neural Language Model
• Weakly Supervised Cross-Lingual Named Entity Recognition via Effective Annotation and Representation Projection
• Modeling Multi-turn Conversation with Deep Utterance Aggregation
• SwellShark: A Generative Model for Biomedical Named Entity Recognition without Labeled Data
• Low-Resource Named Entity Recognition with Cross-Lingual, Character-Level Neural Conditional Random Fields