Contextual String Embeddings for Sequence Labeling

COLING 2018  ·  Alan Akbik, Duncan Blythe, Rol Vollgraf, ·

Recent advances in language modeling using recurrent neural networks have made it viable to model language as distributions over characters. By learning to predict the next character on the basis of previous characters, such models have been shown to automatically internalize linguistic concepts such as words, sentences, subclauses and even sentiment... In this paper, we propose to leverage the internal states of a trained character language model to produce a novel type of word embedding which we refer to as contextual string embeddings. Our proposed embeddings have the distinct properties that they (a) are trained without any explicit notion of words and thus fundamentally model words as sequences of characters, and (b) are contextualized by their surrounding text, meaning that the same word will have different embeddings depending on its contextual use. We conduct a comparative evaluation against previous embeddings and find that our embeddings are highly useful for downstream tasks: across four classic sequence labeling tasks we consistently outperform the previous state-of-the-art. In particular, we significantly outperform previous work on English and German named entity recognition (NER), allowing us to report new state-of-the-art F1-scores on the CoNLL03 shared task. We release all code and pre-trained language models in a simple-to-use framework to the research community, to enable reproduction of these experiments and application of our proposed embeddings to other tasks: https://github.com/zalandoresearch/flair read more

PDF Abstract COLING 2018 PDF COLING 2018 Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Benchmark
Chunking CoNLL 2000 Flair Exact Span F1 96.72 # 5
Named Entity Recognition CoNLL 2003 (English) Flair embeddings F1 93.09 # 18
Named Entity Recognition CoNLL 2003 (German) Revised Flair F1 88.3 # 5
Chunking Penn Treebank Flair embeddings F1 score 96.72 # 2
Part-Of-Speech Tagging Penn Treebank Flair embeddings Accuracy 97.85 # 2

Methods


No methods listed for this paper. Add relevant methods here