Fine-Grained Named Entity Typing over Distantly Supervised Data Based on Refined Representations
This work addresses noisy label issues in NLP for fine-grained entity typing, representing an incremental improvement over existing methods.
The paper tackled the problem of noisy labels in fine-grained named entity typing from distantly supervised data by proposing a graph convolution network that refines mention representations using corpus-level context, resulting in relative improvements of up to 10.2% in macro F1 and 8.3% in micro F1 scores.
Fine-Grained Named Entity Typing (FG-NET) is a key component in Natural Language Processing (NLP). It aims at classifying an entity mention into a wide range of entity types. Due to a large number of entity types, distant supervision is used to collect training data for this task, which noisily assigns type labels to entity mentions irrespective of the context. In order to alleviate the noisy labels, existing approaches on FGNET analyze the entity mentions entirely independent of each other and assign type labels solely based on mention sentence-specific context. This is inadequate for highly overlapping and noisy type labels as it hinders information passing across sentence boundaries. For this, we propose an edge-weighted attentive graph convolution network that refines the noisy mention representations by attending over corpus-level contextual clues prior to the end classification. Experimental evaluation shows that the proposed model outperforms the existing research by a relative score of upto 10.2% and 8.3% for macro f1 and micro f1 respectively.