On the Multi-Property Extraction and Beyond
Tomasz Dwojak, Micha{\l} Pietruszka, {\L}ukasz Borchmann and, Filip Grali\'nski, Jakub Ch{\l}\k{e}dowski
TL;DR
This paper introduces a Dual-source Transformer model that significantly improves information extraction and machine reading comprehension on the WikiReading dataset, and also presents a new, improved dataset called WikiReading Recycled.
Contribution
The paper proposes a novel Dual-source Transformer architecture and introduces WikiReading Recycled, a new dataset for multi-property extraction that addresses limitations of the original.
Findings
Model outperforms previous state-of-the-art on WikiReading
WikiReading Recycled supports multi-property extraction effectively
The new dataset overcomes disadvantages of the original WikiReading
Abstract
In this paper, we investigate the Dual-source Transformer architecture on the WikiReading information extraction and machine reading comprehension dataset. The proposed model outperforms the current state-of-the-art by a large margin. Next, we introduce WikiReading Recycled - a newly developed public dataset, supporting the task of multiple property extraction. It keeps the spirit of the original WikiReading but does not inherit the identified disadvantages of its predecessor.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNatural Language Processing Techniques · Topic Modeling · Multimodal Machine Learning Applications
MethodsLinear Layer · Absolute Position Encodings · Position-Wise Feed-Forward Layer · Residual Connection · Label Smoothing · Multi-Head Attention · Adam · *Communicated@Fast*How Do I Communicate to Expedia? · Dropout · Byte Pair Encoding