TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages

TL;DR

The paper introduces TIE, a novel model that enhances web page reading comprehension by effectively utilizing the topological structure of web pages through a two-stage process combining GAT and PLM, achieving state-of-the-art results.

Contribution

TIE is the first to explicitly incorporate web page topology at the token level by transforming it into a tag-level task with a two-stage process, improving comprehension accuracy.

Findings

TIE outperforms existing baselines on WebSRC benchmark.

The integration of topological information significantly improves comprehension performance.

State-of-the-art results demonstrate the effectiveness of the proposed approach.

Abstract

Recently, the structural reading comprehension (SRC) task on web pages has attracted increasing research interests. Although previous SRC work has leveraged extra information such as HTML tags or XPaths, the informative topology of web pages is not effectively exploited. In this work, we propose a Topological Information Enhanced model (TIE), which transforms the token-level task into a tag-level task by introducing a two-stage process (i.e. node locating and answer refining). Based on that, TIE integrates Graph Attention Network (GAT) and Pre-trained Language Model (PLM) to leverage the topological information of both logical structures and spatial structures. Experimental results demonstrate that our model outperforms strong baselines and achieves state-of-the-art performances on the web-based SRC benchmark WebSRC at the time of writing. The code of TIE will be publicly available at https://github.com/X-LANCE/TIE.