TIE: Topological Information Enhanced Structural Reading Comprehension
on Web Pages
- URL: http://arxiv.org/abs/2205.06435v1
- Date: Fri, 13 May 2022 03:21:09 GMT
- Title: TIE: Topological Information Enhanced Structural Reading Comprehension
on Web Pages
- Authors: Zihan Zhao, Lu Chen, Ruisheng Cao, Hongshen Xu, Xingyu Chen, and Kai
Yu
- Abstract summary: We propose a Topological Information Enhanced model (TIE) to transform the token-level task into a tag-level task.
TIE integrates Graph Attention Network (GAT) and Pre-trained Language Model (PLM) to leverage the information.
Experimental results demonstrate that our model outperforms strong baselines and achieves both logical structures and spatial structures.
- Score: 31.291568831285442
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
- Easy-to-Hard Learning for Information Extraction [57.827955646831526]
Information extraction systems aim to automatically extract structured information from unstructured texts.
We propose a unified easy-to-hard learning framework consisting of three stages, i.e., the easy stage, the hard stage, and the main stage.
By breaking down the learning process into multiple stages, our framework facilitates the model to acquire general IE task knowledge and improve its generalization ability.
arXiv Detail & Related papers (2023-05-16T06:04:14Z) - PLM-GNN: A Webpage Classification Method based on Joint Pre-trained
Language Model and Graph Neural Network [19.75890828376791]
We propose a representation and classification method based on a pre-trained language model and graph neural network, named PLM-GNN.
It is based on the joint encoding of text and HTML DOM trees in the web pages. It performs well on the KI-04 and SWDE datasets and on practical dataset AHS for the project of scholar's homepage crawling.
arXiv Detail & Related papers (2023-05-09T12:19:10Z) - GROWN+UP: A Graph Representation Of a Webpage Network Utilizing
Pre-training [0.2538209532048866]
We introduce an agnostic deep graph neural network feature extractor that can ingest webpage structures, pre-train self-supervised on massive unlabeled data, and fine-tune to arbitrary tasks on webpages effectually.
We show that our pre-trained model achieves state-of-the-art results using multiple datasets on two very different benchmarks: webpage boilerplate removal and genre classification.
arXiv Detail & Related papers (2022-08-03T13:37:27Z) - Fast Inference and Transfer of Compositional Task Structures for
Few-shot Task Generalization [101.72755769194677]
We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph.
Our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks.
Our experiment results on 2D grid-world and complex web navigation domains show that the proposed method can learn and leverage the common underlying structure of the tasks for faster adaptation to the unseen tasks.
arXiv Detail & Related papers (2022-05-25T10:44:25Z) - BSAL: A Framework of Bi-component Structure and Attribute Learning for
Link Prediction [33.488229191263564]
We propose a bicomponent structural and attribute learning framework (BSAL) that is designed to adaptively leverage information from topology and feature spaces.
BSAL constructs a semantic topology via the node attributes and then gets the embeddings regarding the semantic view.
It provides a flexible and easy-to-implement solution to adaptively incorporate the information carried by the node attributes.
arXiv Detail & Related papers (2022-04-18T03:12:13Z) - CSAGN: Conversational Structure Aware Graph Network for Conversational
Semantic Role Labeling [27.528361001332264]
We present a simple and effective architecture for CSRL which aims to address this problem.
Our model is based on a conversational structure-aware graph network which explicitly encodes the speaker dependent information.
arXiv Detail & Related papers (2021-09-23T07:47:28Z) - Temporal Graph Network Embedding with Causal Anonymous Walks
Representations [54.05212871508062]
We propose a novel approach for dynamic network representation learning based on Temporal Graph Network.
For evaluation, we provide a benchmark pipeline for the evaluation of temporal network embeddings.
We show the applicability and superior performance of our model in the real-world downstream graph machine learning task provided by one of the top European banks.
arXiv Detail & Related papers (2021-08-19T15:39:52Z) - StrucTexT: Structured Text Understanding with Multi-Modal Transformers [29.540122964399046]
Structured text understanding on Visually Rich Documents (VRDs) is a crucial part of Document Intelligence.
This paper proposes a unified framework named StrucTexT, which is flexible and effective for handling both sub-tasks.
We evaluate our method for structured text understanding at segment-level and token-level and show it outperforms the state-of-the-art counterparts.
arXiv Detail & Related papers (2021-08-06T02:57:07Z) - Learning Statistical Texture for Semantic Segmentation [53.7443670431132]
We propose a novel Statistical Texture Learning Network (STLNet) for semantic segmentation.
For the first time, STLNet analyzes the distribution of low level information and efficiently utilizes them for the task.
Based on QCO, two modules are introduced: (1) Texture Enhance Module (TEM), to capture texture-related information and enhance the texture details; (2) Pyramid Texture Feature Extraction Module (PTFEM), to effectively extract the statistical texture features from multiple scales.
arXiv Detail & Related papers (2021-03-06T15:05:35Z) - Minimally-Supervised Structure-Rich Text Categorization via Learning on
Text-Rich Networks [61.23408995934415]
We propose a novel framework for minimally supervised categorization by learning from the text-rich network.
Specifically, we jointly train two modules with different inductive biases -- a text analysis module for text understanding and a network learning module for class-discriminative, scalable network learning.
Our experiments show that given only three seed documents per category, our framework can achieve an accuracy of about 92%.
arXiv Detail & Related papers (2021-02-23T04:14:34Z) - KILT: a Benchmark for Knowledge Intensive Language Tasks [102.33046195554886]
We present a benchmark for knowledge-intensive language tasks (KILT)
All tasks in KILT are grounded in the same snapshot of Wikipedia.
We find that a shared dense vector index coupled with a seq2seq model is a strong baseline.
arXiv Detail & Related papers (2020-09-04T15:32:19Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.