More Like this

1. Improving information extraction from visually rich documents using visual span representations

   https://doi.org/10.14778/3446095.3446104  

   Sarkhel, Ritesh; Nandi, Arnab (January 2021, Proceedings of the VLDB Endowment)

   null (Ed.)

   Along with textual content, visual features play an essential role in the semantics of visually rich documents. Information extraction (IE) tasks perform poorly on these documents if these visual cues are not taken into account. In this paper, we present Artemis - a visually aware, machine-learning-based IE method for heterogeneous visually rich documents. Artemis represents a visual span in a document by jointly encoding its visual and textual context for IE tasks. Our main contribution is two-fold. First, we develop a deep-learning model that identifies the local context boundary of a visual span with minimal human-labeling. Second, we describe a deep neural network that encodes the multimodal context of a visual span into a fixed-length vector by taking its textual and layout-specific features into account. It identifies the visual span(s) containing a named entity by leveraging this learned representation followed by an inference task. We evaluate Artemis on four heterogeneous datasets from different domains over a suite of information extraction tasks. Results show that it outperforms state-of-the-art text-based methods by up to 17 points in F1-score. 

   more » « less
2. Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks

   https://doi.org/10.1145/3442381.3450114  

   Zhang, Xinyang; Zhang, Chenwei; Dong, Xin Luna; Shang, Jingbo; Han, Jiawei (April 2021, WWW '21: The Web Conference 2021)

   null (Ed.)

   Text categorization is an essential task in Web content analysis. Considering the ever-evolving Web data and new emerging categories, instead of the laborious supervised setting, in this paper, we focus on the minimally-supervised setting that aims to categorize documents effectively, with a couple of seed documents annotated per category. We recognize that texts collected from the Web are often structure-rich, i.e., accompanied by various metadata. One can easily organize the corpus into a text-rich network, joining raw text documents with document attributes, high-quality phrases, label surface names as nodes, and their associations as edges. Such a network provides a holistic view of the corpus’ heterogeneous data sources and enables a joint optimization for network-based analysis and deep textual model training. We therefore 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. Each module generates pseudo training labels from the unlabeled document set, and both modules mutually enhance each other by co-training using pooled pseudo labels. We test our model on two real-world datasets. On the challenging e-commerce product categorization dataset with 683 categories, our experiments show that given only three seed documents per category, our framework can achieve an accuracy of about 92%, significantly outperforming all compared methods; our accuracy is only less than 2% away from the supervised BERT model trained on about 50K labeled documents. 

   more » « less
3. Hierarchical Metadata-Aware Document Categorization under Weak Supervision

   https://doi.org/10.1145/3437963.3441730  

   Zhang, Yu; Chen, Xiusi; Meng, Yu; Han, Jiawei (March 2021, WSDM'21, The Fourteenth ACM International Conference on Web Search and Data Mining, March 2021)

   null (Ed.)

   Categorizing documents into a given label hierarchy is intuitively appealing due to the ubiquity of hierarchical topic structures in massive text corpora. Although related studies have achieved satisfying performance in fully supervised hierarchical document classification, they usually require massive human-annotated training data and only utilize text information. However, in many domains, (1) annotations are quite expensive where very few training samples can be acquired; (2) documents are accompanied by metadata information. Hence, this paper studies how to integrate the label hierarchy, metadata, and text signals for document categorization under weak supervision. We develop HiMeCat, an embedding-based generative framework for our task. Specifically, we propose a novel joint representation learning module that allows simultaneous modeling of category dependencies, metadata information and textual semantics, and we introduce a data augmentation module that hierarchically synthesizes training documents to complement the original, small-scale training set. Our experiments demonstrate a consistent improvement of HiMeCat over competitive baselines and validate the contribution of our representation learning and data augmentation modules. 

   more » « less
4. Predicting Institution Outcomes for Inter Partes Review (IPR) Proceedings at the United States Patent Trial & Appeal Board by Deep Learning of Patent Owner Preliminary Response Briefs

   https://doi.org/10.3390/app12073656  

   Sokhansanj, Bahrad A.; Rosen, Gail L. (April 2022, Applied Sciences)

   A key challenge for artificial intelligence in the legal field is to determine from the text of a party’s litigation brief whether, and why, it will succeed or fail. This paper shows a proof-of-concept test case from the United States: predicting outcomes of post-grant inter partes review (IPR) proceedings for invalidating patents. The objectives are to compare decision-tree and deep learning methods, validate interpretability methods, and demonstrate outcome prediction based on party briefs. Specifically, this study compares and validates two distinct approaches: (1) representing documents with term frequency inverse document frequency (TF-IDF), training XGBoost gradient-boosted decision-tree models, and using SHAP for interpretation. (2) Deep learning of document text in context, using convolutional neural networks (CNN) with attention, and comparing LIME and attention visualization for interpretability. The methods are validated on the task of automatically determining case outcomes from unstructured written decision opinions, and then used to predict trial institution or denial based on the patent owner’s preliminary response brief. The results show how interpretable deep learning architecture classifies successful/unsuccessful response briefs on temporally separated training and test sets. More accurate prediction remains challenging, likely due to the fact-specific, technical nature of patent cases and changes in applicable law and jurisprudence over time. 

   more » « less
5. IncDSI: Incrementally Updatable Document Retrieval

   Kishore, Varsha; Wan, Chao; Lovelace, Justin; Artzi, Yoav; Weinberger, Kilian Q. (July 2023, Proceedings of the 40th International Conference on Machine Learning)

   Krause, Andreas; Brunskill, Emma; Cho, Kyunghyun; Engelhardt, Barbara; Sabato, Sivan; Scarlett, Jonathan (Ed.)

   Differentiable Search Index is a recently proposed paradigm for document retrieval, that encodes information about a corpus of documents within the parameters of a neural network and directly maps queries to corresponding documents. These models have achieved state-of-the-art performances for document retrieval across many benchmarks. These kinds of models have a significant limitation: it is not easy to add new documents after a model is trained. We propose IncDSI, a method to add documents in real time (about 20-50ms per document), without retraining the model on the entire dataset (or even parts thereof). Instead we formulate the addition of documents as a constrained optimization problem that makes minimal changes to the network parameters. Although orders of magnitude faster, our approach is competitive with re-training the model on the whole dataset and enables the development of document retrieval systems that can be updated with new information in real-time. Our code for IncDSI is available at \href{https://github.com/varshakishore/IncDSI}{https://github.com/varshakishore/IncDSI}. 

   more » « less