Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

"Information Extraction": models, code, and papers

Social Network Extraction Unsupervised

Feb 24, 2022
Mahyuddin K. M. Nasution, Rahmad Syah

In the era of information technology, the two developing sides are data science and artificial intelligence. In terms of scientific data, one of the tasks is the extraction of social networks from information sources that have the nature of big data. Meanwhile, in terms of artificial intelligence, the presence of contradictory methods has an impact on knowledge. This article describes an unsupervised as a stream of methods for extracting social networks from information sources. There are a variety of possible approaches and strategies to superficial methods as a starting concept. Each method has its advantages, but in general, it contributes to the integration of each other, namely simplifying, enriching, and emphasizing the results.

* Turkish Journal of Computer and Mathematics Education Vol.12 No.3(2021), 4443-4449 
* 7 

Data-Efficient Information Extraction from Form-Like Documents

Jan 07, 2022
Beliz Gunel, Navneet Potti, Sandeep Tata, James B. Wendt, Marc Najork, Jing Xie

Automating information extraction from form-like documents at scale is a pressing need due to its potential impact on automating business workflows across many industries like financial services, insurance, and healthcare. The key challenge is that form-like documents in these business workflows can be laid out in virtually infinitely many ways; hence, a good solution to this problem should generalize to documents with unseen layouts and languages. A solution to this problem requires a holistic understanding of both the textual segments and the visual cues within a document, which is non-trivial. While the natural language processing and computer vision communities are starting to tackle this problem, there has not been much focus on (1) data-efficiency, and (2) ability to generalize across different document types and languages. In this paper, we show that when we have only a small number of labeled documents for training (~50), a straightforward transfer learning approach from a considerably structurally-different larger labeled corpus yields up to a 27 F1 point improvement over simply training on the small corpus in the target domain. We improve on this with a simple multi-domain transfer learning approach, that is currently in production use, and show that this yields up to a further 8 F1 point improvement. We make the case that data efficiency is critical to enable information extraction systems to scale to handle hundreds of different document-types, and learning good representations is critical to accomplishing this.

* Published at the 2nd Document Intelligence Workshop @ KDD 2021 (

A new keyphrases extraction method based on suffix tree data structure for arabic documents clustering

Jan 22, 2014
Issam Sahmoudi, Hanane Froud, Abdelmonaime Lachkar

Document Clustering is a branch of a larger area of scientific study known as data mining .which is an unsupervised classification using to find a structure in a collection of unlabeled data. The useful information in the documents can be accompanied by a large amount of noise words when using Full Text Representation, and therefore will affect negatively the result of the clustering process. So it is with great need to eliminate the noise words and keeping just the useful information in order to enhance the quality of the clustering results. This problem occurs with different degree for any language such as English, European, Hindi, Chinese, and Arabic Language. To overcome this problem, in this paper, we propose a new and efficient Keyphrases extraction method based on the Suffix Tree data structure (KpST), the extracted Keyphrases are then used in the clustering process instead of Full Text Representation. The proposed method for Keyphrases extraction is language independent and therefore it may be applied to any language. In this investigation, we are interested to deal with the Arabic language which is one of the most complex languages. To evaluate our method, we conduct an experimental study on Arabic Documents using the most popular Clustering approach of Hierarchical algorithms: Agglomerative Hierarchical algorithm with seven linkage techniques and a variety of distance functions and similarity measures to perform Arabic Document Clustering task. The obtained results show that our method for extracting Keyphrases increases the quality of the clustering results. We propose also to study the effect of using the stemming for the testing dataset to cluster it with the same documents clustering techniques and similarity/distance measures.

* International Journal of Database Management Systems ( IJDMS ) Vol.5, No.6, December 2013 
* 17 pages, 3 figures 

Automated Attack Synthesis by Extracting Finite State Machines from Protocol Specification Documents

Feb 18, 2022
Maria Leonor Pacheco, Max von Hippel, Ben Weintraub, Dan Goldwasser, Cristina Nita-Rotaru

Automated attack discovery techniques, such as attacker synthesis or model-based fuzzing, provide powerful ways to ensure network protocols operate correctly and securely. Such techniques, in general, require a formal representation of the protocol, often in the form of a finite state machine (FSM). Unfortunately, many protocols are only described in English prose, and implementing even a simple network protocol as an FSM is time-consuming and prone to subtle logical errors. Automatically extracting protocol FSMs from documentation can significantly contribute to increased use of these techniques and result in more robust and secure protocol implementations. In this work we focus on attacker synthesis as a representative technique for protocol security, and on RFCs as a representative format for protocol prose description. Unlike other works that rely on rule-based approaches or use off-the-shelf NLP tools directly, we suggest a data-driven approach for extracting FSMs from RFC documents. Specifically, we use a hybrid approach consisting of three key steps: (1) large-scale word-representation learning for technical language, (2) focused zero-shot learning for mapping protocol text to a protocol-independent information language, and (3) rule-based mapping from protocol-independent information to a specific protocol FSM. We show the generalizability of our FSM extraction by using the RFCs for six different protocols: BGPv4, DCCP, LTP, PPTP, SCTP and TCP. We demonstrate how automated extraction of an FSM from an RFC can be applied to the synthesis of attacks, with TCP and DCCP as case-studies. Our approach shows that it is possible to automate attacker synthesis against protocols by using textual specifications such as RFCs.

* To appear in IEEE Security and Privacy, 2022 

Bench-Marking Information Extraction in Semi-Structured Historical Handwritten Records

Jul 17, 2018
Animesh Prasad, Hervé Déjean, Jean-Luc Meunier, Max Weidemann, Johannes Michael, Gundram Leifert

In this report, we present our findings from benchmarking experiments for information extraction on historical handwritten marriage records Esposalles from IEHHR - ICDAR 2017 robust reading competition. The information extraction is modeled as semantic labeling of the sequence across 2 set of labels. This can be achieved by sequentially or jointly applying handwritten text recognition (HTR) and named entity recognition (NER). We deploy a pipeline approach where first we use state-of-the-art HTR and use its output as input for NER. We show that given low resource setup and simple structure of the records, high performance of HTR ensures overall high performance. We explore the various configurations of conditional random fields and neural networks to benchmark NER on given certain noisy input. The best model on 10-fold cross-validation as well as blind test data uses n-gram features with bidirectional long short-term memory.


Vietnamese Open Information Extraction

Jan 23, 2018
Diem Truong, Duc-Thuan Vo, U. T Nguyen

Open information extraction (OIE) is the process to extract relations and their arguments automatically from textual documents without the need to restrict the search to predefined relations. In recent years, several OIE systems for the English language have been created but there is not any system for the Vietnamese language. In this paper, we propose a method of OIE for Vietnamese using a clause-based approach. Accordingly, we exploit Vietnamese dependency parsing using grammar clauses that strives to consider all possible relations in a sentence. The corresponding clause types are identified by their propositions as extractable relations based on their grammatical functions of constituents. As a result, our system is the first OIE system named vnOIE for the Vietnamese language that can generate open relations and their arguments from Vietnamese text with highly scalable extraction while being domain independent. Experimental results show that our OIE system achieves promising results with a precision of 83.71%.


End-to-End Information Extraction without Token-Level Supervision

Jul 16, 2017
Rasmus Berg Palm, Dirk Hovy, Florian Laws, Ole Winther

Most state-of-the-art information extraction approaches rely on token-level labels to find the areas of interest in text. Unfortunately, these labels are time-consuming and costly to create, and consequently, not available for many real-life IE tasks. To make matters worse, token-level labels are usually not the desired output, but just an intermediary step. End-to-end (E2E) models, which take raw text as input and produce the desired output directly, need not depend on token-level labels. We propose an E2E model based on pointer networks, which can be trained directly on pairs of raw input and output text. We evaluate our model on the ATIS data set, MIT restaurant corpus and the MIT movie corpus and compare to neural baselines that do use token-level labels. We achieve competitive results, within a few percentage points of the baselines, showing the feasibility of E2E information extraction without the need for token-level labels. This opens up new possibilities, as for many tasks currently addressed by human extractors, raw input and output data are available, but not token-level labels.

* @ EMNLP 2017 

pdfPapers: shell-script utilities for frequency-based multi-word phrase extraction from PDF documents

Jan 26, 2021
Pavel Loskot

Biomedical research is intensive in processing information in the previously published papers. This motivated a lot of efforts to provide tools for text mining and information extraction from PDF documents over the past decade. The *nix (Unix/Linux) operating systems offer many tools for working with text files, however, very few such tools are available for processing the contents of PDF files. This paper reports our effort to develop shell script utilities for *nix systems with the core functionality focused on viewing and searching multiple PDF documents combining logical and regular expressions, and enabling more reliable text extraction from PDF documents with subsequent manipulation of the resulting blocks of text. Furthermore, a procedure for extracting the most frequently occurring multi-word phrases was devised and then demonstrated on several scientific papers in life sciences. Our experiments revealed that the procedure is surprisingly robust to deficiencies in text extraction and the actual scoring function used to rank the phrases in terms of their importance or relevance. The keyword relevance is strongly context dependent, the word stemming did not provide any recognizable advantage, and the stop-words should only be removed from the beginning and the end of phrases. In addition, the developed utilities were used to convert the list of acronyms and the index from a PDF e-book into a large list of biochemical terms which can be exploited in other text mining tasks. All shell scripts and data files are available in a public repository named \pp\ on the Github. The key lesson learned in this work is that semi-automated methods combining the power of algorithms with the capabilities of research experience are the most promising for improving the research efficiency.

* 23 pages, 4 figures, 10 tables 

MatchVIE: Exploiting Match Relevancy between Entities for Visual Information Extraction

Jun 24, 2021
Guozhi Tang, Lele Xie, Lianwen Jin, Jiapeng Wang, Jingdong Chen, Zhen Xu, Qianying Wang, Yaqiang Wu, Hui Li

Visual Information Extraction (VIE) task aims to extract key information from multifarious document images (e.g., invoices and purchase receipts). Most previous methods treat the VIE task simply as a sequence labeling problem or classification problem, which requires models to carefully identify each kind of semantics by introducing multimodal features, such as font, color, layout. But simply introducing multimodal features couldn't work well when faced with numeric semantic categories or some ambiguous texts. To address this issue, in this paper we propose a novel key-value matching model based on a graph neural network for VIE (MatchVIE). Through key-value matching based on relevancy evaluation, the proposed MatchVIE can bypass the recognitions to various semantics, and simply focuses on the strong relevancy between entities. Besides, we introduce a simple but effective operation, Num2Vec, to tackle the instability of encoded values, which helps model converge more smoothly. Comprehensive experiments demonstrate that the proposed MatchVIE can significantly outperform previous methods. Notably, to the best of our knowledge, MatchVIE may be the first attempt to tackle the VIE task by modeling the relevancy between keys and values and it is a good complement to the existing methods.

* accepted by IJCAI 2021 

Don't read, just look: Main content extraction from web pages using visually apparent features

Oct 27, 2021
Geunseong Jung, Sungjae Han, Hansung Kim, Jaehyuk Cha

The extraction of main content provides only primary informative blocks by removing a web page's minor areas like navigation menu, ads, and site templates. It has various applications: information retrieval, search engine optimization, and browser reader mode. We tested the existing four main content extraction methods (Firefox Readability.js, Chrome DOM Distiller, Web2Text, and Boilernet) in web pages datasets of two English datasets from the global websites and seven non-English datasets from seven local regions each. It shows that the performance decreases by up to 40% in non-English datasets over English datasets. This paper proposes a multilingual main content extraction method that uses visually apparent features such as the elements' positions, size, and distances from the centers of the browser window and the web document. These are based on the authors' intention: the elements' placement and appearance in web pages have constraints because of humans' narrow central vision. Hence, our method, Grid-Center-Expand (GCE), finds the closest leaf node to the centroid of the web page from which minor areas have been removed. For the main content, the leaf node repeatedly ascends to the parent node of the DOM tree until this node fits one of the following conditions: tag, containing specific attributes, or sudden width change. In the non-English datasets, our method performs better than up to 13% over Boilernet, especially 56% in the Japan dataset and 7% in the English dataset. Therefore, our method performs well regardless of the regional and linguistic characteristics of the web page. In addition, we create DNN models using Google's TabNet with GCE's features. The best of our models has similar performance to Boilernet and Web2text in all datasets. Accordingly, we show that these features can be useful to machine learning models for extracting main content.