Syed Toufeeq Ahmed

IntEx: A Syntactic Role Driven Protein-Protein Interaction Extractor for Bio-Medical Text

In this paper, we present a fully automated extraction system, named IntEx, to identify gene and protein interactions in biomedical text. Our approach is based on first splitting complex sentences into simple clausal structures made up of syntactic roles. Then, tagging biological entities with the help of biomedical and linguistic ontologies. Finally, extracting complete interactions by analyzing the matching contents of syntactic roles and their linguistically significant combinations. Our extraction system handles complex sentences and extracts multiple and nested interactions specified in a sentence. Experimental evaluations with two other state of the art extraction systems indicate that the IntEx system achieves better performance without the labor intensive pattern engineering requirement.

Boosting Item Keyword Search with Spreading Activation

Most keyword search engines return directly matching keyword phrases. However, publishers cannot anticipate all possible ways in which users would search for the items in their documents. In fact, many times, there may be no direct keyword match between a keyword search phrase and descriptions of relevant items that are perfect matches for the search. We present an automated, high precision-based information retrieval solution to boost item find-ability by bridging the semantic gap between item information and popular keyword search phrases. Our solution achieves an average of 80% F-measure for various boosted matches for keyword search phrases in various categories.

Analyzing Sentiment Markers Describing Radical and Counter-Radical Elements in Online News

In this study, we aim to obtain “natural groupings” of 151 local non-government organizations and institutions mentioned in a news archive of 77,000 articles spanning a decade (May 1999 to Jan 2010) from Indonesia. One of our goals is to enhance our understanding of counter-radical movements in critical locations in the Muslim world. We present information extraction techniques to recognize entities, and their beliefs and practices in text as a step towards identifying socially significant scales with explanatory power. Then, we proceed to cluster organizations based on these scales. We present experimental results, and discuss challenges in reasoning with the complex interactions of many simultaneous beliefs, practices and attitudes held by the leaders and followers of various organizations.

BioEve: Bio-Molecular Event Extraction from Text Using Semantic Classification and Dependency Parsing

In this paper, we present BioEve a fully automated event extraction system for bio-medical text. It first semantically classifies each sentence to the class type of the event mentioned in the sentence, and then using high coverage hand-crafted rules, it extracts the participants of that event. We participated in Task 1 of BioNLP 2009 Shared task, and the final evaluation results are described here. Our experimentation with different approaches to classify a sentence to bio-interaction classes are also shared.

Tracking terrorism news threads by extracting event signatures

With the humongous amount of news stories published daily and the range of ways (RSS feeds, blogs etc) to disseminate them, even an expert at tracking new developing stories can feel the information overload. At most times, when a user is reading a news story, she would like to know “what happened before this?“ or “how things progressed after this incident?”. In this paper, we present a novel real-time yet simple method to detect and track new events related to violence and terrorism in news streams through their life over a time line. We do this by first extracting signature of the event, at microscopic level rather than topic or macroscopic level, and then tracking and linking this event with mentions of same event signature in other incoming news articles. There by forming a thread that links all the news articles that describe this specific event, with no training data used or machine learning algorithms employed. We also present our experimental evaluations conducted with Document Understand Conference (DUC) datasets that validate our observations and methodology.

Topic development pattern analysis-based adaptation of information spaces

While navigation within complex information spaces is a challenge for all users, the problem is most evident with individuals who are blind or visually impaired. A particular challenge faced by students who are blind when accessing documents in digital libraries is that long documents are almost impenetrable for these users who cannot skim through large documents effectively and who cannot visually organize and re-organize documents for later use in new contexts. We highlight that adaptation and personalization of textual media can be possible only through novel algorithms that can segment media content to its basic information units and enable users to pick, recombine, and re-organize these units into new personalized documents. This is a multi-faceted problem that requires research into technical challenges from user modeling to context analysis. In this paper, we focus on two specific challenges key to the adaptation of textual media: content-segmentation and content-reorganization. In particular, we show that topic development analysis is fundamental in supporting both of these tasks. The algorithms proposed in this paper analyze topic development patterns without having to distill the specific topics, thereby keeping the overall analysis and adaptation processes light weight.

BioEve search: A novel framework to facilitate interactive literature search

Background. Recent advances in computational and biological methods in last two decades have remarkably changed the scale of biomedical research and with it began the unprecedented growth in both the production of biomedical data and amount of published literature discussing it. An automated extraction system coupled with a cognitive search and navigation service over these document collections would not only save time and effort, but also pave the way to discover hitherto unknown information implicitly conveyed in the texts. Results. We developed a novel framework (named “BioEve”) that seamlessly integrates Faceted Search (Information Retrieval) with Information Extraction module to provide an interactive search experience for the researchers in life sciences. It enables guided step-by-step search query refinement, by suggesting concepts and entities (like genes, drugs, and diseases) to quickly filter and modify search direction, and thereby facilitating an enriched paradigm where user can discover related concepts and keywords to search while information seeking. Conclusions. The BioEve Search framework makes it easier to enable scalable interactive search over large collection of textual articles and to discover knowledge hidden in thousands of biomedical literature articles with ease.

Semantic classification and dependency parsing enabled automated bio-molecular event extraction from text

The last two decades of invigorating research in the area of human genome sequencing marked the beginning of large-scale data collection. Much of the valuable knowledge gained is found in published articles, and thus in un-structured textual form. To aid in searching and extracting knowledge from textual sources, we present BioEve, a fully automated system to extract bio-molecular events from Medline abstracts. BioEve first semantically classifies each sentence to the class type of the event mentioned in the sentence, and then using high coverage, class-specific, hand-crafted rules, it extracts the participants of that event. An online version of BioEve is available at http://bioeve.org/.

Extracting Protein-Protein Interactions from MEDLINE Using Syntactic Roles

With rapid growth in genomics research in last decade, amount of information a biomedical researcher has to keep track of and understand has increased tremendously. We present a fully automated information extraction system to aid these researchers to identify and locate gene and protein interactions in biomedical text. Our extraction system handles complex sentences and extracts multiple and nested interactions specified in these sentences. Experimental evaluations with two other state of the art extraction systems indicate that the IntEx system achieves better performance without the labor intensive pattern engineering requirement.

DataRover: An Automated System for Extracting Product Information From Online Catalogs

The increasing number of e-commerce Web sites on the Web introduces numerous challenges in organizing and searching the product information across multiple Web sites. This problem is further exacerbated by various presentation templates that different Web sites use in presenting their product information, and different ways of product information they store in their catalogs. This paper describes the DataRover system, which can automatically crawl and extract all products from online catalogs. DataRover is based on pattern mining algorithms and domain specific heuristics which utilize the navigational and presentation regularities to identify taxonomy, list-of-product and single-product segments within an online catalog. Next, it uses the inferred patterns to extract data from all such data segments and to automatically transform an online catalog into a database of categorized products. We also provide experimental results to demonstrate the efficacy of the DataRover.