We formalize the problem of retrieving daily deals in the context of Web search.We effectively combine keyword-based retrieval with automated classification.Our solution outperforms state-of-the-art query expansion and prior ad ranking work. Daily deals have emerged in the last three years as a successful form of online advertising. The downside of this success is that users are increasingly overloaded by the many thousands of deals offered each day by dozens of deal providers and aggregators. The challenge is thus offering the right deals to the right users i.e., the relevance ranking of deals. This is the problem we address in our paper. Exploiting the characteristics of deals data, we propose a combination of a term- and a concept-based retrieval model that closes the semantic gap between queries and documents expanding both of them with category information. The method consistently outperforms state-of-the-art methods based on term-matching alone and existing approaches for ad classification and ranking.

The LivingKnowledge project aimed to enhance the current state of the art in search, retrieval and knowledge management on the web by advancing the use of sentiment and opinion analysis within multimedia applications. To achieve this aim, a diverse set of novel and complementary analysis techniques have been integrated into a single, but extensible software platform on which such applications can be built. The platform combines state-of-the-art techniques for extracting facts, opinions and sentiment from multimedia documents, and unlike earlier platforms, it exploits both visual and textual techniques to support multimedia information retrieval. Foreseeing the usefulness of this software in the wider community, the platform has been made generally available as an open-source project. This paper describes the platform design, gives an overview of the analysis algorithms integrated into the system and describes two applications that utilise the system for multimedia information retrieval.

Nowadays, successful applications are those which contain features that captivate and engage users. Using an interactive news retrieval system as a use case, in this paper we study the effect of timeline and named-entity components on user engagement. This is in contrast with previous studies where the importance of these components were studied from a retrieval effectiveness point of view. Our experimental results show significant improvements in user engagement when named-entity and timeline components were installed. Further, we investigate if we can predict user-centred metrics through user's interaction with the system. Results show that we can successfully learn a model that predicts all dimensions of user engagement and whether users will like the system or not. These findings might steer systems that apply a more personalised user experience, tailored to the user's preferences.

This paper introduces TwitterPaul, a system designed to make use of Social Media data to help to predict game outcomes for the 2010 FIFA World Cup tournament. To this end, we extracted over 538K mentions to football games from a large sample of tweets that occurred during the World Cup, and we classified into different types with a precision of up to 88%. The different mentions were aggregated in order to make predictions about the outcomes of the actual games. We attempt to learn which Twitter users are accurate predictors and explore several techniques in order to exploit this information to make more accurate predictions. We compare our results to strong baselines and against the betting line (prediction market) and found that the quality of extractions is more important than the quantity, suggesting that high precision methods working on a medium-sized dataset are preferable over low precision methods that use a larger amount of data. Finally, by aggregating some classes of predictions, the system performance is close to the one of the betting line. Furthermore, we believe that this domain independent framework can help to predict other sports, elections, product release dates and other future events that people talk about in social media.

In this paper, we describe the work we are undertaking in producing a truly multimedia platform for the analysis of facts and opinions on the web. The system integrates the analysis of multimodal data (images, text and page layout) into a distributable platform that can be built upon for various applications. We give an overview of the natural language processing tools that have been developed for extracting facts and opinions from the textual content of articles, the image analysis techniques used to extract facts and to help support the opinions found in the contextually related written information, as well as other multimodal tools developed for the analysis of online articles. We describe two applications that have been developed as part of ongoing work of the Living Knowledge project: the News Media Analysis application for the semi-automation of the work of a media analysis company and the Future Predictor application which allows exploration of claims that are made through time.

Despite the great interest in di erent forms of textual annotation (named entity extraction, semantic tagging, syntactic and semantic parsing, etc.), there is still no consensus about which search tasks can be improved with such annotations, and what search algorithms are required to implement e cient engines to solve these tasks. We de ne formally two retrieval tasks in annotated collections: annotated retrieval and element retrieval. We discuss their di erences and describe e cient indexing structures, and how they can be implemented in Lucene and MG4J, two open source retrieval engines. Finally, we give a technical overview of two element retrieval use cases.

We estimate that nearly one third of news articles contain references to future events. While this information can prove crucial to understanding news stories and how events will develop for a given topic, there is currently no easy way to access this information. We propose a new task to address the problem of retrieving and ranking sentences that contain mentions to future events, which we call ranking related news predictions. In this paper, we formally define this task and propose a learning to rank approach based on 4 classes of features: term similarity, entity-based similarity, topic similarity, and temporal similarity. Through extensive evaluations using a corpus consisting of 1.8 millions news articles and 6,000 manually judged relevance pairs, we show that our approach is able to retrieve a significant number of relevant predictions related to a given topic.

Despite the great interest in di erent forms of textual annotation (named entity extraction, semantic tagging, syntactic and semantic parsing, etc.), there is still no consensus about which search tasks can be improved with such annotations, and what search algorithms are required to implement e cient engines to solve these tasks. We de ne formally two retrieval tasks in annotated collections: annotated retrieval and element retrieval. We discuss their di erences and describe e cient indexing structures, and how they can be implemented in Lucene and MG4J, two open source retrieval engines. Finally, we give a technical overview of two element retrieval use cases.

String matching plays an important role in biomedical Term Normalisation, the task of linking mentions of biomedical entities to identifiers in reference databases. This paper evaluates exact, rule-based and various string-similarity-based matching techniques. The matchers are compared in two ways: first, we measure precision and recall against a gold-standard dataset and second, we integrate the matchers into a curation tool and measure gains in curation speed when they were used to assist a curator in normalising protein and tissue entities. The evaluation shows that a rule-based matcher works better on the gold-standard data, while a string-similarity based system and exact string matcher win out on improving curation efficiency.

Although text mining shows considerable promise as a tool for supporting the curation of biomedical text, there is little concrete evidence as to its effectiveness. We report on three experiments measuring the extent to which curation can be speeded up with assistance from Natural Language Processing (NLP), together with subjective feedback from curators on the usability of a curation tool that integrates NLP hypotheses for protein-protein interactions (PPIs). In our curation scenario, we found that a maximum speed-up of 1/3 in curation time can be expected if NLP output is perfectly accurate. The preference of one curator for consistent NLP output and output with high recall needs to be confirmed in a larger study with several curators.

An important task in information extraction (IE) from biomedical articles is term identification (TI), which concerns linking entity mentions (e.g., terms denoting proteins) in text to unambiguous identifiers in standard databases (e.g., RefSeq). Previous work on TI has focused on species-specific documents. However, biomedical documents, especially full-length articles, often talk about entities across a number of species, in which case resolving species ambiguity becomes an indispensable part of ti. This paper describes our rule-based and machine-learning based approaches to species disambiguation and demonstrates that performance of TI can be improved by over 20% if the correct species are known. We also show that using the species predicted by the automatic species taggers can improve TI by a large margin.

Background: The tasks in BioCreative II were designed to approximate some of the laborious work involved in curating biomedical research papers. The approach to these tasks taken by the University of Edinburgh team was to adapt and extend the existing natural language processing (NLP) system that we have developed as part of a commercial curation assistant. Although this paper concentrates on using NLP to assist with curation, the system can be equally employed to extract types of information from the literature that is immediately relevant to biologists in general. Results: Our system was among the highest performing on the interaction subtasks, and competitive performance on the gene mention task was achieved with minimal development effort. For the gene normalization task, a string matching technique that can be quickly applied to new domains was shown to perform close to average. Conclusion: The technologies being developed were shown to be readily adapted to the BioCreative II tasks. Although high performance may be obtained on individual tasks such as gene mention recognition and normalization, and document classification, tasks in which a number of components must be combined, such as detection and normalization of interacting protein pairs, are still challenging for NLP systems.

BACKGROUND:Term identification is the task of grounding ambiguous mentions of biomedical named entities in text to unique database identifiers. Previous work on term identification has focused on studying species-specific documents. However, full-length articles often describe entities across a number of species, in which case resolving the ambiguity of model organisms in entities is critical to achieving accurate term identification.RESULTS:We developed and compared a number of rule-based and machine-learning based approaches to resolving species ambiguity in mentions of biomedical named entities, and demonstrated that a hybrid method achieved the best overall accuracy at 71.7%, as tested on the gold-standard ITI-TXM corpora. By utilising the species information predicted by the hybrid tagger, our rule-based term identification system was improved significantly by up to 11.6%.CONCLUSION:This paper shows that, in the context of identifying terms involving multiple model organisms, integration of an accurate species disambiguation system can significantly improve the performance of term identification systems.

Although text mining shows considerable promise as a tool for supporting the curation of biomedical text, there is little concrete evidence as to its effectiveness. We report on three experiments measuring the extent to which curation can be speeded up with assistance from Natural Language Processing ( NLP ), together with subjective feedback from curators on the usability of a curation tool that integrates NLP hypotheses for protein-protein interactions ( PPI s). In our curation scenario, we found that a maximum speed-up of 1/3 in curation time can be expected if NLP output is perfectly accurate. The preference of one curator for consistent NLP output and output with high recall needs to be confirmed in a larger study with several curators.

We introduce the first meta-service for information extraction in molecular biology, the BioCreative MetaServer (BCMS; http://bcms.bioinfo.cnio.es/). This prototype platform is a joint effort of 13 research groups and provides automatically generated annotations for PubMed/Medline abstracts. Annotation types cover gene names, gene IDs, species, and protein-protein interactions. The annotations are distributed by the meta-server in both human and machine readable formats (HTML/XML). This service is intended to be used by biomedical researchers and database annotators, and in biomedical language processing. The platform allows direct comparison, unified access, and result aggregation of the annotations.

There has been much recent interest in the extraction of PPIs (protein-protein interactions) from biomedical texts, but in order to assist with curation efforts, the PPIs must be enriched with further information of biological interest. This paper describes the implementation of a system to extract and enrich PPIs, developed and tested using an annotated corpus of biomedical texts, and employing both machine-learning and rule-based techniques.