Searching the web: The public and their queries

Spink, Amanda; Wolfram, Dietmar; Jansen, Major B. J.; Saračević, Tefko

doi:10.1002/1097-4571(2000)9999:9999<::aid-asi1591>3.3.co;2-i

Cited by 293 publications

(152 citation statements)

References 15 publications

Supporting

Mentioning

137

Contrasting

Unclassified

Order By: Relevance

“…This difference is evident from the average length, which is about 23 words per sentence on the English side for the gen sets, 17 for the med sets, and only slightly above 2 for the query sets -this is comparable to the observation that user queries to search engines usually consist of 2-3 words [81]. Detailed statistics of the individual data sets are provided in Table 3.…”

Section: Development and Test Datamentioning

confidence: 83%

“…Thus, we can assume a human input to a CLIR system will often be of this non-linguistic form. Although there are tasks where the expected queries may be longer (e.g., in patent retrieval, the query is the complete text of a patent proposal [97]), typical queries tend to be much shorter than a standard MT input [81].…”

Section: Optimizing Query Translation For Cross-lingual Information Rmentioning

confidence: 99%

See 1 more Smart Citation

Adaptation of machine translation for multilingual information retrieval in the medical domain

Pecina¹,

Dušek²,

Goeuriot³

et al. 2014

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

Objective. We investigate machine translation (MT) of user search queries in the context of cross-lingual information retrieval (IR) in the medical domain. The main focus is on techniques to adapt MT to increase translation quality; however, we also explore MT adaptation to improve effectiveness of cross-lingual IR.Methods and Data. Our MT system is Moses, a state-of-the-art phrase-based statistical machine translation system. The IR system is based on the BM25 retrieval model implemented in the Lucene search engine. The MT techniques employed in this work include in-domain training and tuning, intelligent training data selection, optimization of phrase table configuration, compound splitting, and exploiting synonyms as translation variants. The IR methods include morphological normalization and using multiple translation variants for query expansion. The experiments are performed and thoroughly evaluated on three language pairs: Czech-English, German-English, and French-English. MT quality is evaluated on data sets created within the Khresmoi project and IR effectiveness is tested on the CLEF eHealth 2013 data sets.Results. The search query translation results achieved in our experiments are outstanding -our systems outperform not only our strong baselines, but also Google Translate and Microsoft Bing Translator in direct comparison carried out on all the language pairs. The baseline BLEU scores increased from 26.59 to 41.45 for Czech-English, from 23.03 to 40.82 for German-English, and from 32.67 to 40.82 for French-English. This is a 55% improvement on average. In terms of the IR performance on this particular test collection, a significant improvement over the baseline is achieved only for French-English. For Czech-English and German-English, the increased MT quality does not lead to better IR results.Conclusions. Most of the MT techniques employed in our experiments improve MT of medical search queries. Especially the intelligent training data selection proves to be very successful for domain adaptation of MT. Certain improvements are also obtained from German compound splitting on the source language side. Translation quality, however, does not appear to correlate with the IR performance -better translation does not necessarily yield better retrieval. We discuss in detail the contribution of the individual techniques and state-of-the-art features and provide future research directions.

show abstract

Section: Development and Test Datamentioning

confidence: 83%

Section: Optimizing Query Translation For Cross-lingual Information Rmentioning

confidence: 99%

Adaptation of machine translation for multilingual information retrieval in the medical domain

Pecina¹,

Dušek²,

Goeuriot³

et al. 2014

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

show abstract

“…There have been numerous studies on the abilities of people to craft queries and evaluate search results based solely on search engine logs [13,31]. For visual Web search interfaces, it is vitally important to not just log the queries, but also to log how the interactive visual features of the system are being used [37].…”

Section: Instrumentation and Log Analysismentioning

confidence: 99%

User Evaluation Methods for Visual Web Search Interfaces

Hoeber

2009

2009 13th International Conference Information Visualisation

View full text Add to dashboard Cite

In recent years, numerous visual Web search interfaces have been developed in the research community. However, the user evaluations of these interfaces have been performed using a wide range of methods, making it difficult to compare and verify the relative value of the proposed advancements. In this paper, we survey these evaluation methods, and propose a stepped evaluation and refinement model for the systematic study and enhancement of visual Web search interfaces. We suggest that this stepped model can be generalized to support the evaluation of other information visualization systems that target exploratory or knowledge-centric domains.

show abstract

“…First, the gap manifests itself when the untrained user tries to use an existing, usually graph-based, ontology editing tool [14,12] -the editing disconnection. Second, it can be found in the disconnection between a user's information needs and the query (language) with which the user tries to find the required information in an ontology [28,27,9] the querying disconnection. Since editing and querying are two of the major interaction modes with the Semantic Web, bridging them is central to its practical use by end users.…”

Section: Introductionmentioning

confidence: 99%

GINO – A Guided Input Natural Language Ontology Editor

Bernstein

Kaufmann

2006

Lecture Notes in Computer Science

128

View full text Add to dashboard Cite

Abstract. The casual user is typically overwhelmed by the formal logic of the Semantic Web. The gap between the end user and the logic-based scaffolding has to be bridged if the Semantic Web's capabilities are to be utilized by the general public. This paper proposes that controlled natural languages offer one way to bridge the gap. We introduce GINO, a guided input natural language ontology editor that allows users to edit and query ontologies in a language akin to English. It uses a small static grammar, which it dynamically extends with elements from the loaded ontologies. The usability evaluation shows that GINO is well-suited for novice users when editing ontologies. We believe that the use of guided entry overcomes the habitability problem, which adversely affects most natural language systems. Additionally, the approach's dynamic grammar generation allows for easy adaptation to new ontologies.

show abstract

Searching the web: The public and their queries

Cited by 293 publications

References 15 publications

Adaptation of machine translation for multilingual information retrieval in the medical domain

Adaptation of machine translation for multilingual information retrieval in the medical domain

User Evaluation Methods for Visual Web Search Interfaces

GINO – A Guided Input Natural Language Ontology Editor

Contact Info

Product

Resources

About