The peer-reviewed conference track at FIRE 2015 is a maiden endeavour targeted primarily towards the growing IR/NLP community in India. Its scope has significant overlap with that of ACM SIGIR. The quality of a conference is determined by the quality of its peer-review process. We have thus been very fortunate in that many researchers who regularly serve on the SIGIR Program Committee consented to review papers for this track. We would like to take this opportunity to thank all the reviewers for submitting reviews on time despite their very busy schedule. We hope that the authors found the reviews constructive and helpful.
Proceeding Downloads
Context-driven Dimensionality Reduction for Clustering Text Documents
We investigate clustering documents based on automatically annotated potentially sensitive information extracted from a large collection of organizational data. The process of clustering in this particular use case is helpful to visualize and navigate ...
Document Retrieval Metrics for Program Understanding
The need for domain knowledge representation for program comprehension is now widely accepted in the program comprehension community. The so-called "concept assignment problem" represents the challenge to locate domain concepts in the source code of ...
Automatic Identification of Conceptual Structures using Deep Boltzmann Machines
This paper presents an approach to automatically extract Conceptual Graphs (CGs) from patent documents using Over-Replicated Softmax model of Deep Boltzman Machines (DBMs). The main challenge in the extraction of conceptual graphs from the natural ...
OnForumS: The Shared Task on Online Forum Summarisation at MultiLing'15
In this paper we present the Online Forum Summarisation (OnForumS) pilot task at MultiLing'15. OnForumS is a pioneering attempt at encompassing automatic summarisation, argumentation mining and sentiment analysis into one shared task and at bringing ...
An Empirical Comparison of Statistical Term Association Graphs with DBpedia and ConceptNet for Query Expansion
Term graphs constructed from document collections as well as external resources, such as encyclopedias (DBpedia) and knowledge bases (ConceptNet), can be used as sources of semantically related terms for query expansion. Although these resources ...
HBE: Hashtag-Based Emotion Lexicons for Twitter Sentiment Analysis
In this paper we report the first effort of constructing emotion lexicon by utilizing Twitter as source of data. Specifically we used hashtag feature to obtain tweets with certain emotion label in English. There are eight emotion classes used in our ...
Construction of a Semi-Automated model for FAQ Retrieval via Short Message Service
Mobile phones, currently, are one of the most extensive medium for the communication of any kind of information to the general public. Being one of the fastest spreading technologies, even to the remotest of areas, this highly sought after contemporary ...
word2vec or JoBimText?: A Comparison for Lexical Expansion of Hindi Words
Exploration of distributional semantics for NLP tasks in Indian languages has been scarce. This work carries out a comparative analysis of two recent and high performing distributional semantics techniques namely word2vec and JoBimText. The task of ...
A Comparative Study on Different Translation Approaches for Query Formation in the Source Retrieval Task
The text reuse detection among documents in comparable corpora has become an important research topic due to its usages ranging from document linking to plagiarism detection. A text reuse detection system typically computes similarity between source ...
MESS: A Multilingual Error based String Similarity measure for transliterated name variants
Cross-lingual name matching is an important problem in the fields of machine translation and data mining. Though well studied, it lacks a generic solution largely due to issues like language specific nuances, resource scarcity, etc. Most of the proposed ...