arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1607.08883cs.IRcs.CL
收藏

基于条件随机场的查询词标注

Labeling of Query Words using Conditional Random Field

West Bengal University of Technology(西孟加拉理工大学);Jadavpur University(贾达普大学)

Satanu Ghosh, Souvick Ghosh, Dipankar Das

摘要:

本文介绍了我们的方法查询词标注作为一种尝试,在混合脚本信息检索在论坛信息检索评估(FIRE)2015年的共享任务。查询是用罗马字母写的,单词是英语或从印度地方语言音译而来。除英语外,共有八种印度语言。我们还确定了命名实体和特殊符号作为我们任务的一部分。基于CRF的机器学习框架用于用其对应的语言标签来标记各个词。我们使用基于词典的方法进行语言识别。我们在识别语言时还考虑了单词的上下文。我们的系统表现出75.5%的整体准确率为令牌级语言识别。孟加拉语、英语和印地语的符号级语言标签识别的严格F度量分数分别为0.7486、0.892和0.7972。我们的系统的总体加权F度量为0.7498。

英文摘要:

This paper describes our approach on Query Word Labeling as an attempt in the shared task on Mixed Script Information Retrieval at Forum for Information Retrieval Evaluation (FIRE) 2015. The query is written in Roman script and the words were in English or transliterated from Indian regional languages. A total of eight Indian languages were present in addition to English. We also identified the Named Entities and special symbols as part of our task. A CRF based machine learning framework was used for labeling the individual words with their corresponding language labels. We used a dictionary based approach for language identification. We also took into account the context of the word while identifying the language. Our system demonstrated an overall accuracy of 75.5% for token level language identification. The strict F-measure scores for the identification of token level language labels for Bengali, English and Hindi are 0.7486, 0.892 and 0.7972 respectively. The overall weighted F-measure of our system was 0.7498.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑