A Hidden Markov Model Based System for Entity Extraction from Social\n Media English Text at FIRE 2015

2015/12/12 by Kamal Sarkar, Sarkar, Kamal · 1 citation
Computer Science · #Natural Language Processing Techniques #Topic Modeling #Web Data Mining and Analysis

paper · pdf · doi:10.48550/arxiv.1512.03950

Abstract

This paper presents the experiments carried out by us at Jadavpur University\nas part of the participation in FIRE 2015 task: Entity Extraction from Social\nMedia Text - Indian Languages (ESM-IL). The tool that we have developed for the\ntask is based on Trigram Hidden Markov Model that utilizes information like\ngazetteer list, POS tag and some other word level features to enhance the\nobservation probabilities of the known tokens as well as unknown tokens. We\nsubmitted runs for English only. A statistical HMM (Hidden Markov Models) based\nmodel has been used to implement our system. The system has been trained and\ntested on the datasets released for FIRE 2015 task: Entity Extraction from\nSocial Media Text - Indian Languages (ESM-IL). Our system is the best performer\nfor English language and it obtains precision, recall and F-measures of 61.96,\n39.46 and 48.21 respectively.\n

Cited by

• Named Entity Recognition Only from Word Embeddings

Related

• An HMM Based Named Entity Recognition System for Indian Languages: The JU System at ICON 2013
• Part-of-Speech Tagging for Code-mixed Indian Social Media Text at ICON\n 2015
• Hidden Markov Based Mathematical Model dedicated to Extract Ingredients from Recipe Text
• A Simple and Efficient Probabilistic Language model for Code-Mixed Text
• Natural Language Processing for Information Extraction