2018/02/25 by Ahmad Pesaranghader, Pesaranghader, Ahmad, Ali Pesaranghader +5
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling
paper · pdf · doi:10.48550/arxiv.1802.09059
openalex publication_date 2018/02/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Due to recent technical and scientific advances, we have a wealth of\ninformation hidden in unstructured text data such as offline/online narratives,\nresearch articles, and clinical reports. To mine these data properly,\nattributable to their innate ambiguity, a Word Sense Disambiguation (WSD)\nalgorithm can avoid numbers of difficulties in Natural Language Processing\n(NLP) pipeline. However, considering a large number of ambiguous words in one\nlanguage or technical domain, we may encounter limiting constraints for proper\ndeployment of existing WSD models. This paper attempts to address the problem\nof one-classifier-per-one-word WSD algorithms by proposing a single\nBidirectional Long Short-Term Memory (BLSTM) network which by considering\nsenses and context sequences works on all ambiguous words collectively.\nEvaluated on SensEval-3 benchmark, we show the result of our model is\ncomparable with top-performing WSD algorithms. We also discuss how applying\nadditional modifications alleviates the model fault and the need for more\ntraining data.\n