Anti-negation method for handling negation words in question answering system
- PDF / 2,804,680 Bytes
- 23 Pages / 439.37 x 666.142 pts Page_size
- 29 Downloads / 235 Views
Anti‑negation method for handling negation words in question answering system J. Felicia Lilian1 · K. Sundarakantham1 · S. Mercy Shalinie1 Accepted: 14 September 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The question answer (QA) system for a reading comprehension task tries to answer the question by retrieving the needed phrase from the given content. Precise answering is the key role of a QA system. An ambiguity is developed when we need to answer a negative question with a positive reply. The negation words change the polarity of the sentence, and hence, the scope of negation words is notable. This has paved the way for studying the role of ‘negation’ in the natural language processing (NLP) task. The handling of these words is considered a major part of our proposed methodology. In this paper, we propose an algorithm to retrieve and replace the negation words present in the content and query. A comparative study is done for performing word embedding over these words using various state-of-the-art methods. In earlier works when handling the negation the semantics of the sentences are changed. Hence, in this paper we try to maintain the semantics through our proposed methodology. The updated content is embedded into the bi-directional long short-term memory (Bi-LSTM) and thus makes the retrieving of an answer for a question answer system easier. The proposed work has been carried over the Stanford Negation, and the SQuAD dataset with a higher precision value of 96.2% has been achieved in retrieving the answers that are given in the dataset. Keywords Question answer system · Natural language processing · Negation handling · Bidirectional long short-term memory
1 Introduction Natural language processing (NLP) has bound with huge topic variations from computation processing to language understanding. The invention of deep learning algorithms has made the task of NLP easier [1, 2]. Building a high computation algorithm in NLP is used to analyze and represent the human language automatically * J. Felicia Lilian [email protected] 1
Thiagarajar College of Engineering, Madurai, India
13
Vol.:(0123456789)
J. F. Lilian et al.
[3]. Conversations generally need a lot of background knowledge about the topic [4]. When we render our focus toward the background knowledge, the main drawback we come across is the understanding of the language. Retrieval of the exact phrase or sentence as a response to the conversation is the main part of work in NLP. The conversations between the human and a machine are based either on an open domain or a closed domain. The open domain applications need an efficient heuristic combinatorial algorithms to process [5], whereas closed domain can be well performed through rules/artificial intelligence (AI) algorithms. Natural language understanding (NLU) as a subset of NLP focused on developing many AI-dependent applications [6]. The progress of this finds its use in many NLP applications such as Reading Comprehension, Text Summarization, Machi
Data Loading...
