TY - JOUR
T1 - MKPM
T2 - Multi keyword-pair matching for natural language sentences
AU - Lu, Xin
AU - Deng, Yao
AU - Sun, Ting
AU - Gao, Yi
AU - Feng, Jun
AU - Sun, Xia
AU - Sutcliffe, Richard
N1 - Publisher Copyright:
© 2021, The Author(s).
PY - 2022/1
Y1 - 2022/1
N2 - Sentence matching is widely used in various natural language tasks, such as natural language inference, paraphrase identification and question answering. For these tasks, we need to understand the logical and semantic relationship between two sentences. Most current methods use all information within a sentence to build a model and hence determine its relationship to another sentence. However, the information contained in some sentences may cause redundancy or introduce noise, impeding the performance of the model. Therefore, we propose a sentence matching method based on multi keyword-pair matching (MKPM), which uses keyword pairs in two sentences to represent the semantic relationship between them, avoiding the interference of redundancy and noise. Specifically, we first propose a sentence-pair-based attention mechanism sp-attention to select the most important word pair from the two sentences as a keyword pair, and then propose a Bi-task architecture to model the semantic information of these keyword pairs. The Bi-task architecture is as follows: 1. In order to understand the semantic relationship at the word level between two sentences, we design a word-pair task (WP-Task), which uses these keyword pairs to complete sentence matching independently. 2. We design a sentence-pair task (SP-Task) to understand the sentence level semantic relationship between the two sentences by sentence denoising. Through the integration of the two tasks, our model can understand sentences more accurately from the two granularities of word and sentence. Experimental results show that our model can achieve state-of-the-art performance in several tasks. Our source code is publicly available1.
AB - Sentence matching is widely used in various natural language tasks, such as natural language inference, paraphrase identification and question answering. For these tasks, we need to understand the logical and semantic relationship between two sentences. Most current methods use all information within a sentence to build a model and hence determine its relationship to another sentence. However, the information contained in some sentences may cause redundancy or introduce noise, impeding the performance of the model. Therefore, we propose a sentence matching method based on multi keyword-pair matching (MKPM), which uses keyword pairs in two sentences to represent the semantic relationship between them, avoiding the interference of redundancy and noise. Specifically, we first propose a sentence-pair-based attention mechanism sp-attention to select the most important word pair from the two sentences as a keyword pair, and then propose a Bi-task architecture to model the semantic information of these keyword pairs. The Bi-task architecture is as follows: 1. In order to understand the semantic relationship at the word level between two sentences, we design a word-pair task (WP-Task), which uses these keyword pairs to complete sentence matching independently. 2. We design a sentence-pair task (SP-Task) to understand the sentence level semantic relationship between the two sentences by sentence denoising. Through the integration of the two tasks, our model can understand sentences more accurately from the two granularities of word and sentence. Experimental results show that our model can achieve state-of-the-art performance in several tasks. Our source code is publicly available1.
KW - Bi-task architecture
KW - Multi keyword-pair
KW - Sentence matching
UR - http://www.scopus.com/inward/record.url?scp=85107287596&partnerID=8YFLogxK
U2 - 10.1007/s10489-021-02306-5
DO - 10.1007/s10489-021-02306-5
M3 - Article
AN - SCOPUS:85107287596
SN - 0924-669X
VL - 52
SP - 1878
EP - 1892
JO - Applied Intelligence
JF - Applied Intelligence
IS - 2
ER -