
Chinese medical knowledge-based question answering (cMed-KBQA) is a vital component of the intelligence question-answering assignment. Its purpose is to enable the model to comprehend questions and then deduce the proper answer from the knowledge base. Previous methods solely considered how questions and knowledge base paths were represented, disregarding their significance. Due to entity and path sparsity, the performance of question and answer cannot be effectively enhanced. To address this challenge, this paper presents a structured methodology for the cMed-KBQA based on the cognitive science dual systems theory by synchronizing an observation stage (System 1) and an expressive reasoning stage (System 2). System 1 learns the question's representation and queries the associated simple path. Then System 2 retrieves complicated paths for the question from the knowledge base by using the simple path provided by System 1. Specifically, System 1 is implemented by the entity extraction module, entity linking module, simple path retrieval module, and simple path-matching model. Meanwhile, System 2 is performed by using the complex path retrieval module and complex path-matching model. The public CKBQA2019 and CKBQA2020 datasets were extensively studied to evaluate the suggested technique. Using the metric average F1-score, our model achieved 78.12% on CKBQA2019 and 86.60% on CKBQA2020.
Citation: Meiling Wang, Xiaohai He, Zhao Zhang, Luping Liu, Linbo Qing, Yan Liu. Dual-process system based on mixed semantic fusion for Chinese medical knowledge-based question answering[J]. Mathematical Biosciences and Engineering, 2023, 20(3): 4912-4939. doi: 10.3934/mbe.2023228
[1] | Pshtiwan Othman Mohammed, Hari Mohan Srivastava, Sarkhel Akbar Mahmood, Kamsing Nonlaopon, Khadijah M. Abualnaja, Y. S. Hamed . Positivity and monotonicity results for discrete fractional operators involving the exponential kernel. Mathematical Biosciences and Engineering, 2022, 19(5): 5120-5133. doi: 10.3934/mbe.2022239 |
[2] | Pshtiwan Othman Mohammed, Christopher S. Goodrich, Aram Bahroz Brzo, Dumitru Baleanu, Yasser S. Hamed . New classifications of monotonicity investigation for discrete operators with Mittag-Leffler kernel. Mathematical Biosciences and Engineering, 2022, 19(4): 4062-4074. doi: 10.3934/mbe.2022186 |
[3] | Maysaa Al Qurashi, Saima Rashid, Sobia Sultana, Hijaz Ahmad, Khaled A. Gepreel . New formulation for discrete dynamical type inequalities via h-discrete fractional operator pertaining to nonsingular kernel. Mathematical Biosciences and Engineering, 2021, 18(2): 1794-1812. doi: 10.3934/mbe.2021093 |
[4] | M. Botros, E. A. A. Ziada, I. L. EL-Kalla . Semi-analytic solutions of nonlinear multidimensional fractional differential equations. Mathematical Biosciences and Engineering, 2022, 19(12): 13306-13320. doi: 10.3934/mbe.2022623 |
[5] | Jian Huang, Zhongdi Cen, Aimin Xu . An efficient numerical method for a time-fractional telegraph equation. Mathematical Biosciences and Engineering, 2022, 19(5): 4672-4689. doi: 10.3934/mbe.2022217 |
[6] | Tahir Khan, Roman Ullah, Gul Zaman, Jehad Alzabut . A mathematical model for the dynamics of SARS-CoV-2 virus using the Caputo-Fabrizio operator. Mathematical Biosciences and Engineering, 2021, 18(5): 6095-6116. doi: 10.3934/mbe.2021305 |
[7] | Ritu Agarwal, Pooja Airan, Mohammad Sajid . Numerical and graphical simulation of the non-linear fractional dynamical system of bone mineralization. Mathematical Biosciences and Engineering, 2024, 21(4): 5138-5163. doi: 10.3934/mbe.2024227 |
[8] | Noura Laksaci, Ahmed Boudaoui, Seham Mahyoub Al-Mekhlafi, Abdon Atangana . Mathematical analysis and numerical simulation for fractal-fractional cancer model. Mathematical Biosciences and Engineering, 2023, 20(10): 18083-18103. doi: 10.3934/mbe.2023803 |
[9] | H. M. Srivastava, Khaled M. Saad, J. F. Gómez-Aguilar, Abdulrhman A. Almadiy . Some new mathematical models of the fractional-order system of human immune against IAV infection. Mathematical Biosciences and Engineering, 2020, 17(5): 4942-4969. doi: 10.3934/mbe.2020268 |
[10] | Debao Yan . Existence results of fractional differential equations with nonlocal double-integral boundary conditions. Mathematical Biosciences and Engineering, 2023, 20(3): 4437-4454. doi: 10.3934/mbe.2023206 |
Chinese medical knowledge-based question answering (cMed-KBQA) is a vital component of the intelligence question-answering assignment. Its purpose is to enable the model to comprehend questions and then deduce the proper answer from the knowledge base. Previous methods solely considered how questions and knowledge base paths were represented, disregarding their significance. Due to entity and path sparsity, the performance of question and answer cannot be effectively enhanced. To address this challenge, this paper presents a structured methodology for the cMed-KBQA based on the cognitive science dual systems theory by synchronizing an observation stage (System 1) and an expressive reasoning stage (System 2). System 1 learns the question's representation and queries the associated simple path. Then System 2 retrieves complicated paths for the question from the knowledge base by using the simple path provided by System 1. Specifically, System 1 is implemented by the entity extraction module, entity linking module, simple path retrieval module, and simple path-matching model. Meanwhile, System 2 is performed by using the complex path retrieval module and complex path-matching model. The public CKBQA2019 and CKBQA2020 datasets were extensively studied to evaluate the suggested technique. Using the metric average F1-score, our model achieved 78.12% on CKBQA2019 and 86.60% on CKBQA2020.
The construction of discrete fractional sums and differences from the knowledge of samples of their corresponding continuous integrals and derivatives arises in the context of discrete fractional calculus; see [1,2,3,4,5,6] for more details. Recently, discrete fractional operators with more general forms of their kernels and properties have gathered attention in both areas of physics and mathematics; see [7,8,9,10].
In discrete fractional calculus theory, we say that F is monotonically increasing at a time step t if the nabla of F is non-negative, i.e., (∇F)(t):=F(t)−F(t−1)≥0 for each t in the time scale set Nc0+1:={c0+1,c0+2,…}. Moreover, the function F is θ−monotonically increasing (or decreasing) on Nc0 if F(t+1)>θF(t)(orF(t+1)<θF(t)) for each t∈Na). In [11,12] the authors considered 1−monotonicity analysis for standard discrete Riemann-Liouville fractional differences defined on N0 and in [13] the authors generalized the above by introducing θ−monotonicity increasing and decreasing functions and then obtained some θ−monotonicity analysis results for discrete Riemann-Liouville fractional differences defined on N0. In [14,15,16], the authors considered monotonicity and positivity analysis for discrete Caputo, Caputo-Fabrizio and Attangana-Baleanu fractional differences and in [17,18] the authors considered monotonicity and positivity results for abstract convolution equations that could be specialized to yield new insights into qualitative properties of fractional difference operators. In [19], the authors presented positivity and monotonicity results for discrete Caputo-Fabrizo fractional operators which cover both the sequential and non-sequential cases, and showed both similarities and dissimilarities between the exponential kernel case (that is included in Caputo-Fabrizo fractional operators) and fractional differences with other types of kernels. Also in [20] the authors extended the results in [19] to discrete Attangana-Baleanu fractional differences with Mittag-Leffler kernels. The main theoretical developments of monotonicity and positivity analysis in discrete fractional calculus can be found in [21,22,23,24] for nabla differences, and in [25,26,27,28] for delta differences.
The main idea in this article is to analyse discrete Caputo-Fabrizo fractional differences with exponential kernels in the Riemann-Liouville sense. The results are based on a notable lemma combined with summation techniques. The purpose of this article is two-fold. First we show the positiveness of discrete fractional operators from a theoretical point of view. Second we shall complement the theoretical results numerically and graphically based on the standard plots and heat map plots.
The plan of the article is as follows. In Section 2 we present discrete fractional operators and the main lemma. Section 3 analyses the discrete fractional operator in a theoretical sense. In Section 4 we discuss our theoretical strategy on standard plots (Subsection 4.1) and heat map plots (Subsection 4.2). Finally, in Section 5 we summarize our findings.
First we recall the definitions in discrete fractional calculus; see [2,3,5] for more information.
Definition 2.1. (see [2,Definition 2.24]). Let c0∈R, 0<θ≤1, F be defined on Nc0 and Λ(θ)>0 be a normalization constant. Then the following operator
(CFRc0∇θF)(t):=Λ(θ)∇tt∑r=c0+1F(r)(1−θ)t−r{t∈Nc0+1}, |
is called the discrete Caputo-Fabrizio fractional operator with exponential kernels in the Riemann-Liouville sense CFR, and the following operator
(CFCc0∇θF)(t):=Λ(θ)t∑r=c0+1(∇rF)(r)(1−θ)t−r{t∈Nc0+1}, |
is called the discrete Caputo-Fabrizo fractional operator with exponential kernels in the Caputo sense CFC.
Definition 2.2 (see [3]). For F:Nc0−κ→R with κ<θ≤κ+1 and κ∈N0, the discrete nabla CFC and CFR fractional differences can be expressed as follows:
(CFCc0∇θF)(t)=(CFCc0∇θ−κ∇κF)(t), |
and
(CFRc0∇θF)(t)=(CFRc0∇θ−κ∇κF)(t), |
respectively, for each t∈Nc0+1.
The following lemma is essential later.
Lemma 2.1. Assume that F is defined on Nc0 and 1<θ<2. Then the CFR fractional difference is
(CFRc0∇θF)(t)=Λ(θ−1){(∇F)(t)+(1−θ)(2−θ)t−c0−2(∇F)(c0+1)+(1−θ)t−1∑r=c0+2(∇rF)(r)(2−θ)t−r−1}, |
for each t∈Nc0+2.
Proof. From Definitions 2.1 and 2.2, the following can be deduced for 1<θ<2:
(CFRc0∇θF)(t)=Λ(θ−1){t∑r=c0+1(∇rF)(r)(2−θ)t−r−t−1∑r=c0+1(∇rF)(r)(2−θ)t−r−1}=Λ(θ−1){(∇F)(t)+t−1∑r=c0+1(∇rF)(r)[(2−θ)t−r−(2−θ)t−r−1]}=Λ(θ−1){(∇F)(t)+(1−θ)(2−θ)t−c0−2(∇F)(c0+1)+(1−θ)t−1∑r=c0+2(∇rF)(r)(2−θ)t−r−1}, |
for each t∈Nc0+2.
In the following theorem, we will show that F is monotonically increasing at two time steps even if (CFRc0∇θF)(t) is negative at the two time steps.
Theorem 3.1. Let the function F be defined on Nc0+1, and let 1<θ<2 and ϵ>0. Assume that
(CFRc0∇θF)(t)>−ϵΛ(θ−1)(∇F)(c0+1)fort∈{c0+2,c0+3}s.t.(∇F)(c0+1)≥0. | (3.1) |
If (1−θ)(2−θ)<−ϵ, then (∇F)(c0+2) and (∇F)(c0+3) are both nonnegative.
Proof. From Lemma 2.1 and condition (3.1) we have
(∇F)(t)≥−(∇F)(c0+1)[(1−θ)(2−θ)t−c0−2+ϵ]−(1−θ)t−1∑r=c0+2(∇rF)(r)(2−θ)t−r−1, | (3.2) |
for each t∈Nc0+2. At t=c0+2, we have
(∇F)(c0+2)≥−(∇F)(c0+1)[(1−θ)+ϵ]−(1−θ)c0+1∑r=c0+2(∇rF)(r)(2−θ)c0+1−r⏟=0≥0, |
where we have used (1−θ)<(1−θ)(2−θ)<−ϵ and (∇F)(c0+1)≥0 by assumption. At t=c0+3, it follows from (3.2) that
(∇F)(c0+3)=−(∇F)(c0+1)[(1−θ)(2−θ)+ϵ]−(1−θ)c0+2∑r=c0+2(∇rF)(r)(2−θ)c0+2−r=−(∇F)(c0+1)⏟≥0[(1−θ)(2−θ)+ϵ]⏟<0−(1−θ)⏟<0(∇F)(c0+2)⏟≥0≥0, | (3.3) |
as required. Hence the proof is completed.
Remark 3.1. It worth mentioning that Figure 1 shows the graph of θ↦(1−θ)(2−θ) for θ∈(1,2).
In order for Theorem 3.1 to be applicable, the allowable range of ϵ is ϵ∈(0,−(2−θ)(1−θ)) for a fixed θ∈(1,2)
Now, we can define the set Hκ,ϵ as follows
Hκ,ϵ:={θ∈(1,2):(1−θ)(2−θ)κ−c0−2<−ϵ}⊆(1,2),∀κ∈Nc0+3. |
The following lemma shows that the collection {Hκ,ϵ}∞κ=c0+1 forms a nested collection of decreasing sets for each ϵ>0.
Lemma 3.1. Let 1<θ<2. Then, for each ϵ>0 and κ∈Nc0+3 we have that Hκ+1,ϵ⊆Hκ,ϵ.
Proof. Let θ∈Hκ+1,ϵ for some fixed but arbitrary κ∈Nc0+3 and ϵ>0. Then we have
(1−θ)(2−θ)κ−c0−1=(1−θ)(2−θ)(2−θ)κ−c0−2<−ϵ. |
Considering 1<θ<2 and κ∈Nc0+3, we have 0<2−θ<1. Consequently, we have
(1−θ)(2−θ)κ−c0−2<−ϵ⋅ 12−θ⏟>1<−ϵ. |
This implies that θ∈Hκ,ϵ, and thus Hκ+1,ϵ⊆Hκ,ϵ.
Now, Theorem 3.1 and Lemma 3.1 lead to the following corollary.
Corollary 3.1. Let F be a function defined on Nc0+1, θ∈(1,2) and
(CFRc0∇θF)(t)>−ϵΛ(θ−1)(∇F)(c0+1)suchthat(∇F)(c0+1)≥0, | (3.4) |
for each t∈Nsc0+3:={c0+3,c0+4,…,s} and some s∈Nc0+3. If θ∈Hs,ϵ, then we have (∇F)(t)≥0 for each t∈Nsc0+1.
Proof. From the assumption θ∈Hs,ϵ and Lemma 3.1, we have
θ∈Hs,ϵ=Hs,ϵ∩s−1⋂κ=c0+3Hκ,ϵ. |
This leads to
(1−θ)(2−θ)t−c0−2<−ϵ, | (3.5) |
for each t∈Nsc0+3.
Now we use the induction process. First for t=c0+3 we obtain (∇F)(c0+3)≥0 directly as in Theorem 3.1 by considering inequalities (Eq 3.4) and (Eq 3.5) together with the given assumption (∇F)(c0+1)≥0. As a result, we can inductively iterate inequality (Eq 3.2) to get
(∇F)(t)≥0, |
for each t∈Nsc0+2. Moreover, (∇F)(c0+1)≥0 by assumption. Thus, (∇F)(t)≥0 for each t∈Nsc0+1 as desired.
In this section, we consider the methodology for the positivity of ∇F based on previous observations in Theorem 3.1 and Corollary 3.1 in such a way that the initial conditions are known. Later, we will illustrate other parts of our article via standard plots and heat maps for different values of θ and ϵ. The computations in this section were performed with MATLAB software.
Example 4.1. Considering Lemma 1 with t:=c0+3:
(CFRc0∇θF)(c0+3)=Λ(θ−1){(∇F)(c0+3)+(1−θ)(2−θ)(∇F)(c0+1)+(1−θ)c0+2∑r=c0+2(∇rF)(r)(2−θ)c0+2−r}. |
For c0=0, it follows that
(CFR0∇θF)(3)=Λ(θ−1){(∇F)(3)+(1−θ)(2−θ)(∇F)(1)+(1−θ)2∑r=2(∇rF)(r)(2−θ)2−r}=Λ(θ−1){(∇F)(3)+(1−θ)(2−θ)(∇F)(1)+(1−θ)(∇F)(2)}=Λ(θ−1){F(3)−F(2)+(1−θ)(2−θ)[F(1)−F(0)]+(1−θ)[F(2)−F(1)]}. |
If we take θ=1.99,F(0)=0,F(1)=1,F(2)=1.001,F(3)=1.005, and ϵ=0.007, we have
(CFR0∇1.99F)(3)=Λ(0.99){0.004+(−0.99)(0.01)(0)+(−0.99)(0.001)}=−0.0069Λ(0.99)>−0.007Λ(0.99)=−ϵΛ(0.99)(∇F)(1). |
In addition, we see that (1−θ)(2−θ)=−0.0099<−0.007=−ϵ. Since the required conditions are satisfied, Theorem 3.1 ensures that (∇F)(3)>0.
In Figure 2, the sets Hκ,0.008 and Hκ,0.004 are shown for different values of κ, respectively in Figure 2a, b. It is noted that Hκ,0.008 and Hκ,0.004 decrease by increasing the values of κ. Moreover, in Figure 2a, the set Hκ,0.008 becomes empty for κ≥45; however, in Figure 2b, we observe the non-emptiness of the set Hκ,0.004 for many larger values of κ up to 90. We think that the measures of Hκ,0.008 and Hκ,0.004 are not symmetrically distributed when κ increases (see Figure 2a, b). We do not have a good conceptual explanation for why this symmetric behavior is observed. In fact, it is not clear why the discrete nabla fractional difference CFRc0∇θ seems to give monotonically when θ→1 rather than for θ→2, specifically, it gives a maximal information when θ is very close to 1 as ϵ→0+.
In the next figure (Figure 3), we have chosen a smaller ϵ (ϵ=0.001), we see that the set Hκ,0.001 is non-empty for κ>320. This tells us that small choices in ϵ give us a more widely applicable result.
In this part, we introduce the set Hκ:={κ:θ∈Hκ,ϵ} to simulate our main theoretical findings for the cardinality of the set Hκ via heat maps in Figure 4a–d. In these figures: we mean the warm colors such as red ones and the cool colors such as blue ones. Moreover, the θ values are on the x−axis and ϵ values are on the y−axis. We choose ϵ in the interval [0.00001, 0.0001]. Then, the conclusion of these figures are as follows:
● In Figure 4a when θ∈(1,2) and Figure 4b when θ∈(1,1.5), we observe that the warmer colors are somewhat skewed toward θ very close to 1, and the cooler colors cover the rest of the figures for θ above 1.05.
● In Figure 4c, d, the warmest colors move strongly towards the lower values of θ, especially, when θ∈(1,1.05). Furthermore, when as θ increases to up to 1.0368, it drops sharply from magenta to cyan, which implies a sharp decrease in the cardinality of Hκ for a small values of ϵ as in the interval [0.00001, 0.0001].
On the other hand, for larger values of ϵ, the set Hκ will tend to be empty even if we select a smaller θ in such an interval (1,1.05). See the following Figure 5a, b for more.
In conclusion, from Figures 4 and 5, we see that: For a smaller value of ϵ, the set Hκ,ϵ tends to remain non-empty (see Figure 4), unlike for a larger value of ϵ (see Figure 5). Furthermore, these verify that Corollary 3.1 will be more applicable for 1<θ<1.05 and 0.01<ϵ<0.1 as shown in Figure 4d.
Although, our numerical data strongly note the sensitivity of the set Hκ when slight increasing in ϵ is observed for θ close to 2 compares with θ close to 1.
In this paper we developed a positivity method for analysing discrete fractional operators of Riemann-Liouville type based on exponential kernels. In our work we have found that (∇F)(3)≥0 when (CFRc0∇θF)(t)>−ϵΛ(θ−1)(∇F)(c0+1) such that (∇F)(c0+1)≥0 and ϵ>0. We continue to extend this result for each value of t in Nsc0+1 as we have done in Corollary 3.1.
In addition we presented standard plots and heat map plots for the discrete problem that is solved numerically. Two of the graphs are standard plots for Hκ,ϵ for different values of κ and ϵ (see Figure 2), and the other six graphs consider the cardinality of Hκ for different values of ϵ and θ (see Figures 4 and 5). These graphs ensure the validity of our theoretical results.
In the future we hope to apply our method to other types of discrete fractional operators which include Mittag-Leffler and their extensions in kernels; see for example [5,6].
This work was supported by the Taif University Researchers Supporting Project Number (TURSP-2020/86), Taif University, Taif, Saudi Arabia.
The authors declare there is no conflict of interest.
[1] | K. Bollacker, R. Cook, P. Tufts, Freebase: a shared database of structured general human knowledge, in Proceedings of the 22nd national conference on Artificial intelligence, 2 (2007), 1962–1963. |
[2] |
C. Bizer, J. Lehmann, G. Kobilarov, S. Auer, C. Becker, R. Cyganiak, et al., Dbpedia-A crystallization point for the web of data, J. Web Semant., 7 (2009), 154–165. https://doi.org/10.1016/j.websem.2009.07.002 doi: 10.1016/j.websem.2009.07.002
![]() |
[3] |
V. Denny, M. Krötzsch, Wikidata: a free collaborative knowledgebase, Commun. ACM, 57 (2014), 78–85. https://doi.org/10.1145/2629489 doi: 10.1145/2629489
![]() |
[4] | X. Niu, X. Sun, H. Wang, S. Rong, G. Qi, Y. Yu, Zhishi: me-weaving Chinese linking open data, in International Semantic Web Conference, Springer, Berlin, Heidelberg, (2011), 205–220. https://doi.org/10.1007/978-3-642-25093-4_14 |
[5] | B. Xu, Y. Xu, J. Liang, C. Xie, B. Liang, W. Cui, et al., CN-DBpedia: A never-ending Chinese knowledge extraction system, in International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, Springer, Cham, (2017), 428–438. |
[6] | Q. Cai, A. Yates, Large-scale semantic parsing via schema matching and lexicon extension, in Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, 1 (2013), 423–433. |
[7] | J. Berant, A. Chou, R. Frostig, P. Liang, Semantic parsing on freebase from question-answer pairs, in Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, (2013), 1533–1544. |
[8] |
S. Reddy, M. Lapata, M. Steedman, Large-scale semantic parsing without question-answer pairs, Trans. Assoc. Comput. Ling., 2 (2014), 377–392. https://doi.org/10.1162/tacl_a_00190 doi: 10.1162/tacl_a_00190
![]() |
[9] | W. Yih, M. Chang, X. He, J. Gao, Semantic parsing via staged query graph generation: Question answering with knowledge base, in Proceedings of the Joint Conference of the 53rd Annual Meeting of the ACL and the 7th International Joint Conference on Natural Language Processing of the AFNLP, (2015), 1–11. |
[10] |
S. Reddy, O. Täckström, M. Collins, T. Kwiatkowski, D. Das, M. Steedman, et al., Transforming dependency structures to logical forms for semantic parsing, Trans. Assoc. Comput. Ling., 4 (2016), 127–140. https://doi.org/10.1162/tacl_a_00088 doi: 10.1162/tacl_a_00088
![]() |
[11] | E. Hoffer, N. Ailon, Deep metric learning using triplet network, International Workshop on Similarity-based Pattern Recognition, (2015), 84–92. |
[12] | N. Francis, A. Green, P. Guagliardo, L. Libkin, T. Lindaaker, V. Marsault, et al., Cypher: An evolving query language for property graphs, in Proceedings of the 2018 International Conference on Management of Data, (2018), 1433–1445. https://doi.org/10.1145/3183713.3190657 |
[13] | X. Yao, B. Durme, Information extraction over structured data: Question answering with freebase, in Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, 1 (2014), 956–966. |
[14] | M. Petrochuk, L. Zettlemoyer, Simplequestions nearly solved: A new upperbound and baseline approach, preprint, arXiv: 1804.08798. https://doi.org/10.48550/arXiv.1804.08798 |
[15] | T. Mikolov, K. Chen, G. Corrado, J. Dean, Efficient estimation of word representations in vector space, preprint, arXiv: 1301.3781. https://doi.org/10.48550/arXiv.1301.3781 |
[16] | J. Pennington, R. Socher, C. D. Manning, Glove: Global vectors for word representation, in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, (2014), 1532–1543. |
[17] | J. Devlin, M. W. Chang, K. Lee, K. Toutanova, BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics, (2019), 4171–4186. |
[18] | Z. Yang, Z. Dai, Y. Yang, J. Carbonell, R. Salakhutdinov, Q. Le, XLNet: generalized autoregressive pretraining for language understanding, in Proceedings of the 33rd International Conference on Neural Information Processing Systems, (2019), 5753–5763. |
[19] | A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, I. Sutskever, Language models are unsupervised multitask learners, OpenAI blog, 1 (2019), 9–24. |
[20] |
L. Li, Y. Zhai, J. Gao, L. Wang, L. Hou, J. Zhao, Stacking-BERT model for Chinese medical procedure entity normalization, Math. Biosci. Eng., 20 (2023), 1018–1036. https://doi.org/10.3934/mbe.2023047 doi: 10.3934/mbe.2023047
![]() |
[21] |
C. Li, K. Ma, Entity recognition of Chinese medical text based on multi-head self-attention combined with BILSTM-CRF, Math. Biosci. Eng., 19 (2022), 2206–2218. https://doi.org/10.3934/mbe.2022103 doi: 10.3934/mbe.2022103
![]() |
[22] |
S. A. Sloman, The empirical case for two systems of reasoning, Psychol. Bull., 119 (1996), 3–22. https://doi.org/10.1037/0033-2909.119.1.3 doi: 10.1037/0033-2909.119.1.3
![]() |
[23] |
J. St. B. T. Evans, In two minds: dual-process accounts of reasoning, Trends Cognit. Sci., 7 (2003), 454–459. https://doi.org/10.1016/j.tics.2003.08.012 doi: 10.1016/j.tics.2003.08.012
![]() |
[24] |
J. St. B. T. Evans, Dual-processing accounts of reasoning, judgment, and social cognition, Annu. Rev. Psychol., 59 (2008), 255–278. https://doi.org/10.1146/annurev.psych.59.103006.093629 doi: 10.1146/annurev.psych.59.103006.093629
![]() |
[25] | B. Alan, Working memory, Science, 255 (1992), 556–559. https://doi.org/10.1126/science.1736359 |
[26] |
R. M. Terol, P. M. Barco, M. Palomar, A knowledge based method for the medical question answering problem, Comput. Biol. Med., 37 (2007), 1511–1521. https://doi.org/10.1016/j.compbiomed.2007.01.013 doi: 10.1016/j.compbiomed.2007.01.013
![]() |
[27] | Q. Cai, A. Yates, Large-scale semantic parsing via schema matching and lexicon extension, in Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, 1 (2013), 423–433. |
[28] | J. Berant, A. Chou, R. Frostig, P. Liang, Semantic parsing on freebase from question-answer pairs, in Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, (2013), 1533–1544. |
[29] | T. Kwiatkowski, E. Choi, Y. Artzi, L. Zettlemoyer, Scaling semantic parsers with on-the-fly ontology matching, in Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, (2013), 1545–1556. |
[30] | K. Luo, F. Lin, X. Luo, K. Q. Zhu, Knowledge base question answering via encoding of complex query graphs, in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, (2018), 2185–2194. https://doi.org/10.18653/v1/D18-1242 |
[31] | P. Kapanipathi, I. Abdelaziz, S. Ravishankar, S. Roukos, A. G. Gray, R. F. Astudillo, et al., Question answering over knowledge bases by leveraging semantic parsing and neuro-symbolic reasoning, in Proceedings of the AAAI Conference on Artificial Intelligence, (2020), 1–10. |
[32] |
S. Zhu, X. Cheng, S. Su, Knowledge-based question answering by tree-to-sequence learning, Neurocomputing, 372 (2020), 64–72. https://doi.org/10.1016/j.neucom.2019.09.003 doi: 10.1016/j.neucom.2019.09.003
![]() |
[33] | Y. Chen, H. Li, Y. Hua, G. Qi, Formal query building with query structure prediction for complex question answering over knowledge base, in Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence, (2021), 3751–3758. https://doi.org/10.24963/ijcai.2020/519 |
[34] | B. Min, R. Grishman, L. Wan, C. Wang, D. Gondek Distant supervision for relation extraction with an incomplete knowledge base, in Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics, (2013), 777–782. |
[35] | H. Sun, B. Dhingra, M. Zaheer, K. Mazaitis, R. Salakhutdinov, W. W. Cohen, Open domain question answering using early fusion of knowledge bases and text, in Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, (2018), 4231–4242. https://doi.org/10.18653/v1/D18-1455 |
[36] | H. Sun, T. B. Weiss, W. W. Cohen, Pullnet: Open domain question answering with iterative retrieval on knowledge bases and text, in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, (2019), 2380–2390. https://doi.org/10.18653/v1/D19-1242 |
[37] | W. Xiong, M. Yu, S. Chang, X. Guo, W. Wang, Improving question answering over incomplete kbs with knowledge-aware reader, in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, (2019), 4258–4264. https://doi.org/10.18653/v1/P19-1417 |
[38] | J. Han, B. Cheng, X. Wang, Open domain question answering based on text enhanced knowledge graph with hyperedge infusion, in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, (2020), 1475–1481. https://doi.org/10.18653/v1/2020.findings-emnlp.133 |
[39] | A. Saxena, A. Tripathi, P. Talukdar, Improving multi-hop question answering over knowledge graphs using knowledge base embeddings, in Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, (2020), 4498–4507. https://doi.org/10.18653/v1/2020.acl-main.412 |
[40] | A. Bordes, J. Weston, N. Usunier, Open question answering with weakly supervised embedding models, in Joint European Conference on Machine Learning and Knowledge Discovery in Databases, (2014), 165–180. |
[41] | D. Guo, D. Tang, N. Duan, M. Zhou, J. Yin, Dialog-to-action: conversational question answering over a large-scale knowledge base, in Proceedings of the 32nd International Conference on Neural Information Processing Systems, 7 (2018), 2946–2955. |
[42] | X. Huang, J. Zhang, D. Li, P. Li, Knowledge graph embedding based question answering, in Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, (2019), 105–113. https://doi.org/10.1145/3289600.3290956 |
[43] | R. Wang, M. Wang, J. Liu, W. Chen, M. Cochez, S. Decker, Leveraging knowledge graph embeddings for natural language question answering, in International Conference on Database Systems for Advanced Applications, 11446 (2019), 659–675. https://doi.org/10.1007/978-3-030-18576-3_39 |
[44] | L. Dong, F. Wei, M. Zhou, K. Xu, Question answering over freebase with multi-column convolutional neural networks, in Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, 1 (2015), 260–269. |
[45] | Y. Lai, Y. Feng, X. Yu, Z. Wang, K. Xu, D. Zhao, Lattice cnns for matching based chinese question answering, in Proceedings of the AAAI Conference on Artificial Intelligence, 33 (2019), 6634–6641. https://doi.org/10.1609/aaai.v33i01.33016634 |
[46] | Y. Hao, Y. Zhang, K. Liu, S. He, Z. Liu, H. Wu, et al., An end-to-end model for question answering over knowledge base with cross-attention combining global knowledge, in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 1 (2017), 221–231. https://doi.org/10.18653/v1/P17-1021 |
[47] | K. Tai, R. Socher, C. D. Manning, Improved semantic representations from tree-structured long short-term memory networks, in Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, 1 (2015), 1556–1566. |
[48] | M. Cao, S. Li, X. Wang, Z. Yang, H. Lin,, DUTIR: Chinese open domain knowledge base question answering system, in Proceedings of the Evaluation Tasks at the China Conference on Knowledge Graph and Semantic Computing, 1 (2019), 1–6. |
[49] | P. Zhang, K. Wu, Z. Zhu, Y. Jia, X. Zhou, W. Chen, et al., Combining neural network models with rules for Chinese knowledge base question answering, in Proceedings of the Evaluation Tasks at the China Conference on Knowledge Graph and Semantic Computing, 1 (2019), 1–12. |
[50] | Z. Wang, Y. Hou, M. Wang, C. Li, Chinese knowledge base question answering method based on fusion feature, in Proceedings of the evaluation tasks at the china conference on knowledge graph and semantic computing, 1 (2020), 1–7. |
[51] | J. Luo, C. Yin, X. Wu, L. Zhou, H. Zhong, Chinese knowledge base question answering system based on mixed semantic similarity, in Proceedings of the Evaluation Tasks at the China Conference on Knowledge Graph and Semantic Computing, 1 (2019), 1–12. |
[52] | K. Wu, X. Zhou, Z. Li, X. Liang, W. Chen, Path selection for Chinese knowledge base question answering, J. Chin. Inf. Process., 35 (2021), 113–122. |
[53] | M. Tang, H. Xiong, L. Wang, X. Lin, A dynamic answering path based fusion model for KGQA, in International Conference on Knowledge Science, Engineering and Management, 12274 (2020), 235–246. https://doi.org/10.1007/978-3-030-55130-8_21 |
[54] |
H. Xiong, S. Wang, M. Tang, L. Wang, X. Lin, Knowledge graph question answering with semantic oriented fusion model, Knowl.-Based Syst., 221 (2021), 106954–106964. https://doi.org/10.1016/j.knosys.2021.106954 doi: 10.1016/j.knosys.2021.106954
![]() |
[55] | W. Dai, H. Liu, Y. Liu, R. Lv, S. Chen, An integrated path formulation method for open domain question answering over knowledge base, in Proceedings of the Evaluation Tasks at the China Conference on Knowledge Graph and Semantic Computing, 1 (2020), 1–10. |
[56] | H. Zhang, R. Li, S. Wang, J. Huang, Retrieval-matching knowledge base question answering system based on pre-trained language model, in Proceedings of the Evaluation Tasks at the China Conference on Knowledge Graph and Semantic Computing, 1 (2020), 1–10. |
[57] | Y. Cui, W. Che, T. Liu, B. Qin, S. Wang, G. Hu, Revisiting pre-trained models for Chinese natural language processing, in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 1 (2020), 657–668. https://doi.org/10.18653/v1/2020.findings-emnlp.58 |
[58] | B. Steiner, Z. DeVito, S. Chintala, S. Gross, A. Paske, F. Massa, et al., Pytorch: An imperative style, high-performance deep learning library, in Proceedings of the Advances in Neural Information Processing Systems, (2019), 8026–8037. |
[59] | Y. Zhao, H. Zhou, A. Zhang, R. Xie, Q. Li, F. Zhuang, Connecting embeddings based on multiplex relational graph attention networks for knowledge graph entity typing, IEEE Trans. Knowl. Data Eng., (2022), 1–12. https://doi.org/10.1109/TKDE.2022.3142056 |
[60] |
H. Zhu, X. He, M. Wang, M. Zhang, L. Qing, Medical visual question answering via corresponding feature fusion combined with semantic attention, Math. Biosci. Eng., 19 (2022), 10192–10212. https://doi.org/10.3934/mbe.2022478 doi: 10.3934/mbe.2022478
![]() |
[61] | D. Prakash, L. Tuan, L. Thomas, B. Yoshua, B. Xavier, Graph neural networks with learnable structural and positional representations, preprint, arXiv: 2110.07875. https://doi.org/10.48550/arXiv.2110.07875 |