Structural Embedding of Syntactic Trees for Machine Comprehension

By R. Liu, Junjie Hu, Wei Wei, Zi Yang, Eric Nyberg. 2017

51 citations recorded by the source corpus.

Deep neural networks for machine comprehension typically utilizes only word or character embeddings without explicitly taking advantage of structured linguistic information such as constituency trees and dependency trees. In this paper, we propose structural embedding of syntactic trees (SEST), an algorithm framework to utilize structured information and encode them into vector representations that can boost the performance of algorithms for the machine comprehension. We evaluate our approach using a state-of-the-art neural attention model on the SQuAD dataset. Experimental results demonstrate that our model can accurately identify the syntactic boundaries of the sentences and extract answers that are syntactically coherent over the baseline methods.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Extraction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Information Extraction

Citations in the corpus

QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension (2018, neutral): “…al., 2016) 66.2 / 75.9 66.2 / 75.9 FastQA (Weissenborn et al., 2017) 68.4 / 77.1 68.4 / 77.1 BiDAF (Seo et al., 2016) 68.0 / 77.3 68.0 / 77.3 SEDT (Liu et al., 2017a) 68.1 / 77.5 68.5 / 78.0 RaSoR (Lee et al., 2016) 70.8 / 78.7 69.6 / 77.7 FastQAExt (Weissenborn et al., 2017) 70.8 / 78.9 70.8 /…”
Adversarial Examples for Evaluating Reading Comprehension Systems (2017, background): “…2017), Mnemonic Reader Single and Ensemble versions (Hu et al., 2017), Structural Embedding of Dependency Trees (SEDT) Single and Ensemble versions (Liu et al., 2017), jNet (Zhang et al., 2017), Rumi-nating Reader (Gong and Bowman, 2017), Multi-Perspective Context Matching (MPCM) Single version…”
Stochastic Answer Networks for Machine Reading Comprehension (2017, methodology): “SEDT (Liu et al., 2017a) 33.”
FusionNet: Fusing via Fully-Aware Attention with Application to Machine Comprehension (2017, neutral): “EM / F1 LR Baseline (Rajpurkar et al., 2016) 40.4 / 51.0 Match-LSTM (Wang & Jiang, 2016) 64.7 / 73.7 BiDAF (Seo et al., 2017) 68.0 / 77.3 SEDT (Liu et al., 2017) 68.2 / 77.5 RaSoR (Lee et al., 2016) 70.8 / 78.7 DrQA (Chen et al., 2017a) 70.7 / 79.4 ReasoNet (Shen et al., 2017) 70.6 / 79.4 R. Mnemoni”
Explicit Utilization of General Knowledge in Machine Reading Comprehension (2018, background): “If we simply follow the self attentions of other works (Wang et al., 2017; Huang et al., 2017; Liu et al., 2017b; Clark and Gardner, 2017), then for each passage word p i , we should fuse its coarse memory g p i (i.e. the i -th column in G ) with the coarse memories of all the other passage words.”
Making Neural Machine Reading Comprehension Faster (2019, methodology): “Most of the papers that approach to solve SQuAD problem have utilized RNN based models [3, 5, 7, 9, 13, 14, 16, 17, 20, 22–24, 26, 29–31, 34–39, 41, 43] and they follow a similar chain of processes.”
Under review as a conference paper at ICLR 2018 (2017, background): “The papers are as follows: rnet (Microsoft Asia Natural Language Computing Group, 2017), SEDT (Liu et al., 2017), BiDAF (Seo et al.”
Self-Training for Jointly Learning to Ask and Answer Questions (2018, methodology): “After the release of large benchmarks such as SQUAD , MS MARCO and WikiQA , there has been a surge in interest on using neural network or deep-learning models for QA (Yin et al., 2015; Seo et al., 2016; Shen et al., 2016; Chen et al., 2017; Liu et al., 2017; Hu et al., 2017).”
Smarnet: Teaching Machines to Read and Comprehend Like Human (2017, methodology): “Inspired by Yang et al. (Yang et al. 2016) (Monsalve, Frank, and Vigliocco 2012) (Liu et al. 2017) and (Chen et al. 2017), we adopt a more ﬁne-grained dynamic gating mechanism to model the lexical properties related to the question and the passage.”