Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms.
Citations
917 citations
620 citations
388 citations
Cites background or methods from "Coupled Multi-Layer Attentions for ..."
...Meanwhile, W. Wang et al. (2017) proposed a Coupled Multi-Layer Attention Model (CMLA) based on GRU for co-extracting of aspect and opinion terms....
[...]
...…76.6% Digital device JPDA Corpus (Kessler et al., 2010) English F1: 45.1% Web service Darmstadt Corpus (Toprak et al., 2010) English F1: 43.8% 20 W. Wang et al. (2017) Restaurant SemEval '14 English Coupled Multi-layer Attentions (CMLA) based on GRU F1: 85.29% Laptop SemEval '14 English F1:…...
[...]
355 citations
313 citations
Cites background from "Coupled Multi-Layer Attentions for ..."
...Recently, supervised deep learning models dominate both tasks (Wang et al., 2016, 2017; Xu et al., 2018a; Tang et al., 2016; He et al., 2018) and many of these models use handcrafted features, lexicons, and complicated neural network architectures to remedy the insufficient training examples from…...
[...]
References
24,012 citations
"Coupled Multi-Layer Attentions for ..." refers methods in this paper
...Motivated by (Socher et al. 2013), a tensor operator could be viewed 1For initialization of hi, we first pre-train a word embedding xi ∈RD (Mikolov et al. 2013) for wi, and then apply Gated Recurrent Unit (GRU) (Cho et al. 2014) to obtain hi by encoding context information....
[...]
...For initialization of hi, we first pre-train a word embedding xi ∈RD (Mikolov et al. 2013) for wi, and then apply Gated Recurrent Unit (GRU) (Cho et al....
[...]
20,027 citations
"Coupled Multi-Layer Attentions for ..." refers methods in this paper
...Therefore, we propose to use the attention mechanism (Bahdanau, Cho, and Bengio 2014) with tensor operators to replace the role of syntactic/dependency parsers to capture the relations among tokens in a sentence....
[...]
...In most previous studies, attentions have been used for generating sentence- or document- level representation by computing a weighted sum of the input sequence (Bahdanau, Cho, and Bengio 2014)....
[...]
...…and Bordes 2015) have recently been used for various machine learning tasks, including image generation (Gregor et al. 2015), machine translation (Bahdanau, Cho, and Bengio 2014), sentence summarization (Rush, Chopra, and Weston 2015), document sentiment classification (Yang et al. 2016), and…...
[...]
19,998 citations
14,077 citations
7,452 citations
"Coupled Multi-Layer Attentions for ..." refers background in this paper
...Aspect and opinion terms co-extraction, which aims at identifying aspect terms and opinion terms from texts, is an important task in fine-grained sentiment analysis (Pang and Lee 2008)....
[...]