MultiGranCNN: An Architecture for General Matching of Text Chunks on Multiple Levels of Granularity

By Wenpeng Yin, Hinrich Schütze. 2015

81 citations recorded by the source corpus.

We present MultiGranCNN, a general deep learning architecture for matching text chunks. MultiGranCNN supports multigranular comparability of representations: shorter sequences in one chunk can be directly compared to longer sequences in the other chunk. MultiGranCNN also contains a flexible and modularized match feature component that is easily adaptable to different types of chunk matching. We demonstrate stateof-the-art performance of MultiGranCNN on clause coherence and paraphrase identification tasks.

Subfields: Artificial Intelligence, Natural Language Processing, Model Architectures

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

1. W. Bruce Croft
2. Hamed Zamani
3. Jiafeng Guo
4. Xueqi Cheng
5. Yixing Fan
6. Qingyao Ai
7. Andrew Yates
8. Liu Yang

In Natural Language Processing

1. Jiafeng Guo
2. W. Bruce Croft
3. Yixing Fan
4. Xueqi Cheng
5. Qingyao Ai
6. Hamed Zamani
7. Liu Yang
8. Liang Pang

In Model Architectures

1. Germán Kruszewski
2. Liu Yang
3. W. Bruce Croft
4. Qingyao Ai
5. Marco Baroni
6. Xueqi Cheng
7. Jiafeng Guo
8. Gemma Boleda

Citations in the corpus

• The LAMBADA dataset: Word prediction requiring a broad discourse context (2016, background): “Of course, text understanding can be tested through other tasks, including entailment detection (Bowman et al., 2015), answering questions about a text (Richardson et al., 2013; Weston et al., 2015) and measuring inter-clause coherence (Yin and Sch¨utze, 2015).”
• A Deep Relevance Matching Model for Ad-hoc Retrieval (2016, methodology): “In [30], Yin et al. introduced MultiGranCNN which employs a CNN to obtain hierarchical representations of texts, and then computes the matching score based on the interactions between these multigranular representations.”
• A Deep Architecture for Semantic Matching with Multiple Positional Sentence Representations (2015, methodology): “• MultiGranCNN: first uses CNNs to obtain word, phrase and sentence level representations, and then computes the matching score based on the interactions among all these representations (Yin and Sch¨utze 2015b).”
• Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN (2016, background): “Examples include RAE [Socher et al., 2011], DSSM [Huang et al., 2013], CDSSM [Shen et al., 2014], ARC-I [Hu et al., 2014], CNTN [Qiu and Huang, 2015], LSTM-RNN [Palangi et al., 2015], MultiGranCNN [Yin and Schütze, 2015a; Yin and Schütze, 2015b] and MV-LSTM [Wan et al., 2016].”
• A Deep Look into Neural Ranking Models for Information Retrieval (2019, background): “781 MultiGranCNN[90] (2015)2 S/I/M \ \ \ \ 0.”