Learning to Rank Question-Answer Pairs Using Hierarchical Recurrent Encoder with Latent Topic Clustering

By Seunghyun Yoon, Joongbo Shin, Kyomin Jung. 2017

35 citations recorded by the source corpus.

In this paper, we propose a novel end-to-end neural architecture for ranking candidate answers, that adapts a hierarchical recurrent neural network and a latent topic clustering module. With our proposed model, a text is encoded to a vector representation from an word-level to a chunk-level to effectively capture the entire meaning. In particular, by adapting the hierarchical structure, our model shows very small performance degradations in longer text comprehension while other state-of-the-art recurrent neural network models suffer from it. Additionally, the latent topic clustering module extracts semantic information from target samples. This clustering module is useful for any text related tasks by allowing each data sample to find its nearest topic cluster, thus helping the neural network model analyze the entire data. We evaluate our models on the Ubuntu Dialogue Corpus and consumer electronic domain question answering dataset, which is related to Samsung products. The proposed model shows state-of-the-art results for ranking question-answer pairs.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Retrieval & Search, Question Answering & Reading Comprehension

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. Ekaterina Shutova
2. Helen Yannakoudakis
3. Pushkar Mishra
4. Younghun Lee
5. Seunghyun Yoon
6. Kyomin Jung
7. Isar Nejadgholi
8. Svetlana Kiritchenko

In Computer Vision and Pattern Recognition

1. Pushkar Mishra
2. Younghun Lee
3. Helen Yannakoudakis
4. Ekaterina Shutova
5. Seunghyun Yoon
6. Kyomin Jung

In Information Retrieval & Search

1. Younghun Lee
2. Helen Yannakoudakis
3. Ekaterina Shutova
4. Pushkar Mishra
5. Seunghyun Yoon
6. Kyomin Jung

In Question Answering & Reading Comprehension

1. Younghun Lee
2. Helen Yannakoudakis
3. Ekaterina Shutova
4. Pushkar Mishra
5. Seunghyun Yoon
6. Kyomin Jung

Citations in the corpus

• Poly-encoders: Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring (2019, neutral): “5 (Yoon et al., 2017) 65.”
• Comparative Studies of Detecting Abusive Language on Twitter (2018, methodology): “The LTC method extracts latent topic information from the hidden states of RNN, and uses it for additional information in classifying the text data.”
• Tackling Online Abuse: A Survey of Automated Abuse Detection Methods (2019, methodology): “Their most effective setups were: (1) a word-level GRU followed by an LR layer; (2) setup 1 extended with an attention mechanism on words.”
• Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring (2019, unknown): “5 (Yoon et al., 2018) 65.”