Modeling Relational Information in Question-Answer Pairs with Convolutional Neural Networks
By Aliaksei Severyn, Alessandro Moschitti. 2016
49 citations recorded by the source corpus.
In this paper, we propose convolutional neural networks for learning an optimal representation of question and answer sentences. Their main aspect is the use of relational information given by the matches between words from the two members of the pair. The matches are encoded as embeddings with additional parameters (dimensions), which are tuned by the network. These allows for better capturing interactions between questions and answers, resulting in a significant boost in accuracy. We test our models on two widely used answer sentence selection benchmarks. The results clearly show the effectiveness of our relational information, which allows our relatively simple network to approach the state of the art.
Subfields: Artificial Intelligence, Information Systems
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
- Erik Cambria
- Devamanyu Hazarika
- Soujanya Poria
- Tom Young
- Alessandro Moschitti
- Kateryna Tymoshenko
- Navonil Majumder
- Thuy Vu
In Information Systems
- Soujanya Poria
- Devamanyu Hazarika
- Erik Cambria
- Tom Young
- Kateryna Tymoshenko
- Daniele Bonadiman
- Thuy Vu
- Alessandro Moschitti
Citations in the corpus
- Recent Trends in Deep Learning Based Natural Language Processing (2017, methodology): “[58] also used CNN network to model optimal representations of question and answer sentences.”
- Recent Trends in Deep Learning Based Natural Language Processing [Review Article] (2018, methodology): “Severyn and Moschitti [57] also used CNN network to model optimal representations of question and answer sentences.”
- Convolutional Neural Networks vs. Convolution Kernels: Feature Engineering for Answer Sentence Reranking (2016, methodology): “We allow our convolutional neural network to capture the connections between related words in a pair and we feed it with an additional binary-like input about overlapping words (Severyn and Moschitti, 2016).”
- Natural Language Comprehension with the EpiReader (2016, unknown): “Both corpora use Clozestyle questions (Taylor, 1953), which are formulated by replacing a word or phrase in a given sentence with a placeholder token.”
- TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection (2019, background): “They also added embeddings encoding relational links be-tween matching words (Severyn and Moschitti 2016): a sort of hardcoded attention, which highly increases accuracy.”