A Convolutional Neural Network for Modelling Sentences
read the original abstract
The ability to accurately represent sentences is central to language understanding. We describe a convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) that we adopt for the semantic modelling of sentences. The network uses Dynamic k-Max Pooling, a global pooling operation over linear sequences. The network handles input sentences of varying length and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations. The network does not rely on a parse tree and is easily applicable to any language. We test the DCNN in four experiments: small scale binary and multi-class sentiment prediction, six-way question classification and Twitter sentiment prediction by distant supervision. The network achieves excellent performance in the first three tasks and a greater than 25% error reduction in the last task with respect to the strongest baseline.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
Language Models as Knowledge Bases?
BERT stores relational knowledge extractable via cloze queries without fine-tuning and matches supervised baselines on open-domain QA tasks.
-
DRIFT: Drift-Resilient Invariant-Feature Transformer for DGA Detection
DRIFT uses hybrid character and subword tokenization plus multi-task self-supervised pre-training to build DGA detectors that resist temporal drift and outperform baselines in forward-chaining evaluations over nine ye...
-
Compressive Transformers for Long-Range Sequence Modelling
Compressive Transformer sets new records on WikiText-103 (17.1 ppl) and Enwik8 (0.97 bpc) via memory compression and introduces the PG-19 long-range language benchmark.
-
Ranking sentences from product description & bullets for better search
Two RL-based extractive summarization models rank sentences from product fields by leveraging titles and click-through logs to improve search relevance.
-
Water Preservation in Soan River Basin using Deep Learning Techniques
RNN and LSTM models outperform other algorithms in predicting stream flow from precipitation, land use, and temperature, with a public dataset released.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.