Papers › Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information
Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information
Seonhoon Kim, Inho Kang, Nojun Kwak
Sentence matching is widely used in various natural language tasks such as natural language inference, paraphrase identification, and question answering. For these tasks, understanding logical and semantic relationship between two sentences is required but it is yet challenging. Although attention mechanism is useful to capture the semantic relationship and to properly align the elements of two sentences, previous methods of attention mechanism simply use a summation operation which does not retain original features enough. Inspired by DenseNet, a densely connected convolutional network, we propose a densely-connected co-attentive recurrent neural network, each layer of which uses concatenated information of attentive features as well as hidden features of all the preceding recurrent layers. It enables preserving the original and the co-attentive feature information from the bottommost word embedding layer to the uppermost recurrent layer. To alleviate the problem of an ever-increasing size of feature vectors due to dense concatenation operations, we also propose to use an autoencoder after dense concatenation. We evaluate our proposed architecture on highly competitive benchmark datasets related to sentence matching. Experimental results show that our architecture, which retains recurrent and attentive features, achieves state-of-the-art performances for most of the tasks.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Natural Language Inference | SNLI | Densely-Connected Recurrent and Co-Attentive Network Ensemble | % Test Accuracy | 90.1 | #13 of 98 | Archive leaderboard | report |
| Natural Language Inference | SNLI | Densely-Connected Recurrent and Co-Attentive Network Ensemble | % Train Accuracy | 95.0 | #13 of 98 | Archive leaderboard | report |
| Natural Language Inference | SNLI | Densely-Connected Recurrent and Co-Attentive Network Ensemble | Parameters | 53.3m | #13 of 98 | Archive leaderboard | report |
| Natural Language Inference | SNLI | Densely-Connected Recurrent and Co-Attentive Network | % Test Accuracy | 88.9 | #25 of 98 | Archive leaderboard | report |
| Natural Language Inference | SNLI | Densely-Connected Recurrent and Co-Attentive Network | % Train Accuracy | 93.1 | #25 of 98 | Archive leaderboard | report |
| Natural Language Inference | SNLI | Densely-Connected Recurrent and Co-Attentive Network | Parameters | 6.7m | #25 of 98 | Archive leaderboard | report |
| Natural Language Inference | SNLI | Densely-Connected Recurrent and Co-Attentive Network (encoder) | % Test Accuracy | 86.5 | #55 of 98 | Archive leaderboard | report |
| Natural Language Inference | SNLI | Densely-Connected Recurrent and Co-Attentive Network (encoder) | % Train Accuracy | 91.4 | #55 of 98 | Archive leaderboard | report |
| Natural Language Inference | SNLI | Densely-Connected Recurrent and Co-Attentive Network (encoder) | Parameters | 5.6m | #55 of 98 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections