|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
In this paper, we present a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks.
SOTA for Natural Language Inference on SNLI
However, because the performances of sentence classification and sentiment analysis can be enhanced by using a simple sentence representation method, it is not sufficient to claim that these models fully reflect the meanings of sentences based on good performances for such tasks.
Modeling sentence pairs plays the vital role for judging the relationship between two sentences, such as paraphrase identification, natural language inference, and answer sentence selection.
#6 best model for Natural Language Inference on SNLI
In this paper, we analyze several neural network designs (and their variations) for sentence pair modeling and compare their performance extensively across eight datasets, including paraphrase identification, semantic textual similarity, natural language inference, and question answering tasks.
Sentence pair modeling is critical for many NLP tasks, such as paraphrase identification, semantic textual similarity, and natural language inference.
In this work, we present a simple, effective multi-task learning framework for sentence representations that combines the inductive biases of diverse training objectives in a single model.
In this paper, we propose a new recurrent neural network (RNN)-based Seq2seq model, RNN semantic variational autoencoder (RNN--SVAE), to better capture the global latent information of a sequence of words.
Specifically, our model employs a joint deep architecture at the query term level for relevance matching.
#9 best model for Ad-Hoc Information Retrieval on TREC Robust04
In this paper, we study transfer learning for the PI and NLI problems, aiming to propose a general framework, which can effectively and efficiently adapt the shared knowledge learned from a resource-rich source domain to a resource- poor target domain.