Papers › Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference

Discourse Marker Augmented Network with Reinforcement Learning for Natural Language Inference

23 Jul 2019ACL 2018 7arXiv:1907.09692archive 2025-07-28

Boyuan Pan, Yazheng Yang, Zhou Zhao, Yueting Zhuang, Deng Cai, Xiaofei He

Natural Language Inference (NLI), also known as Recognizing Textual Entailment (RTE), is one of the most important problems in natural language processing. It requires to infer the logical relationship between two given sentences. While current approaches mostly focus on the interaction architectures of the sentences, in this paper, we propose to transfer knowledge from some important discourse markers to augment the quality of the NLI model. We observe that people usually use some discourse markers such as "so" or "but" to represent the logical relationship between two sentences. These words potentially have deep connections with the meanings of the sentences, thus can be utilized to help improve the representations of them. Moreover, we use reinforcement learning to optimize a new objective function with a reward defined by the property of the NLI datasets to make full use of the labels information. Experiments show that our method achieves the state-of-the-art performance on several large-scale datasets.

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

ZJULearning/DMP officialmentioned in papertf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Natural Language Inference RTE Reinforcement Learning Reinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Natural Language Inference	SNLI	300D DMAN Ensemble	% Test Accuracy	89.6	#16 of 98	Archive leaderboard	report
Natural Language Inference	SNLI	300D DMAN Ensemble	% Train Accuracy	96.1	#16 of 98	Archive leaderboard	report
Natural Language Inference	SNLI	300D DMAN Ensemble	Parameters	79m	#16 of 98	Archive leaderboard	report
Natural Language Inference	SNLI	300D DMAN	% Test Accuracy	88.8	#28 of 98	Archive leaderboard	report
Natural Language Inference	SNLI	300D DMAN	% Train Accuracy	95.4	#28 of 98	Archive leaderboard	report
Natural Language Inference	SNLI	300D DMAN	Parameters	9.2m	#28 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