LexNET is an open source framework for classifying semantic relations between term-pairs. It uses distributional information on each term, and path-based information, encoded using an LSTM.

If you use LexNET for any published research, please include the following citation:

"Path-based vs. Distributional Information in Recognizing Lexical Semantic Relations"
Vered Shwartz and Ido Dagan. Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex-V), in COLING 2016. link

LexNET participated in the CogALex-V Shared Task on the Corpus-Based Identification of Semantic Relations, and achieved the best performance among the competitors on subtask 2 (semantic relation classification). The following paper describes the submission:

"CogALex-V Shared Task: LexNET - Integrated Path-based and Distributional Method for the Identification of Semantic Relations"
Vered Shwartz and Ido Dagan. Proceedings of the 5th Workshop on Cognitive Aspects of the Lexicon (CogALex-V), in COLING 2016. link

To start using LexNET, read the Quick Start or the Detailed Guide.

• Using dynet instead of pycnn
• Making the resource creation time and memory efficient

• Too many paths in parse_wikipedia (see issue #2)

• To reproduce the results reported in the paper, please use V1.
• The pre-processed corpus files are available for V2 now as well!