Neural GRANNy at SemEval-2019 Task 2: A combined approach for better modeling of semantic relationships in semantic frame induction

Proceedings of the 13th International Workshop on Semantic Evaluation (SemEval-2019), pages 31–38 Minneapolis, Minnesota, USA, June 6–7, 2019. ©2019 Association for Computational Linguistics 31 Neural GRANNy at SemEval-2019 Task 2: A combined approach for better modeling of semantic relationships in semantic frame induction Nikolay Arefyev1,2, Boris Sheludko1,2, Adis Davletov1,2, Dmitry Kharchev1,2, Alex Nevidomsky1, and Alexander Panchenko3,4 1Samsung R&D Institute Russia, Moscow, Russia 2Lomonosov Moscow State University, Moscow, Russia 3Skolkovo Institute of Science and Technology, Moscow, Russia 4Language Technology Group, University of Hamburg, Hamburg, Germany Abstract We describe our solutions for semantic frame and role induction subtasks of SemEval 2019 Task 2. Our approaches got the highest scores, and the solution for the frame induction prob- lem officially took the first place. The main contributions of this paper are related to the se- mantic frame induction problem. We propose a combined approach that employs two differ- ent types of vector representations: dense rep- resentations from hidden layers of a masked language model, and sparse representations based on substitutes for the target word in the context. The first one better groups synonyms, the second one is better at disambiguating homonyms. Extending the context to include nearby sentences improves the results in both cases. New Hearst-like patterns for verbs are introduced that prove to be effective for frame induction. Finally, we propose an approach to selecting the number of clusters in agglomera- tive clustering. 1 Introduction Semeval-2019 Task 2 consisted of three subtasks, this paper presents solutions to all three which were all performing better than other submitted approaches. The first solution officially took the first place in the competition, the other two used tuning on the development set provided by the or- ganizers, which was then interpreted as using ad- ditional corpora. Semantic Frame Induction (Subtask A) is the task of grouping target word occurrences in a text corpus according to their frame (meaning and semantic arguments structure). Target words are usually verbs, nouns, and adjectives (these have argument structure; however in the shared task dataset only verbs were present). For in- stance, the verbs rise, fall and climb in the sen- tences The dollar is rising, which makes Rus- sian economy unstable and The dollar fell 1% in September after climbing 2% in August should be clustered together, while the verb climb in sen- tences like People climb mountains should be clus- tered separately. For the sake of brevity, occur- rences of different words sharing the same frame will be called synonyms, and occurrences of the same word belonging to different frames will be called homonyms. This may violate the traditional meaning of these terms. For instance, fall and rise are not considered synonyms in the classi- cal sense. Semantic Role Induction refers to find- ing realizations of semantic arguments in text and relating them to corresponding semantic frame slots. Generic role induction (subtask B.2) re- quires a small number of frame-independent roles like Agent, Patient, Theme, etc. Frame-specific role induction (subtask B.1) allows labeling ar- guments of each frame independently …

Content truncated to 500 words