UMNDuluth at SemEval-2016 Task 14: WordNet’s Missing Lemmas

Proceedings of SemEval-2016, pages 1346–1350, San Diego, California, June 16-17, 2016. c⃝2016 Association for Computational Linguistics UMNDuluth at SemEval-2016 Task 14: WordNet’s Missing Lemmas Jon Rusert & Ted Pedersen Department of Computer Science University of Minnesota Duluth, MN USA {ruse0008,tpederse}@d.umn.edu Abstract This paper presents a solution to Semeval 2016 Task 14 which asks for a system that is able to insert new lemmas into WordNet. Our system aims to do this by overlapping words in the definitions of the to-be-inserted lemma and all senses in WordNet. This paper includes the results of our system and also includes the baseline provided by Task 14, with our system scoring higher than the random baseline, and lower than the first word baseline. 1 Introduction Semeval 2016 Task 14 called for a system that could help enrich the WordNet taxonomy with new words and their senses. This translates to inserting new lemmas and senses that were previously not in WordNet into their (human perceived) correct place. The system was also to determine whether a sense would merge into the chosen synset or attach itself as a new hyponym. Task 14 allowed for one of two types of systems: 1. A resource-aware system, which could use any dictionary, or 2. Constrained, which used any resource other than a dictionary. We opted with the former, resource-aware. While any dictionary could be used, we chose to use the definitions provided in the data set from Wiktionary, along with definitions from WordNet. 2 Methods Our system solves the given problem in four steps: 1. Pre-processing: Acquire all necessary data from WordNet and store it in one step. The data needed includes each word’s definitions, hypernyms, hyponyms, and synsets. 2. Overlaps: Score each sense on how well it matches each new lemma. 3. Refining chosen sense: Verify that the sense chosen in overlaps was more deserving than the other senses of the same lemma. 4. Determining attach or merge: Decide whether or not the new lemma should be attached to the synset of the chosen sense, or merged into it. 2.1 Pre-processing As the implementation of our system was underway, it was clear that the system would be making a large amount of calls to WordNet. As we accessed more and more data from WordNet1, our program took longer to finish each time which created a problem for testing out changes quickly. In response, the pre- processing method was created. Pre-processing aims to consolidate all calls to WordNet in the beginning of the program, so no duplicate calls need to be made. It does this by first obtaining all nouns and verbs from WordNet and storing them in their respective arrays (one ar- ray for nouns and one for verbs). Pre-processing 1http://search.cpan.org/dist/WordNet- QueryData/QueryData.pm 1346 then iterates through each word and retrieves each sense of each word, since the senses are what will determine which synset the new lemma will be merged or attached to later on. The senses are stored in a separate array, which is iterated through, one …

Content truncated to 500 words