Article Structure
Abstract
In this paper, we propose a computational approach to generate neologisms consisting of homophonic puns and metaphors based on the category of the service to be named and the properties to be underlined.
Introduction
A catchy, memorable and creative name is an important key to a successful business since the name provides the first image and defines the identity of the service to be promoted.
Related Work
In this section, we will analyze the state of the art concerning the naming task from three different aspects: i) linguistic ii) computational iii) commercial.
Dataset and Annotation
In order to create a gold standard for linguistic creativity in naming, collect the common creativity devices used in the naming process and determine the suitable ones for automation, we conducted an annotation task on a dataset of 1000 brand and company names from various domains (Ozbal et al., 2012).
System Description
The resource that we have obtained after the annotation task provides us with a starting point to study and try to replicate the linguistic and cognitive processes behind the creation of a successful name.
Evaluation
We evaluated the performance of our system with a manual annotation in which 5 annotators judged a set of neologisms along 4 dimensions: 1) appropriateness, i.e.
Topics
WordNet
- HAHAcronym is mainly based on lexical substitution via semantic field opposition, rhyme, rhythm and semantic relations such as antonyms retrieved from WordNet (Stark and Riesenfeld, 1998) for adjectives.Page 2, “Related Work”
- To further increase the size of the ingredient list, we utilize another resource called WordNet (Miller, 1995), which is a large lexical database for English.Page 4, “System Description”
- In WordNet , nouns, verbs, adjectives and adverbs are grouped into sets of cognitive synonyms called synsets.Page 4, “System Description”
- Each synset in WordNet expresses a different concept and they are connected to each other with lexical, semantic and conceptual relations.Page 4, “System Description”
- We use the direct hypernym relation of WordNet to retrieve the superordinates of the category word (e.g.Page 4, “System Description”
- We prefer to use this relation of WordNet instead of the relation “13A” inPage 4, “System Description”
- Although we can obtain only the direct hypernyms in WordNet , no such mechanism exists in ConceptNet.Page 5, “System Description”
- In addition, while WordNet has been built by linguists, ConceptNet is built from the contributions of many thousands of people across the Web and naturally it also contains a lot of noise.Page 5, “System Description”
- In WordNet we can decide what relations to explore, with the result of a more precise process with possibly less recall.Page 5, “System Description”
- From the list of lemmas, we only consider the ones which appear in WordNet as a noun.Page 5, “System Description”
- The POS check to obtain only nouns is conducted with a lookup in WordNet as before.Page 5, “System Description”
See all papers in Proc. ACL 2012 that mention WordNet.
See all papers in Proc. ACL that mention WordNet.
Back to top.
language model
- To check the likelihood and well-formedness of the new string after the replacement, we learn a 3- gram language model with absolute smoothing.Page 7, “System Description”
- For leam-ing the language model , we only consider the words in the CMU pronunciation dictionary which also exist in WordNet.Page 7, “System Description”
- We remove the words containing at least one trigram which is very unlikely according to the language model .Page 7, “System Description”
- Therefore, we implemented a ranking mechanism which used a hybrid scoring method by giving equal weights to the language model and the normalized phonetic similarity.Page 7, “Evaluation”
See all papers in Proc. ACL 2012 that mention language model.
See all papers in Proc. ACL that mention language model.
Back to top.
natural language
- We describe all the linguistic resources and natural language processing techniques that we have exploited for this task.Page 1, “Abstract”
- naming agencies and naive generators) that can be used for obtaining name suggestions, we propose a system which combines several linguistic resources and natural language processing (NLP) techniques to generate creative names, more specifically neologisms based on homophonic puns and metaphors.Page 1, “Introduction”
- Accordingly, we have made a systematic attempt to replicate these processes, and implemented a system which combines methods and resources used in various areas of Natural Language Processing (NLP) to create neologisms based on homophonic puns and metaphors.Page 3, “System Description”
- This resource consists of nodes representing concepts which are in the form of words or short phrases of natural language , and labeled relations between them.Page 4, “System Description”
See all papers in Proc. ACL 2012 that mention natural language.
See all papers in Proc. ACL that mention natural language.
Back to top.
semantically related
- HAHAcronym is mainly based on lexical substitution via semantic field opposition, rhyme, rhythm and semantic relations such as antonyms retrieved from WordNet (Stark and Riesenfeld, 1998) for adjectives.Page 2, “Related Work”
- The task that we deal with requires: 1) reasoning of relations between entities and concepts; 2) understanding the desired properties of entities determined by users; 3) identifying semantically related terms which are also consistent with the objectives of the advertisement; 4) finding terms which are suitable metaphors for the properties that need to be emphasized; 5) reasoningPage 3, “System Description”
- 4.3 Adding semantically related wordsPage 4, “System Description”
- It should be noted that we do not consider any other statistical or knowledge based techniques for semantic relatedness .Page 5, “System Description”
See all papers in Proc. ACL 2012 that mention semantically related.
See all papers in Proc. ACL that mention semantically related.
Back to top.
hypernyms
- We use the direct hypernym relation of WordNet to retrieve the superordinates of the category word (e.g.Page 4, “System Description”
- Although we can obtain only the direct hypernyms in WordNet, no such mechanism exists in ConceptNet.Page 5, “System Description”
- In addition to the direct hypernyms of the category word, we increase the size of the ingredient list by adding synonyms of the category word, the new words coming from the relations and the properties determined by the user.Page 5, “System Description”
See all papers in Proc. ACL 2012 that mention hypernyms.
See all papers in Proc. ACL that mention hypernyms.
Back to top.
synset
- In WordNet, nouns, verbs, adjectives and adverbs are grouped into sets of cognitive synonyms called synsets .Page 4, “System Description”
- Each synset in WordNet expresses a different concept and they are connected to each other with lexical, semantic and conceptual relations.Page 4, “System Description”
- To create the dataset, we first compiled a list of 50 categories by selecting 50 hyponyms of the synset consumer goods in WordNet.Page 7, “Evaluation”
See all papers in Proc. ACL 2012 that mention synset.
See all papers in Proc. ACL that mention synset.
Back to top.
