Evaluating Ways of Adapting Word Similarity
People judge pairwise similarity by deciding which aspects of the words{'} meanings are relevant for the comparison of the given pair. However, computational representations of meaning rely on dimensions of the vector representation for similarity comparisons, without considering the specific pairing at hand. Prior work has adapted computational similarity judgments by using the softmax function in order to address this limitation by capturing asymmetry in human judgments. We extend this analysis by showing that a simple modification of cosine similarity offers a better correlation with human judgments over a comprehensive dataset. The modification performs best when the similarity between two words is calculated with reference to other words that are most similar and dissimilar to the pair.
Code (0)
등록된 구현이 없습니다.
Tasks
Word SimilarityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
B2SG: a TOEFL-like Task for Portuguese
Resources such as WordNet are useful for NLP applications, but their manual construction consumes time and personnel, and frequently results in low coverage. One alternative is the automatic construction of large resourc…
Towards a Gold Standard for Evaluating Danish Word Embeddings
This paper presents the process of compiling a model-agnostic similarity goal standard for evaluating Danish word embeddings based on human judgments made by 42 native speakers of Danish. Word embeddings resemble semanti…
Semantic SimilaritySemantic Textual SimilarityWord EmbeddingsWasserstein distances for evaluating cross-lingual embeddings
Word embeddings are high dimensional vector representations of words that capture their semantic similarity in the vector space. There exist several algorithms for learning such embeddings both for a single language as w…
Cross-Lingual Document ClassificationDocument ClassificationRetrievalSemantic Similarity+2Construction of a Japanese Word Similarity Dataset
An evaluation of distributed word representation is generally conducted using a word similarity task and/or a word analogy task. There are many datasets readily available for these tasks in English. However, evaluating d…
Word SimilarityDeriving continous grounded meaning representations from referentially structured multimodal contexts
Corpora of referring expressions paired with their visual referents are a good source for learning word meanings directly grounded in visual representations. Here, we explore additional ways of extracting from them word …
AttributeWord Embeddings