Measuring Numerical Common Sense: Is A Word Embedding Approach Effective?
Numerical common sense (e.g., ``a person with a height of 2m is very tall'') is essential when deploying artificial intelligence (AI) systems in society. To predict ranges of small and large values for a given target noun and unit, previous studies have implemented a rule-based method that processed numeric values appearing in a natural language by using template matching. To obtain numerical knowledge, crawled textual data from web pages are frequently used as the input in the above method. Although this is an important task, few studies have addressed the availability of numerical common sense extracted from corresponding textual information. To this end, we first used a crowdsourcing service to obtain sufficient data for a subjective agreement on numerical common sense. Second, to examine whether common sense is attributed to current word embedding, we examined the performance of a regressor trained on the obtained data. In comparison with humans, the performance of an automatic relevance determination regression model was good, particularly when the unit was yen (a maximum correlation coefficient of 0.57). Although all the regression approach with word embedding does not predict values with high correlation coefficients, this word-embedding method could potentially contribute to construct numerical common sense for AI deployment.
Code (0)
등록된 구현이 없습니다.
Tasks
Common Sense ReasoningregressionTemplate MatchingSimilar Papers 제목 키워드 기반
Modeling Tension in Stories via Commonsense Reasoning and Emotional Word Embeddings
Dramatic tension is crucial for generating interesting stories. This paper aims to model dramatic tension from a story text using neural commonsense-reasoning language models and emotional word embeddings. We also propos…
Word EmbeddingsCLUSE: Cross-Lingual Unsupervised Sense Embeddings
This paper proposes a modularized sense induction and representation learning model that jointly learns bilingual sense embeddings that align well in the vector space, where the cross-lingual signal in the English-Chines…
Representation LearningWord SimilarityBERT Has Uncommon Sense: Similarity Ranking for Word Sense BERTology
An important question concerning contextualized word embedding (CWE) models like BERT is how well they can represent different word senses, especially those in the long tail of uncommon senses. Rather than build a WSD sy…
RetrievalCA-EHN: Commonsense Analogy from E-HowNet
Embedding commonsense knowledge is crucial for end-to-end models to generalize inference beyond training corpora. However, existing word analogy datasets have tended to be handcrafted, involving permutations of hundreds …
Birds have four legs?! NumerSense: Probing Numerical Commonsense Knowledge of Pre-trained Language Models
Recent works show that pre-trained language models (PTLMs), such as BERT, possess certain commonsense and factual knowledge. They suggest that it is promising to use PTLMs as "neural knowledge bases" via predicting maske…
Diagnostic