CA-EHN: Commonsense Word Analogy from E-HowNet (original) (raw)

CA-EHN: Commonsense Analogy from E-HowNet

2020

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 of words with only dozens of pre-defined relations, mostly morphological relations and named entities. In this work, we model commonsense knowledge down to word-level analogical reasoning by leveraging E-HowNet, an ontology that annotates 88K Chinese words with their structured sense definitions and English translations. We present CA-EHN, the first commonsense word analogy dataset containing 90,505 analogies covering 5,656 words and 763 relations. Experiments show that CA-EHN stands out as a great indicator of how well word representations embed commonsense knowledge. The dataset is publicly available at https://github.com/ckiplab/CA-EHN.

Analogical Reasoning with a Synergy of WordNet and HowNet

2006

WordNet and HowNet are large-scale lexical resources that adopt complementary perspectives toward semantic representation. WordNet is differential, inasmuch as it provides a rich taxonomic structure but little in the way of explicit propositional content. HowNet is constructive, and dedicates its representational energies to the explicit definition of relational structures for each lexico-conceptual entry. For purposes of analogy, no one approach is best. Rather, a synergy of both is required, since analogy is a knowledge-hungry process that demands both taxonomic richness and causally descriptive propositional structure. In this paper we consider how such a synergy might be achieved, and how it can be exploited to support a robust model of analogical reasoning.

Multilingual Culture-Independent Word Analogy Datasets

2020

In text processing, deep neural networks mostly use word embeddings as an input. Embeddings have to ensure that relations between words are reflected through distances in a high-dimensional numeric space. To compare the quality of different text embeddings, typically, we use benchmark datasets. We present a collection of such datasets for the word analogy task in nine languages: Croatian, English, Estonian, Finnish, Latvian, Lithuanian, Russian, Slovenian, and Swedish. We designed the monolingual analogy task to be much more culturally independent and also constructed cross-lingual analogy datasets for the involved languages. We present basic statistics of the created datasets and their initial evaluation using fastText embeddings.

Embedding Semantic Relations into Word Representations

Learning representations for semantic relations is important for various tasks such as analogy detection , relational search, and relation classification. Although there have been several proposals for learning representations for individual words, learning word representations that explicitly capture the semantic relations between words remains under developed. We propose an unsupervised method for learning vector representations for words such that the learnt representations are sensitive to the semantic relations that exist between two words. First, we extract lexical patterns from the co-occurrence contexts of two words in a corpus to represent the semantic relations that exist between those two words. Second, we represent a lexical pattern as the weighted sum of the representations of the words that co-occur with that lexical pattern. Third, we train a binary classifier to detect relationally similar vs. non-similar lexical pattern pairs. The proposed method is unsupervised in ...

OMCSNet: A Commonsense Inference Toolkit

2003

Large, easy-to-use semantic networks of symbolic linguistic knowledge such as WordNet and MindNet have become staple resources for semantic analysis tasks from query expansion to word-sense disambiguation.

(Presentation) Fitting Semantic Relations to Word Embeddings

Proceedings of the 10th Global Wordnet Conference, 2019

We fit WordNet relations to word embeddings, using 3CosAvg and LRCos, two set-based methods for analogy resolution, and introduce 3CosWeight, a new, weighted variant of 3CosAvg. We test the performance of the resulting semantic vectors in lexicographic semantics tests, and show that none of the tested classifiers can learn symmetric relations like synonymy and antonymy, since the source and target words of these relations are the same set. By contrast, with the asymmetric relations (hyperonymy / hyponymy and meronymy), both 3CosAvg and LRCos clearly outperform the baseline in all cases, while 3CosWeight attained the best scores with hyponymy and meronymy, suggesting that this new method could provide a useful alternative to previous approaches.

Analogy Generation with HowNet

2005

Analogy is a powerful boundary-transcending process that exploits a conceptual system's ability to perform controlled generalization in one domain and re-specialization into another. The result of this semantic leap is the transference of meaning from one concept to another from which metaphor derives its name (literally: to carry over). Such generalization and re-specialization can be achieved using a variety of representations and techniques, most notably abstraction via a taxonomic backbone, or selective projection via structure-mapping on propositional content. In this paper we explore the extent to which a bilingual lexical ontology for English and Chinese, called HowNet, can support both approaches to analogy.

FAME: Flexible, Scalable Analogy Mappings Engine

arXiv (Cornell University), 2023

Analogy is one of the core capacities of human cognition; when faced with new situations, we often transfer prior experience from other domains. Most work on computational analogy relies heavily on complex, manually crafted input. In this work, we relax the input requirements, requiring only names of entities to be mapped. We automatically extract commonsense representations and use them to identify a mapping between the entities. Unlike previous works, our framework can handle partial analogies and suggest new entities to be added. Moreover, our method's output is easily interpretable, allowing for users to understand why a specific mapping was chosen. Experiments show that our model correctly maps 81.2% of classical 2x2 analogy problems (guess level=50%). On larger problems, it achieves 77.8% accuracy (mean guess level=13.1%). In another experiment, we show our algorithm outperforms human performance, and the automatic suggestions of new entities resemble those suggested by humans. We hope this work will advance computational analogy by paving the way to more flexible, realistic input requirements, with broader applicability.

Extracting Commonsense Properties from Embeddings with Limited Human Guidance

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2018

Intelligent systems require common sense, but automatically extracting this knowledge from text can be difficult. We propose and assess methods for extracting one type of commonsense knowledge, object-property comparisons, from pretrained embeddings. In experiments, we show that our approach exceeds the accuracy of previous work but requires substantially less hand-annotated knowledge. Further, we show that an active learning approach that synthesizes common-sense queries can boost accuracy.

CogALex-V Shared Task: GHHH - Detecting Semantic Relations via Word Embeddings

2016

This paper describes our system submission to the CogALex-2016 Shared Task on Corpus-Based Identification of Semantic Relations. Our system won first place for Task-1 and second place for Task-2. The evaluation results of our system on the test set is 88.1% (79.0% for TRUE only) f-measure for Task-1 on detecting semantic similarity, and 76.0% (42.3% when excluding RANDOM) for Task-2 on identifying finer-grained semantic relations. In our experiments, we try word analogy, linear regression, and multi-task Convolutional Neural Networks (CNNs) with word embeddings from publicly available word vectors. We found that linear regression performs better in the binary classification (Task-1), while CNNs have better performance in the multi-class semantic classification (Task-2). We assume that word analogy is more suited for deterministic answers rather than handling the ambiguity of one-to-many and many-to-many relationships. We also show that classifier performance could benefit from balan...