Exploring Vector Spaces for Semantic Relations

Gábor, Kata; Zargayouna, Haïfa; Buscaldi, Davide; Charnois, Thierry

doi:10.18653/v1/d17-1193

Cited by 11 publications

(6 citation statements)

References 23 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, we first compared the pure course2vec model with the course representations from the multi-factor course2vec model using instructor, department, and both as factors. To further explore improvements to performance, we concatenated the primary course representational layer (W n×v in Figure 1) with the output representation layer (W ′ v×n in Figure 1), as demonstrated to be effective in the language domain [10].…”

Section: Course2vec Vs Multi-factor Course2vecmentioning

confidence: 99%

Designing for serendipity in a university course recommendation system

Pardos

Jiang

2020

Proceedings of the Tenth International Conference on Learning Analytics &Amp; Knowledge

View full text Add to dashboard Cite

Collaborative filtering based algorithms, including Recurrent Neural Networks (RNN), tend towards predicting a perpetuation of past observed behavior. In a recommendation context, this can lead to an overly narrow set of suggestions lacking in serendipity and inadvertently placing the user in what is known as a "filter bubble. " In this paper, we grapple with the issue of the filter bubble in the context of a course recommendation system in production at a public university. Most universities in the United States encourage students to explore developing interests while simultaneously advising them to adhere to course taking norms which progress them towards graduation. These competing objectives, and the stakes involved for students, make this context a particularly meaningful one for investigating real-world recommendation strategies. We introduce a novel modification to the skip-gram model applied to nine years of historic course enrollment sequences to learn course vector representations used to diversify recommendations based on similarity to a student's specified favorite course. This model, which we call multifactor2vec, is intended to improve the semantics of the primary token embedding by also learning embeddings of potentially conflated factors of the token (e.g., instructor). Our offline testing found this model improved accuracy and recall on our course similarity and analogy validation sets over a standard skip-gram. Incorporating course catalog description text resulted in further improvements. We compare the performance of these models to the system's existing RNN-based recommendations with a user study of undergraduates (N = 70) rating six characteristics of their course recommendations. Results of the user study show a dramatic lack of novelty in RNN recommendations, a consequence of the filter bubble, and depict the characteristic trade-offs that make serendipity difficult to achieve.

show abstract

Section: Course2vec Vs Multi-factor Course2vecmentioning

confidence: 99%

Designing for serendipity in a university course recommendation system

Pardos

Jiang

2020

Proceedings of the Tenth International Conference on Learning Analytics &Amp; Knowledge

View full text Add to dashboard Cite

show abstract

“…They are based on the distributional hypothesis (Harris, 1954) and the assumption that meaning can be encoded in a vector space (Turney and Pantel, 2010;Erk, 2010). These approaches also search latent and independent components that underlie the behavior of words (Gábor et al, 2017;Mikolov et al, 2013a).…”

Section: Motivation For Semantic Unitsmentioning

confidence: 99%

A Simple Theoretical Model of Importance for Summarization

Peyrard¹

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Research on summarization has mainly been driven by empirical approaches, crafting systems to perform well on standard datasets with the notion of information Importance remaining latent. We argue that establishing theoretical models of Importance will advance our understanding of the task and help to further improve summarization systems. To this end, we propose simple but rigorous definitions of several concepts that were previously used only intuitively in summarization: Redundancy, Relevance, and Informativeness. Importance arises as a single quantity naturally unifying these concepts. Additionally, we provide intuitions to interpret the proposed quantities and experiments to demonstrate the potential of the framework to inform and guide subsequent works.

show abstract

“…Following Gábor et al (2017), we also report the accuracy (A) that would be achieved by the clustering if we assigned every cluster to the class that is most frequent in this cluster and then used the clustering as a classifier. classes (cls) shows how many classes were assigned to at least one of the clusters.…”

Section: Unsupervised Clusteringmentioning

confidence: 99%

Derivational Morphological Relations in Word Embeddings

Musil¹,

Vidra²,

Mareċek³

2019

Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP

View full text Add to dashboard Cite

Derivation is a type of a word-formation process which creates new words from existing ones by adding, changing or deleting affixes. In this paper, we explore the potential of word embeddings to identify properties of word derivations in the morphologically rich Czech language. We extract derivational relations between pairs of words from DeriNet, a Czech lexical network, which organizes almost one million Czech lemmata into derivational trees. For each such pair, we compute the difference of the embeddings of the two words, and perform unsupervised clustering of the resulting vectors. Our results show that these clusters largely match manually annotated semantic categories of the derivational relations (e.g. the relation 'bake-baker' belongs to category 'actor', and a correct clustering puts it into the same cluster as 'governgovernor').

show abstract

Exploring Vector Spaces for Semantic Relations

Cited by 11 publications

References 23 publications

Designing for serendipity in a university course recommendation system

Designing for serendipity in a university course recommendation system

A Simple Theoretical Model of Importance for Summarization

Derivational Morphological Relations in Word Embeddings

Contact Info

Product

Resources

About