Open Access. Powered by Scholars. Published by Universities.®
- Keyword
-
- Machine learning (2)
- Budget (1)
- Computational semantics (1)
- Corpus bias (1)
- Deep learning (1)
-
- Embodiment (1)
- Ephemeral data (1)
- Error annotation (1)
- F-score (1)
- Factored models (1)
- Feature analysis (1)
- GIS (1)
- Gain (1)
- Hate speech (1)
- Human evaluation (1)
- Hypernym detection (1)
- Idiom dictionary (1)
- Idiom identification (1)
- Landscape archaeology (1)
- Linguistic resource creation (1)
- Mesoamerica (1)
- Model evaluation (1)
- Multidimensional quality metrics (MQM) (1)
- Neural machine translation (1)
- Photogrammetry (1)
- Phrase-based machine translation (1)
- Replicability (1)
- Statistical machine translation (1)
- Virtual reality (1)
- Word embeddings (1)
Articles 1 - 5 of 5
Full-Text Articles in Other Computer Engineering
Using Virtual Reality And Photogrammetry To Enrich 3d Object Identity, Cole Juckette, Heather Richards-Rissetto, Hector Eluid Guerra Aldana, Norman Martinez
Using Virtual Reality And Photogrammetry To Enrich 3d Object Identity, Cole Juckette, Heather Richards-Rissetto, Hector Eluid Guerra Aldana, Norman Martinez
Department of Anthropology: Faculty Publications
The creation of digital 3D models for cultural heritage is commonplace. With the advent of efficient and cost effective technologies archaeologists are making a plethora of digital assets. This paper evaluates the identity of 3D digital assets and explores how to enhance or expand that identity by integrating photogrammetric models into VR. We propose that when a digital object acquires spatial context from its virtual surroundings, it gains an identity in relation to that virtual space, the same way that embedding the object with metadata gives it a specific identity through its relationship to other information. We explore this concept …
Examining A Hate Speech Corpus For Hate Speech Detection And Popularity Prediction, Filip Klubicka, Raquel Fernandez
Examining A Hate Speech Corpus For Hate Speech Detection And Popularity Prediction, Filip Klubicka, Raquel Fernandez
Other resources
As research on hate speech becomes more and more relevant every day, most of it is still focused on hate speech detection. By attempting to replicate a hate speech detection experiment performed on an existing Twitter corpus annotated for hate speech, we highlight some issues that arise from doing research in the field of hate speech, which is essentially still in its infancy. We take a critical look at the training corpus in order to understand its biases, while also using it to venture beyond hate speech detection and investigate whether it can be used to shed light on other …
Is It Worth It? Budget-Related Evaluation Metrics For Model Selection, Filip Klubicka, Giancarlo Salton, John D. Kelleher
Is It Worth It? Budget-Related Evaluation Metrics For Model Selection, Filip Klubicka, Giancarlo Salton, John D. Kelleher
Conference papers
Projects that set out to create a linguistic resource often do so by using a machine learning model that pre-annotates or filters the content that goes through to a human annotator, before going into the final version of the resource. However, available budgets are often limited, and the amount of data that is available exceeds the amount of annotation that can be done. Thus, in order to optimize the benefit from the invested human work, we argue that the decision on which predictive model one should employ depends not only on generalized evaluation metrics, such as accuracy and F-score, but …
Adapt At Semeval-2018 Task 9: Skip-Gram Word Embeddings For Unsupervised Hypernym Discovery In Specialised Corpora, Alfredo Maldonado, Filip Klubicka
Adapt At Semeval-2018 Task 9: Skip-Gram Word Embeddings For Unsupervised Hypernym Discovery In Specialised Corpora, Alfredo Maldonado, Filip Klubicka
Other resources
This paper describes a simple but competitive unsupervised system for hypernym discovery. The system uses skip-gram word embeddings with negative sampling, trained on specialised corpora. Candidate hypernyms for an input word are predicted based on cosine similar- ity scores. Two sets of word embedding mod- els were trained separately on two specialised corpora: a medical corpus and a music indus- try corpus. Our system scored highest in the medical domain among the competing unsu- pervised systems but performed poorly on the music industry domain. Our approach does not depend on any external data other than raw specialised corpora.
Quantitative Fine-Grained Human Evaluation Of Machine Translation Systems: A Case Study On English To Croatian, Filip Klubicka, Antonio Toral, Victor Manuel Sanchez-Cartagena
Quantitative Fine-Grained Human Evaluation Of Machine Translation Systems: A Case Study On English To Croatian, Filip Klubicka, Antonio Toral, Victor Manuel Sanchez-Cartagena
Articles
This paper presents a quantitative fine-grained manual evaluation approach to comparing the performance of different machine translation (MT) systems. We build upon the well-established Multidimensional Quality Metrics (MQM) error taxonomy and implement a novel method that assesses whether the differences in performance for MQM error types between different MT systems are statistically significant. We conduct a case study for English-to- Croatian, a language direction that involves translating into a morphologically rich language, for which we compare three MT systems belonging to different paradigms: pure phrase-based, factored phrase-based and neural. First, we design an MQM-compliant error taxonomy tailored to the relevant …