Search Results for author: Afshin Rahimi

Found 22 papers, 6 papers with code

Automatic Extraction of Structured Mineral Drillhole Results from Unstructured Mining Company Reports

1 code implementation COLING (WNUT) 2022 Adam Dimeski, Afshin Rahimi

Aggregate mining exploration results can help companies and governments to optimise and police mining permits and operations, a necessity for transition to a renewable energy future, however, these results are buried in unstructured text.

Capacity Constraint Analysis Using Object Detection for Smart Manufacturing

no code implementations31 Jan 2024 Hafiz Mughees Ahmad, Afshin Rahimi, Khizer Hayat

In this study, we have initially developed a Convolutional Neural Network (CNN) based OD model to tackle this issue.

Object object-detection +1

Fairness-aware Class Imbalanced Learning

no code implementations EMNLP 2021 Shivashankar Subramanian, Afshin Rahimi, Timothy Baldwin, Trevor Cohn, Lea Frermann

Class imbalance is a common challenge in many NLP tasks, and has clear connections to bias, in that bias in training data often leads to higher accuracy for majority groups at the expense of minority groups.

Fairness Long-tail Learning

Learning Causal Bayesian Networks from Text

no code implementations ALTA 2020 Farhad Moghimifar, Afshin Rahimi, Mahsa Baktashmotlagh, Xue Li

Causal relationships form the basis for reasoning and decision-making in Artificial Intelligence systems.

Decision Making

IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP

no code implementations COLING 2020 Fajri Koto, Afshin Rahimi, Jey Han Lau, Timothy Baldwin

Although the Indonesian language is spoken by almost 200 million people and the 10th most spoken language in the world, it is under-represented in NLP research.

Benchmarking Language Modelling

WikiUMLS: Aligning UMLS to Wikipedia via Cross-lingual Neural Ranking

1 code implementation COLING 2020 Afshin Rahimi, Timothy Baldwin, Karin Verspoor

We present our work on aligning the Unified Medical Language System (UMLS) to Wikipedia, to facilitate manual alignment of the two resources.

Does an LSTM forget more than a CNN? An empirical study of catastrophic forgetting in NLP

no code implementations ALTA 2019 Gaurav Arora, Afshin Rahimi, Timothy Baldwin

Catastrophic forgetting {---} whereby a model trained on one task is fine-tuned on a second, and in doing so, suffers a {``}catastrophic{''} drop in performance over the first task {---} is a hurdle in the development of better transfer learning techniques.

Continual Learning Transfer Learning

Massively Multilingual Transfer for NER

1 code implementation ACL 2019 Afshin Rahimi, Yuan Li, Trevor Cohn

In cross-lingual transfer, NLP models over one or more source languages are applied to a low-resource target language.

Cross-Lingual Transfer Few-Shot Learning +4

Twitter Geolocation using Knowledge-Based Methods

no code implementations WS 2018 Taro Miyazaki, Afshin Rahimi, Trevor Cohn, Timothy Baldwin

Automatic geolocation of microblog posts from their text content is particularly difficult because many location-indicative terms are rare terms, notably entity names such as locations, people or local organisations.

Entity Linking Graph Embedding +1

Continuous Representation of Location for Geolocation and Lexical Dialectology using Mixture Density Networks

1 code implementation EMNLP 2017 Afshin Rahimi, Timothy Baldwin, Trevor Cohn

We propose a method for embedding two-dimensional locations in a continuous vector space using a neural network-based model incorporating mixtures of Gaussian distributions, presenting two model variants for text-based geolocation and lexical dialectology.

regression

A Neural Model for User Geolocation and Lexical Dialectology

no code implementations ACL 2017 Afshin Rahimi, Trevor Cohn, Timothy Baldwin

We propose a simple yet effective text- based user geolocation model based on a neural network with one hidden layer, which achieves state of the art performance over three Twitter benchmark geolocation datasets, in addition to producing word and phrase embeddings in the hidden layer that we show to be useful for detecting dialectal terms.

It is not all downhill from here: Syllable Contact Law in Persian

no code implementations3 Oct 2015 Afshin Rahimi, Moharram Eslami, Bahram Vazirnezhad

Syllable contact pairs crosslinguistically tend to have a falling sonority slope a constraint which is called the Syllable Contact Law SCL In this study the phonotactics of syllable contacts in 4202 CVCCVC words of Persian lexicon is investigated The consonants of Persian were divided into five sonority categories and the frequency of all possible sonority slopes is computed both in lexicon type frequency and in corpus token frequency Since an unmarked phonological structure has been shown to diachronically become more frequent we expect to see the same pattern for syllable contact pairs with falling sonority slope The correlation of sonority categories of the two consonants in a syllable contact pair is measured using Pointwise Mutual Information

P-trac Procedure: The Dispersion and Neutralization of Contrasts in Lexicon

no code implementations3 Oct 2015 Afshin Rahimi, Bahram Vazirnezhad, Moharram Eslami

Cognitive acoustic cues have an important role in shaping the phonological structure of language as a means to optimal communication.

Twitter User Geolocation Using a Unified Text and Network Prediction Model

no code implementations IJCNLP 2015 Afshin Rahimi, Trevor Cohn, Timothy Baldwin

We propose a label propagation approach to geolocation prediction based on Modified Adsorption, with two enhancements:(1) the removal of "celebrity" nodes to increase location homophily and boost tractability, and (2) he incorporation of text-based geolocation priors for test users.

Exploiting Text and Network Context for Geolocation of Social Media Users

no code implementations HLT 2015 Afshin Rahimi, Duy Vu, Trevor Cohn, Timothy Baldwin

Research on automatically geolocating social media users has conventionally been based on the text content of posts from a given user or the social network of the user, with very little crossover between the two, and no bench-marking of the two approaches over compara- ble datasets.

Cannot find the paper you are looking for? You can Submit a new open access paper.