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. However there has traditionally been a disconnect between research on class-imbalanced learning and mitigating bias, and only recently have the two been looked at through a common lens. In this work we evaluate long-tail learning methods for tweet sentiment and occupation classification, and extend a margin-loss based approach with methods to enforce fairness. We empirically show through controlled experiments that the proposed approaches help mitigate both class imbalance and demographic biases.

We present our work on aligning the Unified Medical Language System (UMLS) to Wikipedia, to facilitate manual alignment of the two resources. We propose a cross-lingual neural reranking model to match a UMLS concept with a Wikipedia page, which achieves a recall@1 of 72%, a substantial improvement of 20% over word- and char-level BM25, enabling manual alignment with minimal effort. We release our resources, including ranked Wikipedia pages for 700k UMLS concepts, and WikiUMLS, a dataset for training and evaluation of alignment models between UMLS and Wikipedia. This will provide easier access to Wikipedia for health professionals, patients, and NLP systems, including in multilingual settings.

Although the Indonesian language is spoken by almost 200 million people and the 10th mostspoken language in the world, it is under-represented in NLP research. Previous work on Indonesian has been hampered by a lack of annotated datasets, a sparsity of language resources, and a lack of resource standardization. In this work, we release the INDOLEM dataset comprising seven tasks for the Indonesian language, spanning morpho-syntax, semantics, and discourse. We additionally release INDOBERT, a new pre-trained language model for Indonesian, and evaluate it over INDOLEM, in addition to benchmarking it against existing resources. Our experiments show that INDOBERT achieves state-of-the-art performance over most of the tasks in INDOLEM.

In cross-lingual transfer, NLP models over one or more source languages are applied to a low- resource target language. While most prior work has used a single source model or a few carefully selected models, here we consider a “massive” setting with many such mod- els. This setting raises the problem of poor transfer, particularly from distant languages. We propose two techniques for modulating the transfer, suitable for zero-shot or few-shot learning, respectively. Evaluating on named entity recognition, we show that our tech- niques are much more effective than strong baselines, including standard ensembling, and our unsupervised method rivals oracle selec- tion of the single best individual model.

Social media user geolocation is vital to many applications such as event detection. In this paper, we propose GCN, a multiview geolocation model based on Graph Convolutional Networks, that uses both text and network context. We compare GCN to the state-of-the-art, and to two baselines we propose, and show that our model achieves or is competitive with the state-of-the-art over three benchmark geolocation datasets when sufficient supervision is available. We also evaluate GCN under a minimal supervision scenario, and show it outperforms baselines. We find that highway network gates are essential for controlling the amount of useful neighbourhood expansion in GCN.

We propose a method for embedding two- dimensional locations in a continuous vec- tor space using a neural network-based model incorporating mixtures of Gaussian distributions, presenting two model vari- ants for text-based geolocation and lexi- cal dialectology. Evaluated over Twitter data, the proposed model outperforms con- ventional regression-based geolocation and provides a better estimate of uncertainty. We also show the effectiveness of the rep- resentation for predicting words from loca- tion in lexical dialectology, and evaluate it using the DARE dataset.

We propose a simple yet effective textbased 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. As part of our analysis of dialectal terms, we release DAREDS, a dataset for evaluating dialect term detection methods.

We present pigeo, a Python geolocation prediction tool that predicts a location for a given text input or Twitter user. We discuss the design, implementation and application of pigeo, and empirically evaluate it. pigeo is able to geolocate informal text and is a very useful tool for users who require a free and easy-to-use, yet accurate geolocation service based on pre-trained models. Additionally, users can train their own models easily using pigeo’s API.

Abstract 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) the incorporation of text-based geolocation priors for test users. Experiments over three Twitter benchmark datasets achieve state-of-the-art results, and demonstrate the effectiveness of the enhancements.

Abstract 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 benchmarking of the two approaches over comparable datasets. We bring the two threads of research together in first proposing a text-based method based on adaptive grids, followed by a hybrid network- and text-based method. Evaluating over three Twitter datasets, we show that the empirical difference between textand network-based methods is not great, and that hybridisation of the two is superior to the component methods, especially in contexts where the user graph is not well connected. We achieve state-of-the-art results on all three datasets.