The SIGMORPHON 2022 shared task on morpheme segmentation challenged systems to decompose a word into a sequence of morphemes and covered most types of morphology: compounds, derivations, and inflections. Subtask 1, word-level morpheme segmentation, covered 5 million words in 9 languages (Czech, English, Spanish, Hungarian, French, Italian, Russian, Latin, Mongolian) and received 13 system submissions from 7 teams and the best system averaged 97.29% F1 score across all languages, ranging English (93.84%) to Latin (99.38%). Subtask 2, sentence-level morpheme segmentation, covered 18,735 sentences in 3 languages (Czech, English, Mongolian), received 10 system submissions from 3 teams, and the best systems outperformed all three state-of-the-art subword tokenization methods (BPE, ULM, Morfessor2) by 30.71% absolute. To facilitate error analysis and support any type of future studies, we released all system predictions, the evaluation script, and all gold standard datasets. 1

Mood inference with mobile sensing data has been studied in ubicomp literature over the last decade. This inference enables context-aware and personalized user experiences in general mobile apps and valuable feedback and interventions in mobile health apps. However, even though model generalization issues have been highlighted in many studies, the focus has always been on improving the accuracies of models using different sensing modalities and machine learning techniques, with datasets collected in homogeneous populations. In contrast, less attention has been given to studying the performance of mood inference models to assess whether models generalize to new countries. In this study, we collected a mobile sensing dataset with 329K self-reports from 678 participants in eight countries (China, Denmark, India, Italy, Mexico, Mongolia, Paraguay, UK) to assess the effect of geographical diversity on mood inference models. We define and evaluate country-specific (trained and tested within a country), continent-specific (trained and tested within a continent), country-agnostic (tested on a country not seen on training data), and multi-country (trained and tested with multiple countries) approaches trained on sensor data for two mood inference tasks with population-level (non-personalized) and hybrid (partially personalized) models. We show that partially personalized country-specific models perform the best yielding area under the receiver operating characteristic curve (AUROC) scores of the range 0.78--0.98 for two-class (negative vs. positive valence) and 0.76--0.94 for three-class (negative vs. neutral vs. positive valence) inference. Further, with the country-agnostic approach, we show that models do not perform well compared to country-specific settings, even when models are partially personalized. We also show that continent-specific models outperform multi-country models in the case of Europe. Overall, we uncover generalization issues of mood inference models to new countries and how the geographical similarity of countries might impact mood inference.

This paper describes a method to enrich lexical resources with content relating to linguistic diversity, based on knowledge from the field of lexical typology. We capture the phenomenon of diversity through the notions of lexical gap and language-specific word and use a systematic method to infer gaps semi-automatically on a large scale. As a first result obtained for the domain of kinship terminology, known to be very diverse throughout the world, we publish a lexico-semantic resource consisting of 198 domain concepts, 1,911 words, and 37,370 gaps covering 699 languages. We see potential in the use of resources such as ours for the improvement of a variety of cross-lingual NLP tasks, which we demonstrate through a downstream application for the evaluation of machine translation systems.

No abstract

Lists of semantically related words are better recalled on immediate memory tests than otherwise equivalent lists of unrelated words. However, measuring the degree of relatedness is not straightforward. We report three experiments that assess the ability of various measures of semantic relatedness—including latent semantic analysis (LSA), GloVe, fastText, and a number of measures based on WordNet—to predict whether two lists of words will be differentially recalled. In Experiment 1, all measures except LSA correctly predicted the observed better recall of the related than the unrelated list. In Experiment 2, all measures except JCN predicted that abstract words would be recalled equally as well as concrete words because of their enhanced semantic relatedness. In Experiment 3, LSA, GLoVe, and fastText predicted an enhanced concreteness effect because the concrete words were more related; three WordNet measures predicted a small concreteness effect because the abstract and concrete words did not differ in semantic relatedness; and three other WordNet measures predicted no concreteness effect because the abstract words were more related than the concrete words. A small concreteness effect was observed. Over the three experiments, only two measures, both based on simple WordNet path length, predicted all three results. We suggest that the results are not unexpected because semantic processing in episodic memory experiments differs from that in reading, similarity judgment, and analogy tasks which are the most common way of assessing such measures.