Search

Conversational AI such as smart speakers placed in home environments can accidentally activate and record people’s talk for a short time. What can such devices learn about people by listening in on ongoing conversations? Taking two commonly used speaker traits as an example, we present the results of an experiment that simulates Conversational AI eavesdropping on ongoing talk using transcriptions of naturalistic conversations in private settings. We show that a currently popular type of deep learning-based system can reliably predict if a speaker is “young”, “old”, “female” or “male” (age=99%, gender=82%) based on what they say in around 30 seconds. Our results exemplify how powerful current big data language models are when it comes to data-driven predictions of personal information based on how people talk, even when listening only for a short time. We conclude the experiment with a critical comment on the increasingly pervasive use of such user modeling technology to compute speaker traits, touching upon some potential ethical concerns, bias, and privacy issues.

In this paper we present Uniform Meaning Representation (UMR), a meaning representation designed to annotate the semantic content of a text. UMR is primarily based on Abstract Meaning Representation (AMR), an annotation framework initially designed for English, but also draws from other meaning representations. UMR extends AMR to other languages, particularly morphologically complex, low-resource languages. UMR also adds features to AMR that are critical to semantic interpretation and enhances AMR by proposing a companion document-level representation that captures linguistic phenomena such as coreference as well as temporal and modal dependencies that potentially go beyond sentence boundaries.

Interactions among the environment, humans and language underlie many of the most pressing challenges we face today. This study investigates the use of different verbs to encode various weather events in Sinitic languages, a language family spoken over a wide range of climates and with 3000 years of continuous textual documentation. We propose to synergise the many concepts of kinesis that grew from Aristotle’s original ideas to account for the correlation between meteorological events and their linguistic encoding. It is observed that the two most salient key factors of weather events, i.e., mass of weather substances and speed of weather processes, are the two contributing components of kinetic energy. Leveraging the linguistic theory that kinesis underpins conceptualisation of verb classes, this paper successfully accounts for the selection of verbs for different meteorological events in all Sinitic languages in terms of both language variations and changes. Specifically, weather events with bigger weather substances and faster weather processes tend to select action verbs with high transitivity. The kinesis driven accounts also predict the typological variations between verbal and nominal constructions for weather expressions. The correlation between kinesis and the selection of verbs is further corroborated by an experiment on the perception of native Sinitic language speakers, as well as analyses of regional variations of verb selections that do not follow general typological patterns. It is found that such typological exceptions generally correspond to variations in meteorological patterns. By explicating the pivotal role of kinesis in bridging weather events and the linguistic encoding of weather, this study underlines the role of cognition as the conceptualisation of physical and sensory inputs to sharable knowledge encoded by language.

The Coronavirus Disease 2019 (COVID-19) pandemic has shifted the focus of research worldwide, and more than 10 000 new articles per month have concentrated on COVID-19–related topics. Considering this rapidly growing literature, the efficient and precise extraction of the main topics of COVID-19–relevant articles is of great importance. The manual curation of this information for biomedical literature is labor-intensive and time-consuming, and as such the procedure is insufficient and difficult to maintain. In response to these complications, the BioCreative VII community has proposed a challenging task, LitCovid Track, calling for a global effort to automatically extract semantic topics for COVID-19 literature. This article describes our work on the BioCreative VII LitCovid Track. We proposed the LitCovid Ensemble Learning (LCEL) method for the tasks and integrated multiple biomedical pretrained models to address the COVID-19 multi-label classification problem. Specifically, seven different transformer-based pretrained models were ensembled for the initialization and fine-tuning processes independently. To enhance the representation abilities of the deep neural models, diverse additional biomedical knowledge was utilized to facilitate the fruitfulness of the semantic expressions. Simple yet effective data augmentation was also leveraged to address the learning deficiency during the training phase. In addition, given the imbalanced label distribution of the challenging task, a novel asymmetric loss function was applied to the LCEL model, which explicitly adjusted the negative–positive importance by assigning different exponential decay factors and helped the model focus on the positive samples. After the training phase, an ensemble bagging strategy was adopted to merge the outputs from each model for final predictions. The experimental results show the effectiveness of our proposed approach, as LCEL obtains the state-of-the-art performance on the LitCovid dataset.Database URL: https://github.com/JHnlp/LCEL