Acronym Disambiguation (AD) is crucial for natural language understanding on various sources, including biomedical reports, scientific papers, and search engine queries. However, existing acronym disambiguation benchmarks and tools are limited to specific domains, and the size of prior benchmarks is rather small. To accelerate the research on acronym disambiguation, we construct a new benchmark named GLADIS with three components: (1) a much larger acronym dictionary with 1.5M acronyms and 6.4M long forms; (2) a pre-training corpus with 160 million sentences; (3) three datasets that cover the general, scientific, and biomedical domains. We then pre-train a language model, \emph{AcroBERT}, on our constructed corpus for general acronym disambiguation, and show the challenges and values of our new benchmark.

An obstacle to scientific document understanding is the extensive use of acronyms which are shortened forms of long technical phrases. Acronym disambiguation aims to find the correct meaning of an ambiguous acronym in a given text. Recent efforts attempted to incorporate word embeddings and deep learning architectures, and achieved significant effects in this task. In general domains, kinds of fine-grained pretrained language models have sprung up, thanks to the largescale corpora which can usually be obtained through crowdsourcing. However, these models based on domain agnostic knowledge might achieve insufficient performance when directly applied to the scientific domain. Moreover, obtaining large-scale high-quality annotated data and representing high-level semantics in the scientific domain is challenging and expensive. In this paper, we consider both the domain agnostic and specific knowledge, and propose a Hierarchical Dual-path BERT method coined hdBERT to capture the general fine-grained and high-level specific representations for acronym disambiguation. First, the context-based pretrained models, RoBERTa and SciBERT, are elaborately involved in encoding these two kinds of knowledge respectively. Second, multiple layer perceptron is devised to integrate the dualpath representations simultaneously and outputs the prediction. With a widely adopted SciAD dataset contained 62,441 sentences, we investigate the effectiveness of hdBERT. The experimental results exhibit that the proposed approach outperforms state-of-the-art methods among various evaluation metrics. Specifically, its macro F1 achieves 93.73%.

Don't you think that a great many mobile apps would be a lot more convenient if they had voice control? In most cases, voice navigation or a conversational form-filling is just enough. Through the use of the Habitica example (an open-source Kotlin-based habit tracking app) Vit Gorbachyov, Just AI solution architect, will show you how to add a voice interface into any app swiftly and seamlessly. Let's start with the obvious: It's really obvious, but most of the time voice is simply quicker. Consider this, ordering a ticket saying get me a plane to London for tomorrow for two instead of a long-time form filling.

The Hugo Awards, widely considered the most prestigious science fiction and fantasy prizes, were announced Friday, with female authors dominating and N.K. Jemisin winning the award for novel for the second year in a row. Jemisin, who became the first black author to win the Hugo's novel award last year (for "The Fifth Season"), won again with the book's sequel, "The Obelisk Gate." The third and final book in Jemisin's trilogy, "The Stone Sky," will be released Tuesday. The awards were announced at a ceremony at Worldcon 75, a science fiction festival held this year in Helsinki, Finland. Female authors also took home the awards for novella ("Every Heart a Doorway" by Seanan McGuire), novelette ("The Tomato Thief" by Ursula Vernon) and short story ("Seasons of Glass and Iron" by Amal El-Mohtar).

The winners of the Hugo Awards were announced at a gala ceremony in Kansas City, Mo., on Saturday, marking a good night for women and authors of color, and a very bad one for the "Puppies." Writers N.K. Jemisin and Nnedi Okorafor, both of whom are African American women, won the novel and novella awards, respectively. It was a defeat for the groups the Sad Puppies and the Rabid Puppies, who for two years have semi-successfully gamed the nominations for the Hugos -- which along with the Nebula Awards are generally considered the preeminent awards in science fiction and fantasy -- in an attempt to advance their anti-diversity agendas. Jemisin, who won for her novel "The Fifth Season," referenced the Puppies in her acceptance speech, io9 reports. "Only a small number of ideologues have attempted to game the Hugo Awards," Jemisin said.