Meta, formerly known as Facebook, today showed off a prototype of an AI system that enables people to generate or import things into a virtual world just by using voice commands. The company sees the tool, which is called "Builder Bot," as an "exploratory concept" that shows AI's potential for creating new worlds in the metaverse. Meta CEO Mark Zuckerberg showed off the prototype at the Meta AI: Inside the Lab event on Wednesday in a pre-recorded demo video. In the video, Zuckerberg explained the process of building parts of a virtual world by describing them. He begins with the prompt, "let's go to a park."

During an Inside the Lab: Building for the metaverse with AI livestream event on Wednesday, Meta CEO Mark Zuckerberg didn't just expound on his company's unblinking vision for the future, dubbed the Metaverse. He also revealed that Meta's research division is working on a universal speech translation system that could streamline users' interactions with AI within the company's digital universe. "The big goal here is to build a universal model that can incorporate knowledge across all modalities... all the information that is captured through rich sensors," Zuckerberg said. "This will enable a vast scale of predictions, decisions, and generation as well as whole new architectures training methods and algorithms that can learn from a vast and diverse range of different inputs." Zuckerberg noted that Facebook has continually striven to develop technologies that enable more people worldwide to access the internet and is confident that those efforts will translate to the Metaverse as well.

Amazon Translate is a neural machine translation service that delivers fast, high-quality, affordable, and customizable language translation. Amazon Translate now supports formality customization. This feature allows you to customize the level of formality in your translation output. At the time of writing, the formality customization feature is available for six target languages: French, German, Hindi, Italian, Japanese, and Spanish. You can customize the formality of your translated output to suit your communication needs.

Paraphrase generation is an important NLP task that has achieved significant progress recently. However, one crucial problem is overlooked, `how to evaluate the quality of paraphrase?'. Most existing paraphrase generation models use reference-based metrics (e.g., BLEU) from neural machine translation (NMT) to evaluate their generated paraphrase. Such metrics' reliability is hardly evaluated, and they are only plausible when there exists a standard reference. Therefore, this paper first answers one fundamental question, `Are existing metrics reliable for paraphrase generation?'. We present two conclusions that disobey conventional wisdom in paraphrasing generation: (1) existing metrics poorly align with human annotation in system-level and segment-level paraphrase evaluation. (2) reference-free metrics outperform reference-based metrics, indicating that the standard references are unnecessary to evaluate the paraphrase's quality. Such empirical findings expose a lack of reliable automatic evaluation metrics. Therefore, this paper proposes BBScore, a reference-free metric that can reflect the generated paraphrase's quality. BBScore consists of two sub-metrics: S3C score and SelfBLEU, which correspond to two criteria for paraphrase evaluation: semantic preservation and diversity. By connecting two sub-metrics, BBScore significantly outperforms existing paraphrase evaluation metrics.

In this work, we introduce sequence-to-sequence language resources for Catalan, a moderately under-resourced language, towards two tasks, namely: Summarization and Machine Translation (MT). We present two new abstractive summarization datasets in the domain of newswire. We also introduce a parallel Catalan-English corpus, paired with three different brand new test sets. Finally, we evaluate the data presented with competing state of the art models, and we develop baselines for these tasks using a newly created Catalan BART. We release the resulting resources of this work under open license to encourage the development of language technology in Catalan.

AI essentially works to develop machines that are self-reliant and can think and act like humans. Examples of AI are machine translation such as Google Translate, speech recognition apps such as Google Assistant or Siri, and AI robots such as Aibo and Sophia. ML looks to solve business problems through predictive models built on analytics and computer models. The work of a machine learning engineer is seen in sales forecasting, stock price predictions, and banking fraud analysis, among others. A subset of ML, DL works with artificial neural networks employing algorithms inspired by the structure and working of the human brain. DL algorithms can work with huge amounts of both structured and unstructured data; ML, in comparison, typically requires structured data. Use cases include the detection of cancerous tumors and other objects and the coloring of images.

Amazon Translate is a neural machine translation service that delivers fast, high-quality, affordable, and customizable language translation. This post shows how you can mask profane words and phrases with a grawlix string ("?$#@$"). Amazon Translate typically chooses clean words for your translation output. But in some situations, you want to prevent words that are commonly considered as profane terms from appearing in the translated output. For example, when you're translating video captions or subtitle content, or enabling in-game chat, and you want the translated content to be age appropriate and clear of any profanity, Amazon Translate allows you to mask the profane words and phrases using the profanity masking setting.

We present ClidSum, a benchmark dataset for building cross-lingual summarization systems on dialogue documents. It consists of 67k+ dialogue documents from two subsets (i.e., SAMSum and MediaSum) and 112k+ annotated summaries in different target languages. Based on the proposed ClidSum, we introduce two benchmark settings for supervised and semi-supervised scenarios, respectively. We then build various baseline systems in different paradigms (pipeline and end-to-end) and conduct extensive experiments on ClidSum to provide deeper analyses. Furthermore, we propose mDialBART which extends mBART-50 (a multi-lingual BART) via further pre-training. The multiple objectives used in the further pre-training stage help the pre-trained model capture the structural characteristics as well as important content in dialogues and the transformation from source to the target language. Experimental results show the superiority of mDialBART, as an end-to-end model, outperforms strong pipeline models on ClidSum. Finally, we discuss specific challenges that current approaches faced with this task and give multiple promising directions for future research. We have released the dataset and code at https://github.com/krystalan/ClidSum.

Despite achieving incredibly low perplexities on myriad natural language corpora, today's language models still often underperform when used to generate text. This dichotomy has puzzled the language generation community for the last few years. In this work, we posit that the abstraction of natural language as a communication channel (\`a la Shannon, 1948) can provide new insights into the behaviors of probabilistic language generators, e.g., why high-probability texts can be dull or repetitive. Humans use language as a means of communicating information, and do so in an efficient yet error-minimizing manner, choosing each word in a string with this (perhaps subconscious) goal in mind. We propose that generation from probabilistic models should mimic this behavior. Rather than always choosing words from the high-probability region of the distribution--which have a low Shannon information content--we sample from the set of words with an information content close to its expected value, i.e., close to the conditional entropy of our model. This decision criterion can be realized through a simple and efficient implementation, which we call typical sampling. Automatic and human evaluations show that, in comparison to nucleus and top-k sampling, typical sampling offers competitive performance in terms of quality while consistently reducing the number of degenerate repetitions.

Below are some AI applications that you may not realise are AI-powered: Online shopping and advertising Artificial intelligence is widely used to provide personalised recommendations to people, based for example on their previous searches and purchases or other online behaviour. AI is hugely important in commerce: optimising products, planning inventory, logistics etc. Web search Search engines learn from the vast input of data, provided by their users to provide relevant search results. Digital personal assistants Smartphones use AI to provide services that are as relevant and personalised as possible. Virtual assistants answering questions, providing recommendations and helping organise daily routines have become ubiquitous. Machine translations Language translation software, either based on written or spoken text, relies on artificial intelligence to provide and improve translations.