画像生成AI「DALL・E2」や文章生成AI「GPT-3」「InstructGPT」などを開発するAI研究団体のOpenAIが、2022年9月に高性能な文字起こしAI「Whisper」を発表しました。オープンソースのWhisperはリポジトリが一般公開されており、日本語にも対応しているとのことで、オンライン実行環境のGoogle Colaboratory(Google Colab)やローカルのWindows環境に導入して使ってみました。

Authors writing documents imprint identifying information within their texts: vocabulary, registry, punctuation, misspellings, or even emoji usage. Finding these details is very relevant to profile authors, relating back to their gender, occupation, age, and so on. But most importantly, repeating writing patterns can help attributing authorship to a text. Previous works use hand-crafted features or classification tasks to train their authorship models, leading to poor performance on out-of-domain authors. A better approach to this task is to learn stylometric representations, but this by itself is an open research challenge. In this paper, we propose PART: a contrastively trained model fit to learn \textbf{authorship embeddings} instead of semantics. By comparing pairs of documents written by the same author, we are able to determine the proprietary of a text by evaluating the cosine similarity of the evaluated documents, a zero-shot generalization to authorship identification. To this end, a pre-trained Transformer with an LSTM head is trained with the contrastive training method. We train our model on a diverse set of authors, from literature, anonymous blog posters and corporate emails; a heterogeneous set with distinct and identifiable writing styles. The model is evaluated on these datasets, achieving zero-shot 72.39\% and 86.73\% accuracy and top-5 accuracy respectively on the joint evaluation dataset when determining authorship from a set of 250 different authors. We qualitatively assess the representations with different data visualizations on the available datasets, profiling features such as book types, gender, age, or occupation of the author.

Artificial Intelligence-driven disruptions are increasingly becoming pervasive and are expected to change every industry. The high-tech sector can gain significantly from adopting AI at scale to stay competitive. AI is becoming better and more affordable: Per the 2022 AI-Index-Report by Stanford, since 2018, the cost and the time to train ML (machine learning) tasks have improved, encouraging widespread commercial adoption of AI. Robotic arms are becoming cheaper: An AI Index survey shows the median price of robotic arms has decreased by 46.2 per cent in the past five years, making them more affordable. Large models are doing much more: Large language models trained on enormous data are setting new records on technical benchmarks.

Existing pre-trained transformer analysis works usually focus only on one or two model families at a time, overlooking the variability of the architecture and pre-training objectives. In our work, we utilize the oLMpics benchmark and psycholinguistic probing datasets for a diverse set of 29 models including T5, BART, and ALBERT. Additionally, we adapt the oLMpics zero-shot setup for autoregressive models and evaluate GPT networks of different sizes. Our findings show that none of these models can resolve compositional questions in a zero-shot fashion, suggesting that this skill is not learnable using existing pre-training objectives. Furthermore, we find that global model decisions such as architecture, directionality, size of the dataset, and pre-training objective are not predictive of a model's linguistic capabilities.

Humans are naturally endowed with the ability to write in a particular style. They can, for instance, re-phrase a formal letter in an informal way, convey a literal message with the use of figures of speech or edit a novel by mimicking the style of some well-known authors. Automating this form of creativity constitutes the goal of style transfer. As a natural language generation task, style transfer aims at rewriting existing texts, and specifically, it creates paraphrases that exhibit some desired stylistic attributes. From a practical perspective, it envisions beneficial applications, like chatbots that modulate their communicative style to appear empathetic, or systems that automatically simplify technical articles for a non-expert audience. Several style-aware paraphrasing methods have attempted to tackle style transfer. A handful of surveys give a methodological overview of the field, but they do not support researchers to focus on specific styles. With this paper, we aim at providing a comprehensive discussion of the styles that have received attention in the transfer task. We organize them in a hierarchy, highlighting the challenges for the definition of each of them, and pointing out gaps in the current research landscape. The hierarchy comprises two main groups. One encompasses styles that people modulate arbitrarily, along the lines of registers and genres. The other group corresponds to unintentionally expressed styles, due to an author's personal characteristics. Hence, our review shows how these groups relate to one another, and where specific styles, including some that have not yet been explored, belong in the hierarchy. Moreover, we summarize the methods employed for different stylistic families, hinting researchers towards those that would be the most fitting for future research.

Students often make mistakes on their introductory programming assignments as part of their learning process. Unfortunately, providing custom repairs for these mistakes can require a substantial amount of time and effort from class instructors. Automated program repair (APR) techniques can be used to synthesize such fixes. Prior work has explored the use of symbolic and neural techniques for APR in the education domain. Both types of approaches require either substantial engineering efforts or large amounts of data and training. We propose to use a large language model trained on code, such as Codex, to build an APR system -- MMAPR -- for introductory Python programming assignments. Our system can fix both syntactic and semantic mistakes by combining multi-modal prompts, iterative querying, test-case-based selection of few-shots, and program chunking. We evaluate MMAPR on 286 real student programs and compare to a baseline built by combining a state-of-the-art Python syntax repair engine, BIFI, and state-of-the-art Python semantic repair engine for student assignments, Refactory. We find that MMAPR can fix more programs and produce smaller patches on average.

Language models are increasingly attracting interest from writers. However, such models lack long-range semantic coherence, limiting their usefulness for longform creative writing. We address this limitation by applying language models hierarchically, in a system we call Dramatron. By building structural context via prompt chaining, Dramatron can generate coherent scripts and screenplays complete with title, characters, story beats, location descriptions, and dialogue. We illustrate Dramatron's usefulness as an interactive co-creative system with a user study of 15 theatre and film industry professionals. Participants co-wrote theatre scripts and screenplays with Dramatron and engaged in open-ended interviews. We report critical reflections both from our interviewees and from independent reviewers who watched stagings of the works to illustrate how both Dramatron and hierarchical text generation could be useful for human-machine co-creativity. Finally, we discuss the suitability of Dramatron for co-creativity, ethical considerations -- including plagiarism and bias -- and participatory models for the design and deployment of such tools.

If a Large Language Model (LLM) answers "yes" to the question "Are mountains tall?" then does it know what a mountain is? Can you rely on it responding correctly or incorrectly to other questions about mountains? The success of Large Language Models (LLMs) indicates they are increasingly able to answer queries like these accurately, but that ability does not necessarily imply a general understanding of concepts relevant to the anchor query. We propose conceptual consistency to measure a LLM's understanding of relevant concepts. This novel metric measures how well a model can be characterized by finding out how consistent its responses to queries about conceptually relevant background knowledge are. To compute it we extract background knowledge by traversing paths between concepts in a knowledge base and then try to predict the model's response to the anchor query from the background knowledge. We investigate the performance of current LLMs in a commonsense reasoning setting using the CSQA dataset and the ConceptNet knowledge base. While conceptual consistency, like other metrics, does increase with the scale of the LLM used, we find that popular models do not necessarily have high conceptual consistency. Our analysis also shows significant variation in conceptual consistency across different kinds of relations, concepts, and prompts. This serves as a step toward building models that humans can apply a theory of mind to, and thus interact with intuitively.

Regie.ai, a startup using OpenAI's GPT-3 text-generating system to create sales and marketing content for brands, today announced that it raised $10 million in Series A funding led by Scale Venture Partners with participation from Foundation Capital, South Park Commons, Day One Ventures and prominent angel investors. The fresh investment comes as VCs see a growing opportunity in AI-powered, copy-generating adtech companies, whose tech promise to save time while potentially increasing personalization. Previously a software engineer at Google and Meta, Sridhar is a data scientist by trade, having developed enterprise-scale AI systems that detect duplicate images and rank search results. Millen formerly was a VP at T-Mobile, leading the national sales teams (e.g., strategic accounts and public sector). With Regie, Sridhar says he and Millen aimed to create a way for companies to communicate with their customers via channels like email, social media, text, podcasts, online advertising and more.

Reinforcement Learning (RL) has witnessed great strides for quadruped locomotion, with continued progress in the reliable sim-to-real transfer of policies. However, it remains a challenge to reuse a policy on another robot, which could save time for retraining. In this work, we present a framework for zero-shot policy retargeting wherein diverse motor skills can be transferred between robots of different shapes and sizes. The new framework centers on a planning-and-control pipeline that systematically integrates RL and Model Predictive Control (MPC). The planning stage employs RL to generate a dynamically plausible trajectory as well as the contact schedule, avoiding the combinatorial complexity of contact sequence optimization. This information is then used to seed the MPC to stabilize and robustify the policy roll-out via a new Hybrid Kinodynamic (HKD) model that implicitly optimizes the foothold locations. Hardware results show an ability to transfer policies from both the A1 and Laikago robots to the MIT Mini Cheetah robot without requiring any policy re-tuning.