We present a novel corpus for subjectivity detection at the sentence level. We develop new annotation guidelines for the task, which are not limited to language-specific cues, and apply them to produce a new corpus in English. The corpus consists of 411 subjective and 638 objective sentences extracted from ongoing coverage of political affairs from online news outlets. This new resource paves the way for the development of models for subjectivity detection in English and across other languages, without relying on language-specific tools like lexicons or machine translation. We evaluate state-of-the-art multilingual transformer-based models on the task, both in mono- and cross-lingual settings, the latter with a similar existing corpus in Italian language. We observe that enriching our corpus with resources in other languages improves the results on the task.

An essential element of K-12 AI literacy is educating learners about the ethical and societal implications of AI systems. Previous work in AI ethics literacy have developed curriculum and classroom activities that engage learners in reflecting on the ethical implications of AI systems and developing responsible AI. There is little work in using game-based learning methods in AI literacy. Games are known to be compelling media to teach children about complex STEM concepts. In this work, we developed a competitive card game for middle and high school students called "AI Audit" where they play as AI start-up founders building novel AI-powered technology. Players can challenge other players with potential harms of their technology or defend their own businesses by features that mitigate these harms. The game mechanics reward systems that are ethically developed or that take steps to mitigate potential harms. In this paper, we present the game design, teacher resources for classroom deployment and early playtesting results. We discuss our reflections about using games as teaching tools for AI literacy in K-12 classrooms.

Grammatical error correction (GEC) is the task of correcting typos, spelling, punctuation and grammatical issues in text. Approaching the problem as a sequence-to-sequence task, we compare the use of a common subword unit vocabulary and byte-level encoding. Initial synthetic training data is created using an error-generating pipeline, and used for finetuning two subword-level models and one byte-level model. Models are then finetuned further on hand-corrected error corpora, including texts written by children, university students, dyslexic and second-language writers, and evaluated over different error types and origins. We show that a byte-level model enables higher correction quality than a subword approach, not only for simple spelling errors, but also for more complex semantic, stylistic and grammatical issues. In particular, initial training on synthetic corpora followed by finetuning on a relatively small parallel corpus of real-world errors helps the byte-level model correct a wide range of commonly occurring errors. Our experiments are run for the Icelandic language but should hold for other similar languages, particularly morphologically rich ones.

We study the universality of complex-valued neural networks with bounded widths and arbitrary depths. Under mild assumptions, we give a full description of those activation functions $\varrho:\mathbb{C}\to \mathbb{C}$ that have the property that their associated networks are universal, i.e., are capable of approximating continuous functions to arbitrary accuracy on compact domains. Precisely, we show that deep narrow complex-valued networks are universal if and only if their activation function is neither holomorphic, nor antiholomorphic, nor $\mathbb{R}$-affine. This is a much larger class of functions than in the dual setting of arbitrary width and fixed depth. Unlike in the real case, the sufficient width differs significantly depending on the considered activation function. We show that a width of $2n+2m+5$ is always sufficient and that in general a width of $\max\{2n,2m\}$ is necessary. We prove, however, that a width of $n+m+4$ suffices for a rich subclass of the admissible activation functions. Here, $n$ and $m$ denote the input and output dimensions of the considered networks.

It was a tough week in tech. The top US health official warned about the risks of social media to young people; tech billionaire Elon Musk further trashed his reputation with the disastrous Twitter launch of a presidential campaign; and senior executives at OpenAI, makers of ChatGPT, called for the urgent regulation of "super intelligence". But to Doug Rushkoff – a leading digital age theorist, early cyberpunk and professor at City University of New York – the triple whammy of rough events represented some timely corrective justice for the tech barons of Silicon Valley. And more may be to come as new developments in tech come ever thicker and faster. "They're torturing themselves now, which is kind of fun to see. They're afraid that their little AIs are going to come for them. They're apocalyptic, and so existential, because they have no connection to real life and how things work. They're afraid the AIs are going to be as mean to them as they've been to us," Rushkoff told The Guardian in an interview.

This paper presents HaVQA, the first multimodal dataset for visual question-answering (VQA) tasks in the Hausa language. The dataset was created by manually translating 6,022 English question-answer pairs, which are associated with 1,555 unique images from the Visual Genome dataset. As a result, the dataset provides 12,044 gold standard English-Hausa parallel sentences that were translated in a fashion that guarantees their semantic match with the corresponding visual information. We conducted several baseline experiments on the dataset, including visual question answering, visual question elicitation, text-only and multimodal machine translation.

The paper describes the RuSentNE-2023 evaluation devoted to targeted sentiment analysis in Russian news texts. The task is to predict sentiment towards a named entity in a single sentence. The dataset for RuSentNE-2023 evaluation is based on the Russian news corpus RuSentNE having rich sentiment-related annotation. The corpus is annotated with named entities and sentiments towards these entities, along with related effects and emotional states. The evaluation was organized using the CodaLab competition framework. The main evaluation measure was macro-averaged measure of positive and negative classes. The best results achieved were of 66% Macro F-measure (Positive+Negative classes). We also tested ChatGPT on the test set from our evaluation and found that the zero-shot answers provided by ChatGPT reached 60% of the F-measure, which corresponds to 4th place in the evaluation. ChatGPT also provided detailed explanations of its conclusion. This can be considered as quite high for zero-shot application.

Contextualized embeddings are proven to be powerful tools in multiple NLP tasks. Nonetheless, challenges regarding their interpretability and capability to represent lexical semantics still remain. In this paper, we propose that the task of definition modeling, which aims to generate the human-readable definition of the word, provides a route to evaluate or understand the high dimensional semantic vectors. We propose a `Vec2Gloss' model, which produces the gloss from the target word's contextualized embeddings. The generated glosses of this study are made possible by the systematic gloss patterns provided by Chinese Wordnet. We devise two dependency indices to measure the semantic and contextual dependency, which are used to analyze the generated texts in gloss and token levels. Our results indicate that the proposed `Vec2Gloss' model opens a new perspective to the lexical-semantic applications of contextualized embeddings.

Natural language understanding typically maps single utterances to a dual level semantic frame, sentence level intent and slot labels at the word level. The best performing models force explicit interaction between intent detection and slot filling. We present a novel tri-level joint natural language understanding approach, adding domain, and explicitly exchange semantic information between all levels. This approach enables the use of multi-turn datasets which are a more natural conversational environment than single utterance. We evaluate our model on two multi-turn datasets for which we are the first to conduct joint slot-filling and intent detection. Our model outperforms state-of-the-art joint models in slot filling and intent detection on multi-turn data sets. We provide an analysis of explicit interaction locations between the layers. We conclude that including domain information improves model performance.

The generative retrieval model depends solely on the information encoded in its model parameters without external memory, its information capacity is limited and fixed. To overcome the limitation, we propose Nonparametric Decoding (Np Decoding) which can be applied to existing generative retrieval models. Np Decoding uses nonparametric contextualized vocab embeddings (external memory) rather than vanilla vocab embeddings as decoder vocab embeddings. By leveraging the contextualized vocab embeddings, the generative retrieval model is able to utilize both the parametric and nonparametric space. Evaluation over 9 datasets (8 single-hop and 1 multi-hop) in the document retrieval task shows that applying Np Decoding to generative retrieval models significantly improves the performance. We also show that Np Decoding is data- and parameter-efficient, and shows high performance in the zero-shot setting.