We study the problem of Query Performance Prediction (QPP) for open-domain multi-hop Question Answering (QA), where the task is to estimate the difficulty of evaluating a multi-hop question over a corpus. Despite the extensive research on predicting the performance of ad-hoc and QA retrieval models, there has been a lack of study on the estimation of the difficulty of multi-hop questions. The problem is challenging due to the multi-step nature of the retrieval process, potential dependency of the steps and the reasoning involved. To tackle this challenge, we propose multHP, a novel pre-retrieval method for predicting the performance of open-domain multi-hop questions. Our extensive evaluation on the largest multi-hop QA dataset using several modern QA systems shows that the proposed model is a strong predictor of the performance, outperforming traditional single-hop QPP models. Additionally, we demonstrate that our approach can be effectively used to optimize the parameters of QA systems, such as the number of documents to be retrieved, resulting in improved overall retrieval performance.

Recent conditional language models are able to continue any kind of text source in an often seemingly fluent way. This fact encouraged research in the area of open-domain conversational systems that are based on powerful language models and aim to imitate an interlocutor by generating appropriate contributions to a written dialogue. From a linguistic perspective, however, the complexity of contributing to a conversation is high. In this survey, we interpret Grice's maxims of cooperative conversation from the perspective of this specific research area and systematize the literature under the aspect of what makes a contribution appropriate: A neural conversation model has to be fluent, informative, consistent, coherent, and follow social norms. In order to ensure these qualities, recent approaches try to tame the underlying language models at various intervention points, such as data, training regime or decoding. Sorted by these categories and intervention points, we discuss promising attempts and suggest novel ways for future research.

Machine Learning models are capable of generating complex music across a range of genres from folk to classical music. However, current generative music AI models are typically difficult to understand and control in meaningful ways. Whilst research has started to explore how explainable AI (XAI) generative models might be created for music, no generative XAI models have been studied in music making practice. This paper introduces an autoethnographic study of the use of the MeasureVAE generative music XAI model with interpretable latent dimensions trained on Irish folk music. Findings suggest that the exploratory nature of the music-making workflow foregrounds musical features of the training dataset rather than features of the generative model itself. The appropriation of an XAI model within an iterative workflow highlights the potential of XAI models to form part of a richer and more complex workflow than they were initially designed for.

Determining the sentiment of a tweet can be a laborious task for NLP specialists, as they need to identify the specific segment of the sentence that accurately reflects the sentiment and its boundaries. It can be challenging to accomplish this task when the sentences are lengthy and the intended emotion is conveyed using multiple words or placed at the start or end. Information extraction and sentiment analysis are indispensable for processing news feeds and posts from public profiles of celebrities and ordinary persons to determine the sentiment of a tweet. When automated, these activities allow the categorization of tweets into several predefined classes and perhaps avoid the diffusion of fake news or toxic posts. Emotional writing can engage users and encourage them to spend more time browsing a website or getting more information about a product. However, it can also negatively impact the reader's mood, especially when they come across a toxic text with a high frequency of negative emotions, such as insulting comments or discriminatory remarks from followers on social media. Detecting such infractions early can increase the audience number on a web page and avoid unsubscribing clicks. When it comes to opinion mining, analyzing public opinion can be highly beneficial in assessing satisfaction and agreement with political decisions and programs. This type of analysis can offer valuable insights into a candidate's popularity and even aid in predicting their likelihood of winning an election compared to their competitors.

Recommender systems help people find relevant content in a personalized way. One main promise of such systems is that they are able to increase the visibility of items in the long tail, i.e., the lesser-known items in a catalogue. Existing research, however, suggests that in many situations today's recommendation algorithms instead exhibit a popularity bias, meaning that they often focus on rather popular items in their recommendations. Such a bias may not only lead to limited value of the recommendations for consumers and providers in the short run, but it may also cause undesired reinforcement effects over time. In this paper, we discuss the potential reasons for popularity bias and we review existing approaches to detect, quantify and mitigate popularity bias in recommender systems. Our survey therefore includes both an overview of the computational metrics used in the literature as well as a review of the main technical approaches to reduce the bias. We furthermore critically discuss today's literature, where we observe that the research is almost entirely based on computational experiments and on certain assumptions regarding the practical effects of including long-tail items in the recommendations.

Language models that are sensitive to external context can more effectively capture the speaking patterns of individuals with specific characteristics or in particular environments. However, obtaining and leveraging such annotations can be challenging. In this work, we show how to leverage rich character and film annotations to personalise language models in a scalable manner. Our best model can reduce perplexity by up to 6.5% compared to a parameter-matched language model. Our approach performs on par with speaker-specific fine-tuning when the fine-tuning data (i.e. past dialogue) for individual speakers is available. On top of that, it also generalises well to a scenario with no such data, relying on combinations of demographic characteristics expressed via metadata. Our findings are consistent across two corpora, one of which is also a contribution of this paper: Cornell-rich contains rich manual annotations for 863 speaking characters from the Cornell Movie Dialog Corpus, including features such as characteristic quotes and character descriptions, along with six automatically extracted metadata features for over 95% of the featured films. Finally, we also present a cost-benefit analysis highlighting which annotations are most cost-effective in reducing perplexity.

Text classification methods have been widely investigated as a way to detect content of low credibility: fake news, social media bots, propaganda, etc. Quite accurate models (likely based on deep neural networks) help in moderating public electronic platforms and often cause content creators to face rejection of their submissions or removal of already published texts. Having the incentive to evade further detection, content creators try to come up with a slightly modified version of the text (known as an attack with an adversarial example) that exploit the weaknesses of classifiers and result in a different output. Here we systematically test the robustness of popular text classifiers against available attacking techniques and discover that, indeed, in some cases insignificant changes in input text can mislead the models. We also introduce BODEGA: a benchmark for testing both victim models and attack methods on four misinformation detection tasks in an evaluation framework designed to simulate real use-cases of content moderation. Finally, we manually analyse a subset adversarial examples and check what kinds of modifications are used in successful attacks. The BODEGA code and data is openly shared in hope of enhancing the comparability and replicability of further research in this area

Automatic detection of multimodal fake news has gained a widespread attention recently. Many existing approaches seek to fuse unimodal features to produce multimodal news representations. However, the potential of powerful cross-modal contrastive learning methods for fake news detection has not been well exploited. Besides, how to aggregate features from different modalities to boost the performance of the decision-making process is still an open question. To address that, we propose COOLANT, a cross-modal contrastive learning framework for multimodal fake news detection, aiming to achieve more accurate image-text alignment. To further improve the alignment precision, we leverage an auxiliary task to soften the loss term of negative samples during the contrast process. A cross-modal fusion module is developed to learn the cross-modality correlations. An attention mechanism with an attention guidance module is implemented to help effectively and interpretably aggregate the aligned unimodal representations and the cross-modality correlations. Finally, we evaluate the COOLANT and conduct a comparative study on two widely used datasets, Twitter and Weibo. The experimental results demonstrate that our COOLANT outperforms previous approaches by a large margin and achieves new state-of-the-art results on the two datasets.

We propose an automatic data processing pipeline to extract vocal productions from large-scale natural audio recordings and classify these vocal productions. The pipeline is based on a deep neural network and adresses both issues simultaneously. Though a series of computationel steps (windowing, creation of a noise class, data augmentation, re-sampling, transfer learning, Bayesian optimisation), it automatically trains a neural network without requiring a large sample of labeled data and important computing resources. Our end-to-end methodology can handle noisy recordings made under different recording conditions. We test it on two different natural audio data sets, one from a group of Guinea baboons recorded from a primate research center and one from human babies recorded at home. The pipeline trains a model on 72 and 77 minutes of labeled audio recordings, with an accuracy of 94.58% and 99.76%. It is then used to process 443 and 174 hours of natural continuous recordings and it creates two new databases of 38.8 and 35.2 hours, respectively. We discuss the strengths and limitations of this approach that can be applied to any massive audio recording.

Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. College professors across the country are working frantically to "ChatGPT-proof" their assignments as some educators report seeing dozens of students cheating with the tool. Some professors are planning to return to paper exams after years of conducting them digitally. Others are more drastic and plan to require students to show the draft history on their essay assignments.