While underscoring judges' role, top court says intelligent tech will improve system A competent artificial intelligence system to support the judicial sector is expected to be set up by 2025 to help improve legal services, China's top court said. The goal was embedded in the Opinions on Regulating and Strengthening the Application of Artificial Intelligence in Judicial Fields, a 20-article guideline issued on Friday by the Supreme People's Court. The document reveals that a better regulated and more effective application and theoretical system for AI utilization in the judicial sector will be set up by 2030 to serve the people and support the entire case-handling process. The top court said that in issuing the document, it aims to promote the in-depth integration of AI with judicial work, strengthen the creation of smart courts and work toward a higher level of digital justice. While calling for advancing the application of AI, the document highlights the legality and security of applying AI to judicial affairs, with stipulation that the technological promotion and application not damage national security, infringe upon State secrets or violate personal data security.

RegTech allows companies to better manage regulatory compliance, but it is also a valuable tool to create added value and innovatively grow the business. But for this to be possible, companies need to implement specific technologies, which are the basic conditions for developing a good RegTech system, such as blockchain, AI, and RPA. When building a business and imagining strategies and ways to grow, one cannot help but take into account the regulations and operational and procedural requirements established by the legislature for a given industry, including when it comes to RegTech and regulations. Often, regulation is considered as an element that hinders or slows down the development of the business. In other words, one often perceives the conflict, the opposition between regulation and the development and growth of an entrepreneurial project.

Legal text retrieval serves as a key component in a wide range of legal text processing tasks such as legal question answering, legal case entailment, and statute law retrieval. The performance of legal text retrieval depends, to a large extent, on the representation of text, both query and legal documents. Based on good representations, a legal text retrieval model can effectively match the query to its relevant documents. Because legal documents often contain long articles and only some parts are relevant to queries, it is quite a challenge for existing models to represent such documents. In this paper, we study the use of attentive neural network-based text representation for statute law document retrieval. We propose a general approach using deep neural networks with attention mechanisms. Based on it, we develop two hierarchical architectures with sparse attention to represent long sentences and articles, and we name them Attentive CNN and Paraformer. The methods are evaluated on datasets of different sizes and characteristics in English, Japanese, and Vietnamese. Experimental results show that: i) Attentive neural methods substantially outperform non-neural methods in terms of retrieval performance across datasets and languages; ii) Pretrained transformer-based models achieve better accuracy on small datasets at the cost of high computational complexity while lighter weight Attentive CNN achieves better accuracy on large datasets; and iii) Our proposed Paraformer outperforms state-of-the-art methods on COLIEE dataset, achieving the highest recall and F2 scores in the top-N retrieval task.

Online personalized recommendation services are generally hosted in the cloud where users query the cloud-based model to receive recommended input such as merchandise of interest or news feed. State-of-the-art recommendation models rely on sparse and dense features to represent users' profile information and the items they interact with. Although sparse features account for 99% of the total model size, there was not enough attention paid to the potential information leakage through sparse features. These sparse features are employed to track users' behavior, e.g., their click history, object interactions, etc., potentially carrying each user's private information. Sparse features are represented as learned embedding vectors that are stored in large tables, and personalized recommendation is performed by using a specific user's sparse feature to index through the tables. Even with recently-proposed methods that hides the computation happening in the cloud, an attacker in the cloud may be able to still track the access patterns to the embedding tables. This paper explores the private information that may be learned by tracking a recommendation model's sparse feature access patterns. We first characterize the types of attacks that can be carried out on sparse features in recommendation models in an untrusted cloud, followed by a demonstration of how each of these attacks leads to extracting users' private information or tracking users by their behavior over time.

Bi-encoders and cross-encoders are widely used in many state-of-the-art retrieval pipelines. In this work we study the generalization ability of these two types of architectures on a wide range of parameter count on both in-domain and out-of-domain scenarios. We find that the number of parameters and early query-document interactions of cross-encoders play a significant role in the generalization ability of retrieval models. Our experiments show that increasing model size results in marginal gains on in-domain test sets, but much larger gains in new domains never seen during fine-tuning. Furthermore, we show that cross-encoders largely outperform bi-encoders of similar size in several tasks. In the BEIR benchmark, our largest cross-encoder surpasses a state-of-the-art bi-encoder by more than 4 average points. Finally, we show that using bi-encoders as first-stage retrievers provides no gains in comparison to a simpler retriever such as BM25 on out-of-domain tasks. The code is available at https://github.com/guilhermemr04/scaling-zero-shot-retrieval.git

More than three years ago, this editor sat down with Sam Altman for a small event in San Francisco soon after he'd left his role as the president of Y Combinator to become CEO of the AI company he co-founded in 2015 with Elon Musk and others, OpenAI. At the time, Altman described OpenAI's potential in language that sounded outlandish to some. Altman said, for example, that the opportunity with artificial general intelligence -- machine intelligence that can solve problems as well as a human -- is so great that if OpenAI managed to crack it, the outfit could "maybe capture the light cone of all future value in the universe." He said that the company was "going to have to not release research" because it was so powerful. Asked if OpenAI was guilty of fear-mongering -- Musk has repeatedly called all organizations developing AI to be regulated -- Altman talked about the dangers of not thinking about "societal consequences" when "you're building something on an exponential curve."

During the early years of the Cold War, an array of underwater microphones monitoring for sounds of Russian submarines captured something otherworldly in the depths of the North Atlantic. The haunting sounds came not from enemy craft, nor aliens, but humpback whales, a species that, at the time, humans had hunted almost to the brink of extinction. Years later, when environmentalist Roger Payne obtained the recordings from U.S. Navy storage and listened to them, he was deeply moved. The whale songs seemed to reveal majestic creatures that could communicate with one another in complex ways. If only the world could hear these sounds, Payne reasoned, the humpback whale might just be saved from extinction. When Payne released the recordings in 1970 as the album Songs of the Humpback Whale, he was proved right. It was played at the U.N. general assembly, and it inspired Congress to pass the 1973 endangered species act. By 1986, commercial whaling was banned under international law.

Artificial Intelligence is everywhere, but what it is? The theory and development of computer systems able to perform task that normally require human intelligence, such as visual perception, speech recognition, decision-making, translation between languages. For many employers, artificial intelligence ("AI") is a tool in recruiting that allows employers to perform complex tasks in extraordinarily short periods of time while eliminating human bias and increasing outreach to diverse candidates. What is the legal risk for AI? Studies show that 80% of employers use AI in recruiting.

In many applications, heterogeneous treatment effects on a censored response variable are of primary interest, and it is natural to evaluate the effects at different quantiles (e.g., median). The large number of potential effect modifiers, the unknown structure of the treatment effects, and the presence of right censoring pose significant challenges. In this paper, we develop a hybrid forest approach called Hybrid Censored Quantile Regression Forest (HCQRF) to assess the heterogeneous effects varying with high-dimensional variables. The hybrid estimation approach takes advantage of the random forests and the censored quantile regression. We propose a doubly-weighted estimation procedure that consists of a redistribution-of-mass weight to handle censoring and an adaptive nearest neighbor weight derived from the forest to handle high-dimensional effect functions. We propose a variable importance decomposition to measure the impact of a variable on the treatment effect function. Extensive simulation studies demonstrate the efficacy and stability of HCQRF. The result of the simulation study also convinces us of the effectiveness of the variable importance decomposition. We apply HCQRF to a clinical trial of colorectal cancer. We achieve insightful estimations of the treatment effect and meaningful variable importance results. The result of the variable importance also confirms the necessity of the decomposition.

Pre-training large neural language models, such as BERT, has led to impressive gains on many natural language processing (NLP) tasks. Although this method has proven to be effective for many domains, it might not always provide desirable benefits. In this paper, we study the effects of hateful pre-training on low-resource hate speech classification tasks. While previous studies on the English language have emphasized its importance, we aim to augment their observations with some non-obvious insights. We evaluate different variations of tweet-based BERT models pre-trained on hateful, non-hateful, and mixed subsets of a 40M tweet dataset. This evaluation is carried out for the Indian languages Hindi and Marathi. This paper is empirical evidence that hateful pre-training is not the best pre-training option for hate speech detection. We show that pre-training on non-hateful text from the target domain provides similar or better results. Further, we introduce HindTweetBERT and MahaTweetBERT, the first publicly available BERT models pre-trained on Hindi and Marathi tweets, respectively. We show that they provide state-of-the-art performance on hate speech classification tasks. We also release hateful BERT for the two languages and a gold hate speech evaluation benchmark HateEval-Hi and HateEval-Mr consisting of manually labeled 2000 tweets each. The models and data are available at https://github.com/l3cube-pune/MarathiNLP .