We introduce primed-PCA (pPCA), an extension of the recently proposed EigenGame algorithm for computing principal components in a large-scale setup. Our algorithm first runs EigenGame to get an approximation of the principal components, and then applies an exact PCA in the subspace they span. Since this subspace is of small dimension in any practical use of EigenGame, this second step is extremely cheap computationally. Nonetheless, it improves accuracy significantly for a given computational budget across datasets. In this setup, the purpose of EigenGame is to narrow down the search space, and prepare the data for the second step, an exact calculation. We show formally that pPCA improves upon EigenGame under very mild conditions, and we provide experimental validation on both synthetic and real large-scale datasets showing that it systematically translates to improved performance. In our experiments we achieve improvements in convergence speed by factors of 5-25 on the datasets of the original EigenGame paper.

Bayesian methods have become a popular way to incorporate prior knowledge and a notion of uncertainty into machine learning models. At the same time, the complexity of modern machine learning makes it challenging to comprehend a model's reasoning process, let alone express specific prior assumptions in a rigorous manner. While primarily interested in the former issue, recent developments in transparent machine learning could also broaden the range of prior information that we can provide to complex Bayesian models. Inspired by the idea of selfexplaining models, we introduce a corresponding concept for variational Gaussian Processes. On the one hand, our contribution improves transparency for these types of models. More importantly though, our proposed self-explaining variational posterior distribution allows to incorporate both general prior knowledge about a target function as a whole and prior knowledge about the contribution of individual features.

The US District Court for the Eastern District of Virginia on Wednesday ruled that an artificial intelligence (AI) machine cannot be an inventor under the Patent Act. The action was a motion for summary judgement concerning two patent applications filed by Stephen Thaler for an AI machine called DABUS. DABUS was listed as the inventor for Neural Flame--a light beacon that flashes in a new and inventive manner to attract attention--and Fractal Container--a beverage container based on fractal geometry. Thaler's patent applications were rejected by the US Patent and Trademarks Office (USPTO) and he challenged this refusal as "arbitrary, capricious, an abuse of direction and not in accordance with the law". He filed this action seeking a declaration that a patent application should not be rejected only on grounds that there is no natural person identified as the inventor and that a patent application for an invention by AI should list the AI as the inventor when the criteria for inventorship has been fulfilled by the AI. The court rejected Thaler's contentions, holding that the definitions provided by Congress for "inventor" within the Patent Act reference an "individual" whose ordinary dictionary and statutory meaning is a natural person or a human being.

Every time you search for something in Google, artificial intelligence is working behind the scenes to generate responses to your query. A deep learning system called RankBrain has changed the way the search engine functions. In many cases, RankBrain handles search queries better than traditional algorithmic rules that were hand-coded by human engineers, and Google realized a long time ago that AI is the future of their search platform. AI will try to understand exactly what we are searching for and then deliver personalized results to us, based on what it knows about us. You may not realize it, but AI is already deeply integrated into many of the Google products you are using today.

One of the most popular methods for context-aware machine translation (MT) is to use separate encoders for the source sentence and context as multiple sources for one target sentence. Recent work has cast doubt on whether these models actually learn useful signals from the context or are improvements in automatic evaluation metrics just a side-effect. We show that multi-source transformer models improve MT over standard transformer-base models even with empty lines provided as context, but the translation quality improves significantly (1.51 - 2.65 BLEU) when a sufficient amount of correct context is provided. We also show that even though randomly shuffling in-domain context can also improve over baselines, the correct context further improves translation quality and random out-of-domain context further degrades it.

In this paper we present IndicBART, a multilingual, sequence-to-sequence pre-trained model focusing on 11 Indic languages and English. Different from existing pre-trained models, IndicBART utilizes the orthographic similarity between Indic scripts to improve transfer learning between similar Indic languages. We evaluate IndicBART on two NLG tasks: Neural Machine Translation (NMT) and extreme summarization. Our experiments on NMT for 12 language pairs and extreme summarization for 7 languages using multilingual fine-tuning show that IndicBART is competitive with or better than mBART50 despite containing significantly fewer parameters. Our analyses focus on identifying the impact of script unification (to Devanagari), corpora size as well as multilingualism on the final performance. The IndicBART model is available under the MIT license at https://indicnlp.ai4bharat.org/indic-bart .

Sequential diagnosis prediction on the Electronic Health Record (EHR) has been proven crucial for predictive analytics in the medical domain. EHR data, sequential records of a patient's interactions with healthcare systems, has numerous inherent characteristics of temporality, irregularity and data insufficiency. Some recent works train healthcare predictive models by making use of sequential information in EHR data, but they are vulnerable to irregular, temporal EHR data with the states of admission/discharge from hospital, and insufficient data. To mitigate this, we propose an end-to-end robust transformer-based model called SETOR, which exploits neural ordinary differential equation to handle both irregular intervals between a patient's visits with admitted timestamps and length of stay in each visit, to alleviate the limitation of insufficient data by integrating medical ontology, and to capture the dependencies between the patient's visits by employing multi-layer transformer blocks. Experiments conducted on two real-world healthcare datasets show that, our sequential diagnoses prediction model SETOR not only achieves better predictive results than previous state-of-the-art approaches, irrespective of sufficient or insufficient training data, but also derives more interpretable embeddings of medical codes. The experimental codes are available at the GitHub repository (https://github.com/Xueping/SETOR).

Conversational search systems, such as Google Assistant and Microsoft Cortana, provide a new search paradigm where users are allowed, via natural language dialogues, to communicate with search systems. Evaluating such systems is very challenging since search results are presented in the format of natural language sentences. Given the unlimited number of possible responses, collecting relevance assessments for all the possible responses is infeasible. In this paper, we propose POSSCORE, a simple yet effective automatic evaluation method for conversational search. The proposed embedding-based metric takes the influence of part of speech (POS) of the terms in the response into account. To the best knowledge, our work is the first to systematically demonstrate the importance of incorporating syntactic information, such as POS labels, for conversational search evaluation. Experimental results demonstrate that our metrics can correlate with human preference, achieving significant improvements over state-of-the-art baseline metrics.

Recently, large pre-trained neural language models have attained remarkable performance on many downstream natural language processing (NLP) applications via fine-tuning. In this paper, we target at how to further improve the token representations on the language models. We, therefore, propose a simple yet effective plug-and-play module, Sequential Attention Module (SAM), on the token embeddings learned from a pre-trained language model. Our proposed SAM consists of two main attention modules deployed sequentially: Feature-wise Attention Module (FAM) and Token-wise Attention Module (TAM). More specifically, FAM can effectively identify the importance of features at each dimension and promote the effect via dot-product on the original token embeddings for downstream NLP applications. Meanwhile, TAM can further re-weight the features at the token-wise level. Moreover, we propose an adaptive filter on FAM to prevent noise impact and increase information absorption. Finally, we conduct extensive experiments to demonstrate the advantages and properties of our proposed SAM. We first show how SAM plays a primary role in the champion solution of two subtasks of SemEval'21 Task 7. After that, we apply SAM on sentiment analysis and three popular NLP tasks and demonstrate that SAM consistently outperforms the state-of-the-art baselines.

One challenge for dialogue agents is to recognize feelings of the conversation partner and respond accordingly. In this work, RoBERTa-GPT2 is proposed for empathetic dialogue generation, where the pre-trained auto-encoding RoBERTa is utilised as encoder and the pre-trained auto-regressive GPT-2 as decoder. With the combination of the pre-trained RoBERTa and GPT-2, our model realizes a new state-of-the-art emotion accuracy. To enable the empathetic ability of RoBERTa-GPT2 model, we propose a commonsense knowledge and emotional concepts extractor, in which the commonsensible and emotional concepts of dialogue context are extracted for the GPT-2 decoder. The experiment results demonstrate that the empathetic dialogue generation benefits from both pre-trained encoder-decoder architecture and external knowledge.