Recent work has demonstrated substantial gains on many NLP tasks and benchmarks by pre-training on a large corpus of text followed by fine-tuning on a specific task. While typically task-agnostic in architecture, this method still requires task-specific fine-tuning datasets of thousands or tens of thousands of examples. By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do. Here we show that scaling up language models greatly improves task-agnostic, few-shot performance, sometimes even reaching competitiveness with prior state-of-the-art fine-tuning approaches. Specifically, we train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous non-sparse language model, and test its performance in the few-shot setting. For all tasks, GPT-3 is applied without any gradient updates or fine-tuning, with tasks and few-shot demonstrations specified purely via text interaction with the model. GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic. At the same time, we also identify some datasets where GPT-3's few-shot learning still struggles, as well as some datasets where GPT-3 faces methodological issues related to training on large web corpora. Finally, we find that GPT-3 can generate samples of news articles which human evaluators have difficulty distinguishing from articles written by humans. We discuss broader societal impacts of this finding and of GPT-3 in general.

/pdf/language-models-are-few-shot-learners-2fg8gvia7m.pdf

Language Models are Few-Shot Learners

Today's Web-enabled deluge of electronic data calls for automated methods of data analysis. Machine learning provides these, developing methods that can automatically detect patterns in data and then use the uncovered patterns to predict future data. This textbook offers a comprehensive and self-contained introduction to the field of machine learning, based on a unified, probabilistic approach. The coverage combines breadth and depth, offering necessary background material on such topics as probability, optimization, and linear algebra as well as discussion of recent developments in the field, including conditional random fields, L1 regularization, and deep learning. The book is written in an informal, accessible style, complete with pseudo-code for the most important algorithms. All topics are copiously illustrated with color images and worked examples drawn from such application domains as biology, text processing, computer vision, and robotics. Rather than providing a cookbook of different heuristic methods, the book stresses a principled model-based approach, often using the language of graphical models to specify models in a concise and intuitive way. Almost all the models described have been implemented in a MATLAB software package--PMTK (probabilistic modeling toolkit)--that is freely available online. The book is suitable for upper-level undergraduates with an introductory-level college math background and beginning graduate students.

Machine Learning : A Probabilistic Perspective

This tutorial is concerned with a comprehensive introduction to the research area of learning to rank for information retrieval. In the first part of the tutorial, we will introduce three major approaches to learning to rank, i.e., the pointwise, pairwise, and listwise approaches, analyze the relationship between the loss functions used in these approaches and the widely-used IR evaluation measures, evaluate the performance of these approaches on the LETOR benchmark datasets, and demonstrate how to use these approaches to solve real ranking applications. In the second part of the tutorial, we will discuss some advanced topics regarding learning to rank, such as relational ranking, diverse ranking, semi-supervised ranking, transfer ranking, query-dependent ranking, and training data preprocessing. In the third part, we will briefly mention the recent advances on statistical learning theory for ranking, which explain the generalization ability and statistical consistency of different ranking methods. In the last part, we will conclude the tutorial and show several future research directions.

/pdf/learning-to-rank-for-information-retrieval-2q6t3viyug.pdf

Learning to Rank for Information Retrieval

The paper is concerned with learning to rank, which is to construct a model or a function for ranking objects. Learning to rank is useful for document retrieval, collaborative filtering, and many other applications. Several methods for learning to rank have been proposed, which take object pairs as 'instances' in learning. We refer to them as the pairwise approach in this paper. Although the pairwise approach offers advantages, it ignores the fact that ranking is a prediction task on list of objects. The paper postulates that learning to rank should adopt the listwise approach in which lists of objects are used as 'instances' in learning. The paper proposes a new probabilistic method for the approach. Specifically it introduces two probability models, respectively referred to as permutation probability and top k probability, to define a listwise loss function for learning. Neural Network and Gradient Descent are then employed as model and algorithm in the learning method. Experimental results on information retrieval show that the proposed listwise approach performs better than the pairwise approach.

https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/tr-2007-40.pdf

Learning to rank: from pairwise approach to listwise approach

Ranking problem is becoming important in many fields, especially in information retrieval (IR). Many machine learning techniques have been proposed for ranking problem, such as RankSVM, RankBoost, and RankNet. Among them, RankNet, which is based on a probabilistic ranking framework, is leading to promising results and has been applied to a commercial Web search engine. In this paper we conduct further study on the probabilistic ranking framework and provide a novel loss function named fidelity loss for measuring loss of ranking. The fidelity loss notonly inherits effective properties of the probabilistic ranking framework in RankNet, but possesses new properties that are helpful for ranking. This includes the fidelity loss obtaining zero for each document pair, and having a finite upper bound that is necessary for conducting query-level normalization. We also propose an algorithm named FRank based on a generalized additive model for the sake of minimizing the fedelity loss and learning an effective ranking function. We evaluated the proposed algorithm for two datasets: TREC dataset and real Web search dataset. The experimental results show that the proposed FRank algorithm outperforms other learning-based ranking methods on both conventional IR problem and Web search.

/pdf/frank-a-ranking-method-with-fidelity-loss-4kvfeav4oo.pdf

FRank: a ranking method with fidelity loss

Recommender systems are vital ingredients for many e-commerce services. In the literature, two of the most popular approaches are based on factorization and graph-based models; the former approach captures user preferences by factorizing the observed direct interactions between users and items, and the latter extracts indirect preferences from the graphs constructed by user-item interactions. In this paper we present HOP-Rec, a unified and efficient method that incorporates the two approaches. The proposed method involves random surfing on a graph to harvest high-order information among neighborhood items for each user. Instead of factorizing a transition matrix, our method introduces a confidence weighting parameter to simulate all high-order information simultaneously, for which we maintain a sparse user-item interaction matrix and enrich the matrix for each user using random walks. Experimental results show that our approach significantly outperforms the state of the art on a range of large-scale real-world datasets.

HOP-rec: high-order proximity for implicit recommendation

Mitochondrial Ca(2+) uptake, a process crucial for bioenergetics and Ca(2+) signaling, is catalyzed by the mitochondrial calcium uniporter. The uniporter is a multi-subunit Ca(2+)-activated Ca(2+) channel, with the Ca(2+) pore formed by the MCU protein and Ca(2+)-dependent activation mediated by MICU subunits. Recently, a mitochondrial inner membrane protein EMRE was identified as a uniporter subunit absolutely required for Ca(2+) permeation. However, the molecular mechanism and regulatory purpose of EMRE remain largely unexplored. Here, we determine the transmembrane orientation of EMRE, and show that its known MCU-activating function is mediated by the interaction of transmembrane helices from both proteins. We also reveal a second function of EMRE: to maintain tight MICU regulation of the MCU pore, a role that requires EMRE to bind MICU1 using its conserved C-terminal polyaspartate tail. This dual functionality of EMRE ensures that all transport-competent uniporters are tightly regulated, responding appropriately to a dynamic intracellular Ca(2+) landscape.

https://cdn.elifesciences.org/articles/15545/elife-15545-v5.pdf

Dual functions of a small regulatory subunit in the mitochondrial calcium uniporter complex

Many machine learning technologies such as support vector machines, boosting, and neural networks have been applied to the ranking problem in information retrieval. However, since originally the methods were not developed for this task, their loss functions do not directly link to the criteria used in the evaluation of ranking. Specifically, the loss functions are defined on the level of documents or document pairs, in contrast to the fact that the evaluation criteria are defined on the level of queries. Therefore, minimizing the loss functions does not necessarily imply enhancing ranking performances. To solve this problem, we propose using query-level loss functions in learning of ranking functions. We discuss the basic properties that a query-level loss function should have and propose a query-level loss function based on the cosine similarity between a ranking list and the corresponding ground truth. We further design a coordinate descent algorithm, referred to as RankCosine, which utilizes the proposed loss function to create a generalized additive ranking model. We also discuss whether the loss functions of existing ranking algorithms can be extended to query-level. Experimental results on the datasets of TREC web track, OHSUMED, and a commercial web search engine show that with the use of the proposed query-level loss function we can significantly improve ranking accuracies. Furthermore, we found that it is difficult to extend the document-level loss functions to query-level loss functions.

Ming-Feng Tsai

Papers

Learning to rank: from pairwise approach to listwise approach

FRank: a ranking method with fidelity loss

HOP-rec: high-order proximity for implicit recommendation

Dual functions of a small regulatory subunit in the mitochondrial calcium uniporter complex

Query-level loss functions for information retrieval