The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses ‘value networks’ to evaluate board positions and ‘policy networks’ to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of stateof-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.

/pdf/mastering-the-game-of-go-with-deep-neural-networks-and-tree-3viuxo6uxm.pdf

Mastering the game of Go with deep neural networks and tree search

Recent progress in artificial intelligence has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats that of humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn and how they learn it. Specifically, we argue that these machines should (1) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; (2) ground learning in intuitive theories of physics and psychology to support and enrich the knowledge that is learned; and (3) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes toward these goals that can combine the strengths of recent neural network advances with more structured cognitive models.

/pdf/building-machines-that-learn-and-think-like-people-w8p3qwruiy.pdf

Building machines that learn and think like people.

This paper proposes to tackle open- domain question answering using Wikipedia as the unique knowledge source: the answer to any factoid question is a text span in a Wikipedia article. This task of machine reading at scale combines the challenges of document retrieval (finding the relevant articles) with that of machine comprehension of text (identifying the answer spans from those articles). Our approach combines a search component based on bigram hashing and TF-IDF matching with a multi-layer recurrent neural network model trained to detect answers in Wikipedia paragraphs. Our experiments on multiple existing QA datasets indicate that (1) both modules are highly competitive with respect to existing counterparts and (2) multitask learning using distant supervision on their combination is an effective complete system on this challenging task.

Reading Wikipedia to Answer Open-Domain Questions

Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this work, we show that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dual-encoder framework. When evaluated on a wide range of open-domain QA datasets, our dense retriever outperforms a strong Lucene-BM25 system largely by 9%-19% absolute in terms of top-20 passage retrieval accuracy, and helps our end-to-end QA system establish new state-of-the-art on multiple open-domain QA benchmarks.

Dense Passage Retrieval for Open-Domain Question Answering

Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this work, we show that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dual-encoder framework. When evaluated on a wide range of open-domain QA datasets, our dense retriever outperforms a strong Lucene-BM25 system greatly by 9%-19% absolute in terms of top-20 passage retrieval accuracy, and helps our end-to-end QA system establish new state-of-the-art on multiple open-domain QA benchmarks.

/pdf/dense-passage-retrieval-for-open-domain-question-answering-qq5rzovuru.pdf

We briefly survey the current state of art in the field of Question Answering and present the YodaQA system, an open source framework for this task and a baseline pipeline with reasonable performance. We take a holistic approach, reviewing and aiming to integrate many different question answering task definitions and approaches concerning classes of knowledge bases, question representation and answer generation. To ease performance comparisons of general-purpose QA systems, we also propose an effort in building a new reference QA testing corpus which is a curated and extended version of the TREC corpus.

Modeling of the Question Answering Task in the YodaQA System

We present a state of the art implementation of the Monte Carlo Tree Search algorithm for the game of Go. Our Pachi software is currently one of the strongest open source Go programs, competing at the top level with other programs and playing evenly against advanced human players. We describe our implementation and choice of published algorithms as well as three notable original improvements: (1) an adaptive time control algorithm, (2) dynamic komi, and (3) the usage of the criticality statistic. We also present new methods to achieve efficient scaling both in terms of multiple threads and multiple machines in a cluster.

PACHI: State of the Art Open Source Go Program

We review the task of Sentence Pair Scoring, popular in the literature in various forms - viewed as Answer Sentence Selection, Semantic Text Scoring, Next Utterance Ranking, Recognizing Textual Entailment, Paraphrasing or e.g. a component of Memory Networks. 
We argue that all such tasks are similar from the model perspective and propose new baselines by comparing the performance of common IR metrics and popular convolutional, recurrent and attention-based neural models across many Sentence Pair Scoring tasks and datasets. We discuss the problem of evaluating randomized models, propose a statistically grounded methodology, and attempt to improve comparisons by releasing new datasets that are much harder than some of the currently used well explored benchmarks. We introduce a unified open source software framework with easily pluggable models and tasks, which enables us to experiment with multi-task reusability of trained sentence model. We set a new state-of-art in performance on the Ubuntu Dialogue dataset.

Sentence Pair Scoring: Towards Unified Framework for Text Comprehension

Table detection and extraction has been studied in the context of documents like reports, where tables are clearly outlined and stand out from the document structure visually. We study this topic in a rather more challenging domain of layout-heavy business documents, particularly invoices. Invoices present the novel challenges of tables being often without outlines - either in the form of borders or surrounding text flow - with ragged columns and widely varying data content. We will also show, that we can extract specific information from structurally different tables or table-like structures with one model. We present a comprehensive representation of a page using graph over word boxes, positional embeddings, trainable textual features and rephrase the table detection as a text box labeling problem. We will work on our newly presented dataset of pro forma invoices, invoices and debit note documents using this representation and propose multiple baselines to solve this labeling problem. We then propose a novel neural network model that achieves strong, practical results on the presented dataset and analyze the model performance and effects of graph convolutions and self-attention in detail.

Table Understanding in Structured Documents

The recently proposed Brent-STEP algorithm was generalized for separable functions by performing axis-parallel searches, interleaving the steps in individual dimensions in a round-robin fashion. This article explores the possibility to choose the dimension for the next step in a more "intelligent way", i.e. to optimize first along dimensions which are believed to bring the highest profit. We present here the results for the epsilon-greedy strategy, and for a method based on the internals of the Brent-STEP algorithm. Although the proposed methods work better than the round robin strategy in some situations, due to the marginal improvement they bring we suggest the round robin strategy to be used, thanks to its simplicity.

/pdf/dimension-selection-in-axis-parallel-brent-step-method-for-wnlmete5lk.pdf

Petr Baudiš

Papers

Modeling of the Question Answering Task in the YodaQA System

PACHI: State of the Art Open Source Go Program

Sentence Pair Scoring: Towards Unified Framework for Text Comprehension

Table Understanding in Structured Documents

Dimension Selection in Axis-Parallel Brent-STEP Method for Black-Box Optimization of Separable Continuous Functions