Multi-View Broad Learning System for Primate Oculomotor Decision Decoding

Multi-view learning improves the learning performance by utilizing multi-view data: data collected from multiple sources, or feature sets extracted from the same data source. This approach is suitable for primate brain state decoding using cortical neural signals. This is because the complementary components of simultaneously recorded neural signals, local field potentials (LFPs) and action potentials (spikes), can be treated as two views. In this paper, we extended broad learning system (BLS), a recently proposed wide neural network architecture, from single-view learning to multi-view learning, and validated its performance in monkey oculomotor decision decoding from medial frontal LFPs and spikes. We demonstrated that medial frontal LFPs and spikes in non-human primate do contain complementary information about the oculomotor decision, and that the proposed multi-view BLS is a more effective approach to classify the oculomotor decision, than several classical and state-of-the-art single-view and multi-view learning approaches.

GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing

We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating). These toolkits provide state-of-the-art pre-trained models, training scripts, and training logs, to facilitate rapid prototyping and promote reproducible research. We also provide modular APIs with flexible building blocks to enable efficient customization. Leveraging the MXNet ecosystem, the deep learning models in GluonCV and GluonNLP can be deployed onto a variety of platforms with different programming languages. Benefiting from open source under the Apache 2.0 license, GluonCV and GluonNLP have attracted 100 contributors worldwide on GitHub. Models of GluonCV and GluonNLP have been downloaded for more than 1.6 million times in fewer than 10 months.

Pun Generation with Surprise

We tackle the problem of generating a pun sentence given a pair of homophones (e.g., "died" and "dyed"). Supervised text generation is inappropriate due to the lack of a large corpus of puns, and even if such a corpus existed, mimicry is at odds with generating novel content. In this paper, we propose an unsupervised approach to pun generation using a corpus of unhumorous text and what we call the local-global surprisal principle: we posit that in a pun sentence, there is a strong association between the pun word (e.g., "dyed") and the distant context, as well as a strong association between the alternative word (e.g., "died") and the immediate context. This contrast creates surprise and thus humor. We instantiate this principle for pun generation in two ways: (i) as a measure based on the ratio of probabilities under a language model, and (ii) a retrieve-and-edit approach based on words suggested by a skip-gram model. Human evaluation shows that our retrieve-and-edit approach generates puns successfully 31% of the time, tripling the success rate of a neural generation baseline.

Quizbowl: The Case for Incremental Question Answering

Quizbowl is a scholastic trivia competition that tests human knowledge and intelligence; additionally, it supports diverse research in question answering (QA). A Quizbowl question consists of multiple sentences whose clues are arranged by difficulty (from obscure to obvious) and uniquely identify a well-known entity such as those found on Wikipedia. Since players can answer the question at any time, an elite player (human or machine) demonstrates its superiority by answering correctly given as few clues as possible. We make two key contributions to machine learning research through Quizbowl: (1) collecting and curating a large factoid QA dataset and an accompanying gameplay dataset, and (2) developing a computational approach to playing Quizbowl that involves determining both what to answer and when to answer. Our Quizbowl system has defeated some of the best trivia players in the world over a multi-year series of exhibition matches. Throughout this paper, we show that collaborations with the vibrant Quizbowl community have contributed to the high quality of our dataset, led to new research directions, and doubled as an exciting way to engage the public with research in machine learning and natural language processing.

Decoupling Strategy and Generation in Negotiation Dialogues

We consider negotiation settings in which two agents use natural language to bargain on goods. Agents need to decide on both high-level strategy (e.g., proposing \$50) and the execution of that strategy (e.g., generating "The bike is brand new. Selling for just \$50."). Recent work on negotiation trains neural models, but their end-to-end nature makes it hard to control their strategy, and reinforcement learning tends to lead to degenerate solutions. In this paper, we propose a modular approach based on coarse di- alogue acts (e.g., propose(price=50)) that decouples strategy and generation. We show that we can flexibly set the strategy using supervised learning, reinforcement learning, or domain-specific knowledge without degeneracy, while our retrieval-based generation can maintain context-awareness and produce diverse utterances. We test our approach on the recently proposed DEALORNODEAL game, and we also collect a richer dataset based on real items on Craigslist. Human evaluation shows that our systems achieve higher task success rate and more human-like negotiation behavior than previous approaches.

QuAC : Question Answering in Context

We present QuAC, a dataset for Question Answering in Context that contains 14K information-seeking QA dialogs (100K questions in total). The dialogs involve two crowd workers: (1) a student who poses a sequence of freeform questions to learn as much as possible about a hidden Wikipedia text, and (2) a teacher who answers the questions by providing short excerpts from the text. QuAC introduces challenges not found in existing machine comprehension datasets: its questions are often more open-ended, unanswerable, or only meaningful within the dialog context, as we show in a detailed qualitative evaluation. We also report results for a number of reference models, including a recently state-of-the-art reading comprehension architecture extended to model dialog context. Our best model underperforms humans by 20 F1, suggesting that there is significant room for future work on this data. Dataset, baseline, and leaderboard available at http://quac.ai.

Transfer Learning for Brain-Computer Interfaces: An Euclidean Space Data Alignment Approach

Almost all EEG-based brain-computer interfaces (BCIs) need some labeled subject-specific data to calibrate a new subject, as neural responses are different across subjects to even the same stimulus. So, a major challenge in developing high-performance and user-friendly BCIs is to cope with such individual differences so that the calibration can be reduced or even completely eliminated. This paper focuses on the latter. More specifically, we consider an offline application scenario, in which we have unlabeled EEG trials from a new subject, and would like to accurately label them by leveraging auxiliary labeled EEG trials from other subjects in the same task. To accommodate the individual differences, we propose a novel unsupervised approach to align the EEG trials from different subjects in the Euclidean space to make them more consistent. It has three desirable properties: 1) the aligned trial lie in the Euclidean space, which can be used by any Euclidean space signal processing and machine learning approach; 2) it can be computed very efficiently; and, 3) it does not need any labeled trials from the new subject. Experiments on motor imagery and event-related potentials demonstrated the effectiveness and efficiency of our approach.

Transfer Learning Enhanced Common Spatial Pattern Filtering for Brain Computer Interfaces (BCIs): Overview and a New Approach

The electroencephalogram (EEG) is the most widely used input for brain computer interfaces (BCIs), and common spatial pattern (CSP) is frequently used to spatially filter it to increase its signal-to-noise ratio. However, CSP is a supervised filter, which needs some subject-specific calibration data to design. This is time-consuming and not user-friendly. A promising approach for shortening or even completely eliminating this calibration session is transfer learning, which leverages relevant data or knowledge from other subjects or tasks. This paper reviews three existing approaches for incorporating transfer learning into CSP, and also proposes a new transfer learning enhanced CSP approach. Experiments on motor imagery classification demonstrate their effectiveness. Particularly, our proposed approach achieves the best performance when the number of target domain calibration samples is small.

Spatial Filtering for Brain Computer Interfaces: A Comparison between the Common Spatial Pattern and Its Variant

The electroencephalogram (EEG) is the most popular form of input for brain computer interfaces (BCIs). However, it can be easily contaminated by various artifacts and noise, e.g., eye blink, muscle activities, powerline noise, etc. Therefore, the EEG signals are often filtered both spatially and temporally to increase the signal-to-noise ratio before they are fed into a machine learning algorithm for recognition. This paper considers spatial filtering, particularly, the common spatial pattern (CSP) filters for EEG classification. In binary classification, CSP seeks a set of filters to maximize the variance for one class while minimizing it for the other. We first introduce the traditional solution, and then a new solution based on a slightly different objective function. We performed comprehensive experiments on motor imagery to compare the two approaches, and found that generally the traditional CSP solution still gives better results. We also showed that adding regularization to the covariance matrices can improve the final classification performance, no matter which objective function is used.

Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context

We know very little about how neural language models (LM) use prior linguistic context. In this paper, we investigate the role of context in an LSTM LM, through ablation studies. Specifically, we analyze the increase in perplexity when prior context words are shuffled, replaced, or dropped. On two standard datasets, Penn Treebank and WikiText-2, we find that the model is capable of using about 200 tokens of context on average, but sharply distinguishes nearby context (recent 50 tokens) from the distant history. The model is highly sensitive to the order of words within the most recent sentence, but ignores word order in the long-range context (beyond 50 tokens), suggesting the distant past is modeled only as a rough semantic field or topic. We further find that the neural caching model (Grave et al., 2017b) especially helps the LSTM to copy words from within this distant context. Overall, our analysis not only provides a better understanding of how neural LMs use their context, but also sheds light on recent success from cache-based models.