Transformer is a popularly used neural network architecture, especially for language understanding. We introduce an extended and unified architecture which can be used for tasks involving a variety of modalities like image, text, videos, etc. We propose a spatio-temporal cache mechanism that enables learning spatial dimension of the input in addition to the hidden states corresponding to the temporal input sequence. The proposed architecture further enables a single model to support tasks with multiple input modalities as well as asynchronous multi-task learning, thus we refer to it as OmniNet. For example, a single instance of OmniNet can concurrently learn to perform the tasks of part-of-speech tagging, image captioning, visual question answering and video activity recognition. We demonstrate that training these four tasks together results in about three times compressed model while retaining the performance in comparison to training them individually. We also show that using this neural network pre-trained on some modalities assists in learning an unseen task. This illustrates the generalization capacity of the self-attention mechanism on the spatio-temporal cache present in OmniNet.

We present new techniques for automatically constructing probabilistic programs for data analysis, interpretation, and prediction. These techniques work with probabilistic domain-specific data modeling languages that capture key properties of a broad class of data generating processes, using Bayesian inference to synthesize probabilistic programs in these modeling languages given observed data. We provide a precise formulation of Bayesian synthesis for automatic data modeling that identifies sufficient conditions for the resulting synthesis procedure to be sound. We also derive a general class of synthesis algorithms for domain-specific languages specified by probabilistic context-free grammars and establish the soundness of our approach for these languages. We apply the techniques to automatically synthesize probabilistic programs for time series data and multivariate tabular data. We show how to analyze the structure of the synthesized programs to compute, for key qualitative properties of interest, the probability that the underlying data generating process exhibits each of these properties. Second, we translate probabilistic programs in the domain-specific language into probabilistic programs in Venture, a general-purpose probabilistic programming system. The translated Venture programs are then executed to obtain predictions of new time series data and new multivariate data records. Experimental results show that our techniques can accurately infer qualitative structure in multiple real-world data sets and outperform standard data analysis methods in forecasting and predicting new data.

We study a formalization of the grammar induction problem that models sentences as being generated by a compound probabilistic context-free grammar. In contrast to traditional formulations which learn a single stochastic grammar, our context-free rule probabilities are modulated by a per-sentence continuous latent variable, which induces marginal dependencies beyond the traditional context-free assumptions. Inference in this grammar is performed by collapsed variational inference, in which an amortized variational posterior is placed on the continuous variable, and the latent trees are marginalized with dynamic programming. Experiments on English and Chinese show the effectiveness of our approach compared to recent state-of-the-art methods for grammar induction from words with neural language models.

Semantic parsing converts natural language queries into structured logical forms. The paucity of annotated training samples is a fundamental challenge in this field. In this work, we develop a semantic parsing framework with the dual learning algorithm, which enables a semantic parser to make full use of data (labeled and even unlabeled) through a dual-learning game. This game between a primal model (semantic parsing) and a dual model (logical form to query) forces them to regularize each other, and can achieve feedback signals from some prior-knowledge. By utilizing the prior-knowledge of logical form structures, we propose a novel reward signal at the surface and semantic levels which tends to generate complete and reasonable logical forms. Experimental results show that our approach achieves new state-of-the-art performance on ATIS dataset and gets competitive performance on Overnight dataset.

In many machine learning scenarios, supervision by gold labels is not available and consequently neural models cannot be trained directly by maximum likelihood estimation (MLE). In a weak supervision scenario, metric-augmented objectives can be employed to assign feedback to model outputs, which can be used to extract a supervision signal for training. We present several objectives for two separate weakly supervised tasks, machine translation and semantic parsing. We show that objectives should actively discourage negative outputs in addition to promoting a surrogate gold structure. This notion of bipolarity is naturally present in ramp loss objectives, which we adapt to neural models. We show that bipolar ramp loss objectives outperform other non-bipolar ramp loss objectives and minimum risk training (MRT) on both weakly supervised tasks, as well as on a supervised machine translation task. Additionally, we introduce a novel token-level ramp loss objective, which is able to outperform even the best sequence-level ramp loss on both weakly supervised tasks.

Synthetic images rendered by graphics engines are a promising source for training deep networks. However, it is challenging to ensure that they can help train a network to perform well on real images, because a graphics-based generation pipeline requires numerous design decisions such as the selection of 3D shapes and the placement of the camera. In this work, we propose a new method that optimizes the generation of 3D training data based on what we call "hybrid gradient". We parametrize the design decisions as a real vector, and combine the approximate gradient and the analytical gradient to obtain the hybrid gradient of the network performance with respect to this vector. We evaluate our approach on the task of estimating surface normals from a single image. Experiments on standard benchmarks show that our approach can outperform the prior state of the art on optimizing the generation of 3D training data, particularly in terms of computational efficiency.

Different linguistic perspectives cause many diverse segmentation criteria for Chinese word segmentation (CWS). Most existing methods focus on improving the performance of single-criterion CWS. However, it is interesting to exploit these heterogeneous segmentation criteria and mine their common underlying knowledge. In this paper, we propose a concise and effective model for multi-criteria CWS, which utilizes a shared fully-connected self-attention model to segment the sentence according to a criterion indicator. Experiments on eight datasets with heterogeneous segmentation criteria show that the performance of each corpus obtains a significant improvement, compared to single-criterion learning.

Program synthesis of general-purpose source code from natural language specifications is challenging due to the need to reason about high-level patterns in the target program and low-level implementation details at the same time. In this work, we present PATOIS, a system that allows a neural program synthesizer to explicitly interleave high-level and low-level reasoning at every generation step. It accomplishes this by automatically mining common code idioms from a given corpus, incorporating them into the underlying language for neural synthesis, and training a tree-based neural synthesizer to use these idioms during code generation. We evaluate PATOIS on two complex semantic parsing datasets and show that using learned code idioms improves the synthesizer's accuracy.

The work presented in this master thesis consists of extracting a set of events from texts written in natural language. For this purpose, we have based ourselves on the basic notions of the information extraction as well as the open information extraction. First, we applied an open information extraction(OIE) system for the relationship extraction, to highlight the importance of OIEs in event extraction, and we used the ontology to the event modeling. We tested the results of our approach with test metrics. As a result, the two-level event extraction approach has shown good performance results but requires a lot of expert intervention in the construction of classifiers and this will take time. In this context we have proposed an approach that reduces the expert intervention in the relation extraction, the recognition of entities and the reasoning which are automatic and based on techniques of adaptation and correspondence. Finally, to prove the relevance of the extracted results, we conducted a set of experiments using different test metrics as well as a comparative study.

Text IQ, a machine learning system that parses and understands sensitive corporate data, has raised $12.6 million in Series A funding led by FirstMark Capital, with participation from Sierra Ventures. Text IQ started as co-founder Apoorv Agarwal's Columbia thesis project titled "Social Network Extraction From Text." The algorithm he built was able to read a novel, like Jane Austen's "Emma," for example, and understand the social hierarchy and interactions between characters. This people-centric approach to parsing unstructured data eventually became the kernel of Text IQ, which helps corporations find what they're looking for in a sea of unstructured, and highly sensitive, data. The platform started as a tool used by corporate legal teams.