http://pancamr.lecture.ub.ac.id/files/2012/02/A-survey-on-vision-based-human-action-recognition_Image-and-Vision-Computing_2010.pdf

A survey on vision-based human action recognition

Labeling training data is increasingly the largest bottleneck in deploying machine learning systems. We present Snorkel, a first-of-its-kind system that enables users to train state-of-the-art models without hand labeling any training data. Instead, users write labeling functions that express arbitrary heuristics, which can have unknown accuracies and correlations. Snorkel denoises their outputs without access to ground truth by incorporating the first end-to-end implementation of our recently proposed machine learning paradigm, data programming. We present a flexible interface layer for writing labeling functions based on our experience over the past year collaborating with companies, agencies, and research labs. In a user study, subject matter experts build models 2.8X faster and increase predictive performance an average 45.5% versus seven hours of hand labeling. We study the modeling tradeoffs in this new setting and propose an optimizer for automating tradeoff decisions that gives up to 1.8X speedup per pipeline execution. In two collaborations, with the U.S. Department of Veterans Affairs and the U.S. Food and Drug Administration, and on four open-source text and image data sets representative of other deployments, Snorkel provides 132% average improvements to predictive performance over prior heuristic approaches and comes within an average 3.60% of the predictive performance of large hand-curated training sets.

/pdf/snorkel-rapid-training-data-creation-with-weak-supervision-15qyryp476.pdf

Snorkel: rapid training data creation with weak supervision

We present LDAvis, a web-based interactive visualization of topics estimated using Latent Dirichlet Allocation that is built using a combination of R and D3. Our visualization provides a global view of the topics (and how they differ from each other), while at the same time allowing for a deep inspection of the terms most highly associated with each individual topic. First, we propose a novel method for choosing which terms to present to a user to aid in the task of topic interpretation, in which we define the relevance of a term to a topic. Second, we present results from a user study that suggest that ranking terms purely by their probability under a topic is suboptimal for topic interpretation. Last, we describe LDAvis, our visualization system that allows users to flexibly explore topic-term relationships using relevance to better understand a fitted LDA model.

/pdf/ldavis-a-method-for-visualizing-and-interpreting-topics-293hxgmxqn.pdf

LDAvis: A method for visualizing and interpreting topics

We present a system to automatically generate natural language descriptions from images. This system consists of two parts. The first part, content planning, smooths the output of computer vision-based detection and recognition algorithms with statistics mined from large pools of visually descriptive text to determine the best content words to use to describe an image. The second step, surface realization, chooses words to construct natural language sentences based on the predicted content and general statistics from natural language. We present multiple approaches for the surface realization step and evaluate each using automatic measures of similarity to human generated reference descriptions. We also collect forced choice human evaluations between descriptions from the proposed generation system and descriptions from competing approaches. The proposed system is very effective at producing relevant sentences for images. It also generates descriptions that are notably more true to the specific image content than previous work.

/pdf/babytalk-understanding-and-generating-simple-image-4k1zgl82iq.pdf

BabyTalk: Understanding and Generating Simple Image Descriptions

Distant supervision for relation extraction (RE) -- gathering training data by aligning a database of facts with text -- is an efficient approach to scale RE to thousands of different relations. However, this introduces a challenging learning scenario where the relation expressed by a pair of entities found in a sentence is unknown. For example, a sentence containing Balzac and France may express BornIn or Died, an unknown relation, or no relation at all. Because of this, traditional supervised learning, which assumes that each example is explicitly mapped to a label, is not appropriate. We propose a novel approach to multi-instance multi-label learning for RE, which jointly models all the instances of a pair of entities in text and all their labels using a graphical model with latent variables. Our model performs competitively on two difficult domains.

/pdf/multi-instance-multi-label-learning-for-relation-extraction-4q8wivifiw.pdf

Multi-instance Multi-label Learning for Relation Extraction

One of the first steps in the utterance interpretation pipeline of many task-oriented conversational AI systems is to identify user intents and the corresponding slots. Since data collection for machine learning models for this task is time-consuming, it is desirable to make use of existing data in a high-resource language to train models in low-resource languages. However, development of such models has largely been hindered by the lack of multilingual training data. In this paper, we present a new data set of 57k annotated utterances in English (43k), Spanish (8.6k) and Thai (5k) across the domains weather, alarm, and reminder. We use this data set to evaluate three different cross-lingual transfer methods: (1) translating the training data, (2) using cross-lingual pre-trained embeddings, and (3) a novel method of using a multilingual machine translation encoder as contextual word representations. We find that given several hundred training examples in the the target language, the latter two methods outperform translating the training data. Further, in very low-resource settings, multilingual contextual word representations give better results than using cross-lingual static embeddings. We also compare the cross-lingual methods to using monolingual resources in the form of contextual ELMo representations and find that given just small amounts of target language data, this method outperforms all cross-lingual methods, which highlights the need for more sophisticated cross-lingual methods.

Cross-lingual Transfer Learning for Multilingual Task Oriented Dialog

We propose Make-A-Video -- an approach for directly translating the tremendous recent progress in Text-to-Image (T2I) generation to Text-to-Video (T2V). Our intuition is simple: learn what the world looks like and how it is described from paired text-image data, and learn how the world moves from unsupervised video footage. Make-A-Video has three advantages: (1) it accelerates training of the T2V model (it does not need to learn visual and multimodal representations from scratch), (2) it does not require paired text-video data, and (3) the generated videos inherit the vastness (diversity in aesthetic, fantastical depictions, etc.) of today's image generation models. We design a simple yet effective way to build on T2I models with novel and effective spatial-temporal modules. First, we decompose the full temporal U-Net and attention tensors and approximate them in space and time. Second, we design a spatial temporal pipeline to generate high resolution and frame rate videos with a video decoder, interpolation model and two super resolution models that can enable various applications besides T2V. In all aspects, spatial and temporal resolution, faithfulness to text, and quality, Make-A-Video sets the new state-of-the-art in text-to-video generation, as determined by both qualitative and quantitative measures.

Make-A-Video: Text-to-Video Generation without Text-Video Data

Task oriented dialog systems typically first parse user utterances to semantic frames comprised of intents and slots. Previous work on task oriented intent and slot-filling work has been restricted to one intent per query and one slot label per token, and thus cannot model complex compositional requests. Alternative semantic parsing systems have represented queries as logical forms, but these are challenging to annotate and parse. We propose a hierarchical annotation scheme for semantic parsing that allows the representation of compositional queries, and can be efficiently and accurately parsed by standard constituency parsing models. We release a dataset of 44k annotated queries (http://fb.me/semanticparsingdialog), and show that parsing models outperform sequence-to-sequence approaches on this dataset.

/pdf/semantic-parsing-for-task-oriented-dialog-using-hierarchical-aetuy3mg88.pdf

Semantic Parsing for Task Oriented Dialog using Hierarchical Representations

Bootstrapped pattern learning for entity extraction usually starts with seed entities and iteratively learns patterns and entities from unlabeled text. Patterns are scored by their ability to extract more positive entities and less negative entities. A problem is that due to the lack of labeled data, unlabeled entities are either assumed to be negative or are ignored by the existing pattern scoring measures. In this paper, we improve pattern scoring by predicting the labels of unlabeled entities. We use various unsupervised features based on contrasting domain-specific and general text, and exploiting distributional similarity and edit distances to learned entities. Our system outperforms existing pattern scoring algorithms for extracting drug-andtreatment entities from four medical forums.

/pdf/improved-pattern-learning-for-bootstrapped-entity-extraction-z4b65awndn.pdf

Improved Pattern Learning for Bootstrapped Entity Extraction

We present a method for characterizing a research work in terms of its focus, domain of application, and techniques used. We show how tracing these aspects over time provides a novel measure of the influence of research communities on each other. We extract these characteristics by matching semantic extraction patterns, learned using bootstrapping, to the dependency trees of sentences in an article’s

/pdf/analyzing-the-dynamics-of-research-by-extracting-key-aspects-5dp5r0pj4i.pdf

Sonal Gupta

Papers

Cross-lingual Transfer Learning for Multilingual Task Oriented Dialog

Make-A-Video: Text-to-Video Generation without Text-Video Data

Semantic Parsing for Task Oriented Dialog using Hierarchical Representations

Improved Pattern Learning for Bootstrapped Entity Extraction

Analyzing the Dynamics of Research by Extracting Key Aspects of Scientific Papers