Paper Group NANR 127
The Variational Homoencoder: Learning to Infer High-Capacity Generative Models from Few Examples. Using exemplar responses for training and evaluating automated speech scoring systems. Squib: The Language Resource Switchboard. Facial Expression Recognition with Inconsistently Annotated Datasets. Relational Summarization for Corpus Analysis. Mallows …
The Variational Homoencoder: Learning to Infer High-Capacity Generative Models from Few Examples
| Title | The Variational Homoencoder: Learning to Infer High-Capacity Generative Models from Few Examples |
| Authors | Luke Hewitt, Andrea Gane, Tommi Jaakkola, Joshua B. Tenenbaum |
| Abstract | Hierarchical Bayesian methods have the potential to unify many related tasks (e.g. k-shot classification, conditional, and unconditional generation) by framing each as inference within a single generative model. We show that existing approaches for learning such models can fail on expressive generative networks such as PixelCNNs, by describing the global distribution with little reliance on latent variables. To address this, we develop a modification of the Variational Autoencoder in which encoded observations are decoded to new elements from the same class; the result, which we call a Variational Homoencoder (VHE), may be understood as training a hierarchical latent variable model which better utilises latent variables in these cases. Using this framework enables us to train a hierarchical PixelCNN for the Omniglot dataset, outperforming all existing models on test set likelihood. With a single model we achieve both strong one-shot generation and near human-level classification, competitive with state-of-the-art discriminative classifiers. The VHE objective extends naturally to richer dataset structures such as factorial or hierarchical categories, as we illustrate by training models to separate character content from simple variations in drawing style, and to generalise the style of an alphabet to new characters. |
| Tasks | Omniglot |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HJ5AUm-CZ |
| https://openreview.net/pdf?id=HJ5AUm-CZ | |
| PWC | https://paperswithcode.com/paper/the-variational-homoencoder-learning-to-infer |
| Repo | |
| Framework | |
Using exemplar responses for training and evaluating automated speech scoring systems
| Title | Using exemplar responses for training and evaluating automated speech scoring systems |
| Authors | Anastassia Loukina, Klaus Zechner, James Bruno, Beata Beigman Klebanov |
| Abstract | Automated scoring engines are usually trained and evaluated against human scores and compared to the benchmark of human-human agreement. In this paper we compare the performance of an automated speech scoring engine using two corpora: a corpus of almost 700,000 randomly sampled spoken responses with scores assigned by one or two raters during operational scoring, and a corpus of 16,500 exemplar responses with scores reviewed by multiple expert raters. We show that the choice of corpus used for model evaluation has a major effect on estimates of system performance with r varying between 0.64 and 0.80. Surprisingly, this is not the case for the choice of corpus for model training: when the training corpus is sufficiently large, the systems trained on different corpora showed almost identical performance when evaluated on the same corpus. We show that this effect is consistent across several learning algorithms. We conclude that evaluating the model on a corpus of exemplar responses if one is available provides additional evidence about system validity; at the same time, investing effort into creating a corpus of exemplar responses for model training is unlikely to lead to a substantial gain in model performance. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0501/ |
| https://www.aclweb.org/anthology/W18-0501 | |
| PWC | https://paperswithcode.com/paper/using-exemplar-responses-for-training-and |
| Repo | |
| Framework | |
Squib: The Language Resource Switchboard
| Title | Squib: The Language Resource Switchboard |
| Authors | Claus Zinn |
| Abstract | The CLARIN research infrastructure gives users access to an increasingly rich and diverse set of language-related resources and tools. Whereas there is ample support for searching resources using metadata-based search, or full-text search, or for aggregating resources into virtual collections, there is little support for users to help them process resources in one way or another. In spite of the large number of tools that process texts in many different languages, there is no single point of access where users can find tools to fit their needs and the resources they have. In this squib, we present the Language Resource Switchboard (LRS), which helps users to discover tools that can process their resources. For this, the LRS identifies all applicable tools for a given resource, lists the tasks the tools can achieve, and invokes the selected tool in such a way so that processing can start immediately with little or no prior tool parameterization. |
| Tasks | |
| Published | 2018-12-01 |
| URL | https://www.aclweb.org/anthology/J18-4002/ |
| https://www.aclweb.org/anthology/J18-4002 | |
| PWC | https://paperswithcode.com/paper/squib-the-language-resource-switchboard |
| Repo | |
| Framework | |
Facial Expression Recognition with Inconsistently Annotated Datasets
| Title | Facial Expression Recognition with Inconsistently Annotated Datasets |
| Authors | Jiabei Zeng, Shiguang Shan, Xilin Chen |
| Abstract | Annotation errors and bias are inevitable among different facial expression datasets due to the subjectiveness of annotating facial expressions. Ascribe to the inconsistent annotations, performance of existing facial expression recognition (FER) methods cannot keep improving when the training set is enlarged by merging multiple datasets. To address the inconsistency, we propose an Inconsistent Pseudo Annotations to Latent Truth(IPA2LT) framework to train a FER model from multiple inconsistently labeled datasets and large scale unlabeled data. In IPA2LT, we assign each sample more than one labels with human annotations or model predictions. Then, we propose an end-to-end LTNet with a scheme of discovering the latent truth from the inconsistent pseudo labels and the input face images. To our knowledge, IPA2LT serves as the first work to solve the training problem with inconsistently labeled FER datasets. Experiments on synthetic data validate the effectiveness of the proposed method in learning from inconsistent labels. We also conduct extensive experiments in FER and show that our method outperforms other state-of-the-art and optional methods under a rigorous evaluation protocol involving 7 FER datasets. |
| Tasks | Facial Expression Recognition |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Jiabei_Zeng_Facial_Expression_Recognition_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Jiabei_Zeng_Facial_Expression_Recognition_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/facial-expression-recognition-with |
| Repo | |
| Framework | |
Relational Summarization for Corpus Analysis
| Title | Relational Summarization for Corpus Analysis |
| Authors | H, Abram ler, Brendan O{'}Connor |
| Abstract | This work introduces a new problem, relational summarization, in which the goal is to generate a natural language summary of the relationship between two lexical items in a corpus, without reference to a knowledge base. Motivated by the needs of novel user interfaces, we define the task and give examples of its application. We also present a new query-focused method for finding natural language sentences which express relationships. Our method allows for summarization of more than two times more query pairs than baseline relation extractors, while returning measurably more readable output. Finally, to help guide future work, we analyze the challenges of relational summarization using both a news and a social media corpus. |
| Tasks | Relation Extraction |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1159/ |
| https://www.aclweb.org/anthology/N18-1159 | |
| PWC | https://paperswithcode.com/paper/relational-summarization-for-corpus-analysis |
| Repo | |
| Framework | |
Mallows Models for Top-k Lists
| Title | Mallows Models for Top-k Lists |
| Authors | Flavio Chierichetti, Anirban Dasgupta, Shahrzad Haddadan, Ravi Kumar, Silvio Lattanzi |
| Abstract | The classic Mallows model is a widely-used tool to realize distributions on per- mutations. Motivated by common practical situations, in this paper, we generalize Mallows to model distributions on top-k lists by using a suitable distance measure between top-k lists. Unlike many earlier works, our model is both analytically tractable and computationally efficient. We demonstrate this by studying two basic problems in this model, namely, sampling and reconstruction, from both algorithmic and experimental points of view. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7691-mallows-models-for-top-k-lists |
| http://papers.nips.cc/paper/7691-mallows-models-for-top-k-lists.pdf | |
| PWC | https://paperswithcode.com/paper/mallows-models-for-top-k-lists |
| Repo | |
| Framework | |
EMTC: Multilabel Corpus in Movie Domain for Emotion Analysis in Conversational Text
| Title | EMTC: Multilabel Corpus in Movie Domain for Emotion Analysis in Conversational Text |
| Authors | Duc-Anh Phan, Yuji Matsumoto |
| Abstract | |
| Tasks | Emotion Classification, Emotion Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1418/ |
| https://www.aclweb.org/anthology/L18-1418 | |
| PWC | https://paperswithcode.com/paper/emtc-multilabel-corpus-in-movie-domain-for |
| Repo | |
| Framework | |
Learning Neural Representation for CLIR with Adversarial Framework
| Title | Learning Neural Representation for CLIR with Adversarial Framework |
| Authors | Bo Li, Ping Cheng |
| Abstract | The existing studies in cross-language information retrieval (CLIR) mostly rely on general text representation models (e.g., vector space model or latent semantic analysis). These models are not optimized for the target retrieval task. In this paper, we follow the success of neural representation in natural language processing (NLP) and develop a novel text representation model based on adversarial learning, which seeks a task-specific embedding space for CLIR. Adversarial learning is implemented as an interplay between the generator process and the discriminator process. In order to adapt adversarial learning to CLIR, we design three constraints to direct representation learning, which are (1) a matching constraint capturing essential characteristics of cross-language ranking, (2) a translation constraint bridging language gaps, and (3) an adversarial constraint forcing both language and media invariant to be reached more efficiently and effectively. Through the joint exploitation of these constraints in an adversarial manner, the underlying cross-language semantics relevant to retrieval tasks are better preserved in the embedding space. Standard CLIR experiments show that our model significantly outperforms state-of-the-art continuous space models and is better than the strong machine translation baseline. |
| Tasks | Document Ranking, Information Retrieval, Machine Translation, Representation Learning |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1212/ |
| https://www.aclweb.org/anthology/D18-1212 | |
| PWC | https://paperswithcode.com/paper/learning-neural-representation-for-clir-with |
| Repo | |
| Framework | |
Supervising the new with the old: learning SFM from SFM
| Title | Supervising the new with the old: learning SFM from SFM |
| Authors | Maria Klodt, Andrea Vedaldi |
| Abstract | Recent work has demonstrated that it is possible to learn deep neural networks for monocular depth and ego-motion estimation from unlabelled video sequences, an interesting theoretical development with numerous advantages in applications. In this paper, we propose a number of improvements to these approaches. First, since such self-supervised approaches are based on the brightness constancy assumption, which is valid only for a subset of pixels, we propose a probabilistic learning formulation where the network predicts distributions over variables rather than specific values. As these distributions are conditioned on the observed image, the network can learn which scene and object types are likely to violate the model assumptions, resulting in more robust learning. We also propose to build on dozens of years of experience in developing handcrafted structure-from-motion (SFM) algorithms. We do so by using an off-the-shelf SFM system to generate a supervisory signal for the deep neural network. While this signal is also noisy, we show that our probabilistic formulation can learn and account for the defects of SFM, helping to integrate different sources of information and boosting the overall performance of the network. |
| Tasks | Motion Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Maria_Klodt_Supervising_the_new_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Maria_Klodt_Supervising_the_new_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/supervising-the-new-with-the-old-learning-sfm |
| Repo | |
| Framework | |
A Neural Autoencoder Approach for Document Ranking and Query Refinement in Pharmacogenomic Information Retrieval
| Title | A Neural Autoencoder Approach for Document Ranking and Query Refinement in Pharmacogenomic Information Retrieval |
| Authors | Jonas Pfeiffer, Samuel Broscheit, Rainer Gemulla, Mathias G{"o}schl |
| Abstract | In this study, we investigate learning-to-rank and query refinement approaches for information retrieval in the pharmacogenomic domain. The goal is to improve the information retrieval process of biomedical curators, who manually build knowledge bases for personalized medicine. We study how to exploit the relationships between genes, variants, drugs, diseases and outcomes as features for document ranking and query refinement. For a supervised approach, we are faced with a small amount of annotated data and a large amount of unannotated data. Therefore, we explore ways to use a neural document auto-encoder in a semi-supervised approach. We show that a combination of established algorithms, feature-engineering and a neural auto-encoder model yield promising results in this setting. |
| Tasks | Decision Making, Document Ranking, Feature Engineering, Information Retrieval, Learning-To-Rank |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2310/ |
| https://www.aclweb.org/anthology/W18-2310 | |
| PWC | https://paperswithcode.com/paper/a-neural-autoencoder-approach-for-document |
| Repo | |
| Framework | |
Turning NMT Research into Commercial Products
| Title | Turning NMT Research into Commercial Products |
| Authors | Dragos Munteanu, Adri{`a} Gispert |
| Abstract | |
| Tasks | |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1914/ |
| https://www.aclweb.org/anthology/W18-1914 | |
| PWC | https://paperswithcode.com/paper/turning-nmt-research-into-commercial-products |
| Repo | |
| Framework | |
Phrase2VecGLM: Neural generalized language model–based semantic tagging for complex query reformulation in medical IR
| Title | Phrase2VecGLM: Neural generalized language model–based semantic tagging for complex query reformulation in medical IR |
| Authors | Manirupa Das, Eric Fosler-Lussier, Simon Lin, Soheil Moosavinasab, David Chen, Steve Rust, Yungui Huang, Rajiv Ramnath |
| Abstract | In this work, we develop a novel, completely unsupervised, neural language model-based document ranking approach to semantic tagging of documents, using the document to be tagged as a query into the GLM to retrieve candidate phrases from top-ranked related documents, thus associating every document with novel related concepts extracted from the text. For this we extend the word embedding-based general language model due to Ganguly et al 2015, to employ phrasal embeddings, and use the semantic tags thus obtained for downstream query expansion, both directly and in feedback loop settings. Our method, evaluated using the TREC 2016 clinical decision support challenge dataset, shows statistically significant improvement not only over various baselines that use standard MeSH terms and UMLS concepts for query expansion, but also over baselines using human expert{–}assigned concept tags for the queries, run on top of a standard Okapi BM25{–}based document retrieval system. |
| Tasks | Document Ranking, Information Retrieval, Knowledge Graphs, Language Modelling, Question Answering |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2313/ |
| https://www.aclweb.org/anthology/W18-2313 | |
| PWC | https://paperswithcode.com/paper/phrase2vecglm-neural-generalized-language |
| Repo | |
| Framework | |
SyntNN at SemEval-2018 Task 2: is Syntax Useful for Emoji Prediction? Embedding Syntactic Trees in Multi Layer Perceptrons
| Title | SyntNN at SemEval-2018 Task 2: is Syntax Useful for Emoji Prediction? Embedding Syntactic Trees in Multi Layer Perceptrons |
| Authors | Fabio Massimo Zanzotto, Andrea Santilli |
| Abstract | In this paper, we present SyntNN as a way to include traditional syntactic models in multilayer neural networks used in the task of Semeval Task 2 of emoji prediction. The model builds on the distributed tree embedder also known as distributed tree kernel. Initial results are extremely encouraging but additional analysis is needed to overcome the problem of overfitting. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1076/ |
| https://www.aclweb.org/anthology/S18-1076 | |
| PWC | https://paperswithcode.com/paper/syntnn-at-semeval-2018-task-2-is-syntax |
| Repo | |
| Framework | |
SMT versus NMT: Preliminary comparisons for Irish
| Title | SMT versus NMT: Preliminary comparisons for Irish |
| Authors | Meghan Dowling, Teresa Lynn, Alberto Poncelas, Andy Way |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-2202/ |
| https://www.aclweb.org/anthology/W18-2202 | |
| PWC | https://paperswithcode.com/paper/smt-versus-nmt-preliminary-comparisons-for |
| Repo | |
| Framework | |
Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations
| Title | Proceedings of the 27th International Conference on Computational Linguistics: System Demonstrations |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-2000/ |
| https://www.aclweb.org/anthology/C18-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-27th-international |
| Repo | |
| Framework | |
