Paper Group NANR 183
Optimal Subsampling with Influence Functions. An Analysis of Scale Invariance in Object Detection  SNIP. Effective Crowdsourcing for a New Type of Summarization Task. When data permutations are pathological: the case of neural natural language inference. Generating Classical Chinese Poems via Conditional Variational Autoencoder and Adversarial Tr …
Optimal Subsampling with Influence Functions
| Title | Optimal Subsampling with Influence Functions |
| Authors | Daniel Ting, Eric Brochu |
| Abstract | Subsampling is a common and often effective method to deal with the computational challenges of large datasets. However, for most statistical models, there is no well-motivated approach for drawing a non-uniform subsample. We show that the concept of an asymptotically linear estimator and the associated influence function leads to asymptotically optimal sampling probabilities for a wide class of popular models. This is the only tight optimality result for subsampling we are aware of as other methods only provide probabilistic error bounds or optimal rates. Furthermore, for linear regression models, which have well-studied procedures for non-uniform subsampling, we empirically show our optimal influence function based method outperforms previous approaches even when using approximations to the optimal probabilities. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7623-optimal-subsampling-with-influence-functions |
| http://papers.nips.cc/paper/7623-optimal-subsampling-with-influence-functions.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-subsampling-with-influence-functions |
| Repo | |
| Framework | |
An Analysis of Scale Invariance in Object Detection  SNIP
| Title | An Analysis of Scale Invariance in Object Detection  SNIP |
| Authors | Bharat Singh, Larry S. Davis |
| Abstract | An analysis of different techniques for recognizing and detecting objects under extreme scale variation is presented. Scale specific and scale invariant design of detectors are compared by training them with different configurations of input data. By evaluating the performance of different network architectures for classifying small objects on ImageNet, we show that CNNs are not robust to changes in scale. Based on this analysis, we propose to train and test detectors on the same scales of an image-pyramid. Since small and large objects are difficult to recognize at smaller and larger scales respectively, we present a novel training scheme called Scale Normalization for Image Pyramids (SNIP) which selectively back-propagates the gradients of object instances of different sizes as a function of the image scale. On the COCO dataset, our single model performance is 45.7% and an ensemble of 3 networks obtains an mAP of 48.3%. We use off-the-shelf ImageNet-1000 pre-trained models and only train with bounding box supervision. Our submission won the Best Student Entry in the COCO 2017 challenge. Code will be made available at url{http://bit.ly/2yXVg4c}. |
| Tasks | Object Detection |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Singh_An_Analysis_of_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Singh_An_Analysis_of_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/an-analysis-of-scale-invariance-in-object |
| Repo | |
| Framework | |
Effective Crowdsourcing for a New Type of Summarization Task
| Title | Effective Crowdsourcing for a New Type of Summarization Task |
| Authors | Youxuan Jiang, Catherine Finegan-Dollak, Jonathan K. Kummerfeld, Walter Lasecki |
| Abstract | Most summarization research focuses on summarizing the entire given text, but in practice readers are often interested in only one aspect of the document or conversation. We propose targeted summarization as an umbrella category for summarization tasks that intentionally consider only parts of the input data. This covers query-based summarization, update summarization, and a new task we propose where the goal is to summarize a particular aspect of a document. However, collecting data for this new task is hard because directly asking annotators (e.g., crowd workers) to write summaries leads to data with low accuracy when there are a large number of facts to include. We introduce a novel crowdsourcing workflow, Pin-Refine, that allows us to collect high-quality summaries for our task, a necessary step for the development of automatic systems. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2099/ |
| https://www.aclweb.org/anthology/N18-2099 | |
| PWC | https://paperswithcode.com/paper/effective-crowdsourcing-for-a-new-type-of |
| Repo | |
| Framework | |
When data permutations are pathological: the case of neural natural language inference
| Title | When data permutations are pathological: the case of neural natural language inference |
| Authors | Natalie Schluter, Daniel Varab |
| Abstract | Consider two competitive machine learning models, one of which was considered state-of-the art, and the other a competitive baseline. Suppose that by just permuting the examples of the training set, say by reversing the original order, by shuffling, or by mini-batching, you could report substantially better/worst performance for the system of your choice, by multiple percentage points. In this paper, we illustrate this scenario for a trending NLP task: Natural Language Inference (NLI). We show that for the two central NLI corpora today, the learning process of neural systems is far too sensitive to permutations of the data. In doing so we reopen the question of how to judge a good neural architecture for NLI, given the available dataset and perhaps, further, the soundness of the NLI task itself in its current state. |
| Tasks | Natural Language Inference |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1534/ |
| https://www.aclweb.org/anthology/D18-1534 | |
| PWC | https://paperswithcode.com/paper/when-data-permutations-are-pathological-the |
| Repo | |
| Framework | |
Generating Classical Chinese Poems via Conditional Variational Autoencoder and Adversarial Training
| Title | Generating Classical Chinese Poems via Conditional Variational Autoencoder and Adversarial Training |
| Authors | Juntao Li, Yan Song, Haisong Zhang, Dongmin Chen, Shuming Shi, Dongyan Zhao, Rui Yan |
| Abstract | It is a challenging task to automatically compose poems with not only fluent expressions but also aesthetic wording. Although much attention has been paid to this task and promising progress is made, there exist notable gaps between automatically generated ones with those created by humans, especially on the aspects of term novelty and thematic consistency. Towards filling the gap, in this paper, we propose a conditional variational autoencoder with adversarial training for classical Chinese poem generation, where the autoencoder part generates poems with novel terms and a discriminator is applied to adversarially learn their thematic consistency with their titles. Experimental results on a large poetry corpus confirm the validity and effectiveness of our model, where its automatic and human evaluation scores outperform existing models. |
| Tasks | Machine Translation, Text Generation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1423/ |
| https://www.aclweb.org/anthology/D18-1423 | |
| PWC | https://paperswithcode.com/paper/generating-classical-chinese-poems-via |
| Repo | |
| Framework | |
Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching
| Title | Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3200/ |
| https://www.aclweb.org/anthology/W18-3200 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-third-workshop-on-2 |
| Repo | |
| Framework | |
Neural Hidden Markov Model for Machine Translation
| Title | Neural Hidden Markov Model for Machine Translation |
| Authors | Weiyue Wang, Derui Zhu, Tamer Alkhouli, Zixuan Gan, Hermann Ney |
| Abstract | Attention-based neural machine translation (NMT) models selectively focus on specific source positions to produce a translation, which brings significant improvements over pure encoder-decoder sequence-to-sequence models. This work investigates NMT while replacing the attention component. We study a neural hidden Markov model (HMM) consisting of neural network-based alignment and lexicon models, which are trained jointly using the forward-backward algorithm. We show that the attention component can be effectively replaced by the neural network alignment model and the neural HMM approach is able to provide comparable performance with the state-of-the-art attention-based models on the WMT 2017 German↔English and Chinese→English translation tasks. |
| Tasks | Machine Translation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2060/ |
| https://www.aclweb.org/anthology/P18-2060 | |
| PWC | https://paperswithcode.com/paper/neural-hidden-markov-model-for-machine |
| Repo | |
| Framework | |
基於數字文本相關之語者驗證系統的研究與實作 (Study and Implementation on Digit-related Speaker Verification) [In Chinese]
| Title | 基於數字文本相關之語者驗證系統的研究與實作 (Study and Implementation on Digit-related Speaker Verification) [In Chinese] |
| Authors | Chung-Hung Chou, Jyh-Shing Roger Jang, Shan-Wen Hsiao |
| Abstract | |
| Tasks | Speaker Recognition, Speaker Verification |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/O18-1001/ |
| https://www.aclweb.org/anthology/O18-1001 | |
| PWC | https://paperswithcode.com/paper/ao14-ac-ea1eaeeec3ccc-cea-a12-study-and |
| Repo | |
| Framework | |
Neural Caption Generation for News Images
| Title | Neural Caption Generation for News Images |
| Authors | Vishwash Batra, Yulan He, George Vogiatzis |
| Abstract | |
| Tasks | Image Captioning, Information Retrieval, Machine Translation, Speech Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1273/ |
| https://www.aclweb.org/anthology/L18-1273 | |
| PWC | https://paperswithcode.com/paper/neural-caption-generation-for-news-images |
| Repo | |
| Framework | |
Transition-Based Chinese AMR Parsing
| Title | Transition-Based Chinese AMR Parsing |
| Authors | Chuan Wang, Bin Li, Nianwen Xue |
| Abstract | This paper presents the first AMR parser built on the Chinese AMR bank. By applying a transition-based AMR parsing framework to Chinese, we first investigate how well the transitions first designed for English AMR parsing generalize to Chinese and provide a comparative analysis between the transitions for English and Chinese. We then perform a detailed error analysis to identify the major challenges in Chinese AMR parsing that we hope will inform future research in this area. |
| Tasks | Amr Parsing, Reading Comprehension, Text Generation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2040/ |
| https://www.aclweb.org/anthology/N18-2040 | |
| PWC | https://paperswithcode.com/paper/transition-based-chinese-amr-parsing |
| Repo | |
| Framework | |
Encoding Conversation Context for Neural Keyphrase Extraction from Microblog Posts
| Title | Encoding Conversation Context for Neural Keyphrase Extraction from Microblog Posts |
| Authors | Yingyi Zhang, Jing Li, Yan Song, Chengzhi Zhang |
| Abstract | Existing keyphrase extraction methods suffer from data sparsity problem when they are conducted on short and informal texts, especially microblog messages. Enriching context is one way to alleviate this problem. Considering that conversations are formed by reposting and replying messages, they provide useful clues for recognizing essential content in target posts and are therefore helpful for keyphrase identification. In this paper, we present a neural keyphrase extraction framework for microblog posts that takes their conversation context into account, where four types of neural encoders, namely, averaged embedding, RNN, attention, and memory networks, are proposed to represent the conversation context. Experimental results on Twitter and Weibo datasets show that our framework with such encoders outperforms state-of-the-art approaches. |
| Tasks | Information Retrieval, Text Summarization |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1151/ |
| https://www.aclweb.org/anthology/N18-1151 | |
| PWC | https://paperswithcode.com/paper/encoding-conversation-context-for-neural |
| Repo | |
| Framework | |
Sparse Attentive Backtracking: Temporal Credit Assignment Through Reminding
| Title | Sparse Attentive Backtracking: Temporal Credit Assignment Through Reminding |
| Authors | Nan Rosemary Ke, Anirudh Goyal Alias Parth Goyal, Olexa Bilaniuk, Jonathan Binas, Michael C. Mozer, Chris Pal, Yoshua Bengio |
| Abstract | Learning long-term dependencies in extended temporal sequences requires credit assignment to events far back in the past. The most common method for training recurrent neural networks, back-propagation through time (BPTT), requires credit information to be propagated backwards through every single step of the forward computation, potentially over thousands or millions of time steps. This becomes computationally expensive or even infeasible when used with long sequences. Importantly, biological brains are unlikely to perform such detailed reverse replay over very long sequences of internal states (consider days, months, or years.) However, humans are often reminded of past memories or mental states which are associated with the current mental state. We consider the hypothesis that such memory associations between past and present could be used for credit assignment through arbitrarily long sequences, propagating the credit assigned to the current state to the associated past state. Based on this principle, we study a novel algorithm which only back-propagates through a few of these temporal skip connections, realized by a learned attention mechanism that associates current states with relevant past states. We demonstrate in experiments that our method matches or outperforms regular BPTT and truncated BPTT in tasks involving particularly long-term dependencies, but without requiring the biologically implausible backward replay through the whole history of states. Additionally, we demonstrate that the proposed method transfers to longer sequences significantly better than LSTMs trained with BPTT and LSTMs trained with full self-attention. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7991-sparse-attentive-backtracking-temporal-credit-assignment-through-reminding |
| http://papers.nips.cc/paper/7991-sparse-attentive-backtracking-temporal-credit-assignment-through-reminding.pdf | |
| PWC | https://paperswithcode.com/paper/sparse-attentive-backtracking-temporal-credit |
| Repo | |
| Framework | |
The Computational Complexity of Distinctive Feature Minimization in Phonology
| Title | The Computational Complexity of Distinctive Feature Minimization in Phonology |
| Authors | Hubie Chen, Mans Hulden |
| Abstract | We analyze the complexity of the problem of determining whether a set of phonemes forms a natural class and, if so, that of finding the minimal feature specification for the class. A standard assumption in phonology is that finding a minimal feature specification is an automatic part of acquisition and generalization. We find that the natural class decision problem is tractable (i.e. is in P), while the minimization problem is not; the decision version of the problem which determines whether a natural class can be defined with $k$ features or less is NP-complete. We also show that, empirically, a greedy algorithm for finding minimal feature specifications will sometimes fail, and thus cannot be assumed to be the basis for human performance in solving the problem. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2086/ |
| https://www.aclweb.org/anthology/N18-2086 | |
| PWC | https://paperswithcode.com/paper/the-computational-complexity-of-distinctive |
| Repo | |
| Framework | |
Estimating Summary Quality with Pairwise Preferences
| Title | Estimating Summary Quality with Pairwise Preferences |
| Authors | Markus Zopf |
| Abstract | Automatic evaluation systems in the field of automatic summarization have been relying on the availability of gold standard summaries for over ten years. Gold standard summaries are expensive to obtain and often require the availability of domain experts to achieve high quality. In this paper, we propose an alternative evaluation approach based on pairwise preferences of sentences. In comparison to gold standard summaries, they are simpler and cheaper to obtain. In our experiments, we show that humans are able to provide useful feedback in the form of pairwise preferences. The new framework performs better than the three most popular versions of ROUGE with less expensive human input. We also show that our framework can reuse already available evaluation data and achieve even better results. |
| Tasks | Text Summarization |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1152/ |
| https://www.aclweb.org/anthology/N18-1152 | |
| PWC | https://paperswithcode.com/paper/estimating-summary-quality-with-pairwise |
| Repo | |
| Framework | |
Variable Typing: Assigning Meaning to Variables in Mathematical Text
| Title | Variable Typing: Assigning Meaning to Variables in Mathematical Text |
| Authors | Yiannos Stathopoulos, Simon Baker, Marek Rei, Simone Teufel |
| Abstract | Information about the meaning of mathematical variables in text is useful in NLP/IR tasks such as symbol disambiguation, topic modeling and mathematical information retrieval (MIR). We introduce \textit{variable typing}, the task of assigning one \textit{mathematical type} (multi-word technical terms referring to mathematical concepts) to each variable in a sentence of mathematical text. As part of this work, we also introduce a new annotated data set composed of 33,524 data points extracted from scientific documents published on arXiv. Our intrinsic evaluation demonstrates that our data set is sufficient to successfully train and evaluate current classifiers from three different model architectures. The best performing model is evaluated on an extrinsic task: MIR, by producing a \textit{typed formula index}. Our results show that the best performing MIR models make use of our typed index, compared to a formula index only containing raw symbols, thereby demonstrating the usefulness of variable typing. |
| Tasks | Information Retrieval |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1028/ |
| https://www.aclweb.org/anthology/N18-1028 | |
| PWC | https://paperswithcode.com/paper/variable-typing-assigning-meaning-to |
| Repo | |
| Framework | |
