Paper Group NANR 73
Relevant Emotion Ranking from Text Constrained with Emotion Relationships. Towards Evaluating Narrative Quality In Student Writing. Improving generalization by regularizing in $L^2$ function space. Proceedings of the AMTA 2018 Workshop on The Role of Authoritative Standards in the MT Environment. Noising and Denoising Natural Language: Diverse Back …
Relevant Emotion Ranking from Text Constrained with Emotion Relationships
| Title | Relevant Emotion Ranking from Text Constrained with Emotion Relationships |
| Authors | Deyu Zhou, Yang Yang, Yulan He |
| Abstract | Text might contain or invoke multiple emotions with varying intensities. As such, emotion detection, to predict multiple emotions associated with a given text, can be cast into a multi-label classification problem. We would like to go one step further so that a ranked list of relevant emotions are generated where top ranked emotions are more intensely associated with text compared to lower ranked emotions, whereas the rankings of irrelevant emotions are not important. A novel framework of relevant emotion ranking is proposed to tackle the problem. In the framework, the objective loss function is designed elaborately so that both emotion prediction and rankings of only relevant emotions can be achieved. Moreover, we observe that some emotions co-occur more often while other emotions rarely co-exist. Such information is incorporated into the framework as constraints to improve the accuracy of emotion detection. Experimental results on two real-world corpora show that the proposed framework can effectively deal with emotion detection and performs remarkably better than the state-of-the-art emotion detection approaches and multi-label learning methods. |
| Tasks | Multi-Label Classification, Multi-Label Learning, Topic Models |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1052/ |
| https://www.aclweb.org/anthology/N18-1052 | |
| PWC | https://paperswithcode.com/paper/relevant-emotion-ranking-from-text |
| Repo | |
| Framework | |
Towards Evaluating Narrative Quality In Student Writing
| Title | Towards Evaluating Narrative Quality In Student Writing |
| Authors | Swapna Somasundaran, Michael Flor, Martin Chodorow, Hillary Molloy, Binod Gyawali, Laura McCulla |
| Abstract | This work lays the foundation for automated assessments of narrative quality in student writing. We first manually score essays for narrative-relevant traits and sub-traits, and measure inter-annotator agreement. We then explore linguistic features that are indicative of good narrative writing and use them to build an automated scoring system. Experiments show that our features are more effective in scoring specific aspects of narrative quality than a state-of-the-art feature set. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/Q18-1007/ |
| https://www.aclweb.org/anthology/Q18-1007 | |
| PWC | https://paperswithcode.com/paper/towards-evaluating-narrative-quality-in |
| Repo | |
| Framework | |
Improving generalization by regularizing in $L^2$ function space
| Title | Improving generalization by regularizing in $L^2$ function space |
| Authors | Ari S Benjamin, Konrad Kording |
| Abstract | Learning rules for neural networks necessarily include some form of regularization. Most regularization techniques are conceptualized and implemented in the space of parameters. However, it is also possible to regularize in the space of functions. Here, we propose to measure networks in an $L^2$ Hilbert space, and test a learning rule that regularizes the distance a network can travel through $L^2$-space each update. This approach is inspired by the slow movement of gradient descent through parameter space as well as by the natural gradient, which can be derived from a regularization term upon functional change. The resulting learning rule, which we call Hilbert-constrained gradient descent (HCGD), is thus closely related to the natural gradient but regularizes a different and more calculable metric over the space of functions. Experiments show that the HCGD is efficient and leads to considerably better generalization. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=H1l8sz-AW |
| https://openreview.net/pdf?id=H1l8sz-AW | |
| PWC | https://paperswithcode.com/paper/improving-generalization-by-regularizing-in |
| Repo | |
| Framework | |
Proceedings of the AMTA 2018 Workshop on The Role of Authoritative Standards in the MT Environment
| Title | Proceedings of the AMTA 2018 Workshop on The Role of Authoritative Standards in the MT Environment |
| Authors | |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-2000/ |
| https://www.aclweb.org/anthology/W18-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-amta-2018-workshop-on-the |
| Repo | |
| Framework | |
Noising and Denoising Natural Language: Diverse Backtranslation for Grammar Correction
| Title | Noising and Denoising Natural Language: Diverse Backtranslation for Grammar Correction |
| Authors | Ziang Xie, Guillaume Genthial, Stanley Xie, Andrew Ng, Dan Jurafsky |
| Abstract | Translation-based methods for grammar correction that directly map noisy, ungrammatical text to their clean counterparts are able to correct a broad range of errors; however, such techniques are bottlenecked by the need for a large parallel corpus of noisy and clean sentence pairs. In this paper, we consider synthesizing parallel data by noising a clean monolingual corpus. While most previous approaches introduce perturbations using features computed from local context windows, we instead develop error generation processes using a neural sequence transduction model trained to translate clean examples to their noisy counterparts. Given a corpus of clean examples, we propose beam search noising procedures to synthesize additional noisy examples that human evaluators were nearly unable to discriminate from nonsynthesized examples. Surprisingly, when trained on additional data synthesized using our best-performing noising scheme, our model approaches the same performance as when trained on additional nonsynthesized data. |
| Tasks | Denoising, Machine Translation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1057/ |
| https://www.aclweb.org/anthology/N18-1057 | |
| PWC | https://paperswithcode.com/paper/noising-and-denoising-natural-language |
| Repo | |
| Framework | |
Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications
| Title | Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3700/ |
| https://www.aclweb.org/anthology/W18-3700 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-5th-workshop-on-natural |
| Repo | |
| Framework | |
Querying Word Embeddings for Similarity and Relatedness
| Title | Querying Word Embeddings for Similarity and Relatedness |
| Authors | Fatemeh Torabi Asr, Robert Zinkov, Michael Jones |
| Abstract | Word embeddings obtained from neural network models such as Word2Vec Skipgram have become popular representations of word meaning and have been evaluated on a variety of word similarity and relatedness norming data. Skipgram generates a set of word and context embeddings, the latter typically discarded after training. We demonstrate the usefulness of context embeddings in predicting asymmetric association between words from a recently published dataset of production norms (Jouravlev {&} McRae, 2016). Our findings suggest that humans respond with words closer to the cue within the context embedding space (rather than the word embedding space), when asked to generate thematically related words. |
| Tasks | Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1062/ |
| https://www.aclweb.org/anthology/N18-1062 | |
| PWC | https://paperswithcode.com/paper/querying-word-embeddings-for-similarity-and |
| Repo | |
| Framework | |
Automatic Pyramid Evaluation Exploiting EDU-based Extractive Reference Summaries
| Title | Automatic Pyramid Evaluation Exploiting EDU-based Extractive Reference Summaries |
| Authors | Tsutomu Hirao, Hidetaka Kamigaito, Masaaki Nagata |
| Abstract | This paper tackles automation of the pyramid method, a reliable manual evaluation framework. To construct a pyramid, we transform human-made reference summaries into extractive reference summaries that consist of Elementary Discourse Units (EDUs) obtained from source documents and then weight every EDU by counting the number of extractive reference summaries that contain the EDU. A summary is scored by the correspondences between EDUs in the summary and those in the pyramid. Experiments on DUC and TAC data sets show that our methods strongly correlate with various manual evaluations. |
| Tasks | Semantic Textual Similarity |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1450/ |
| https://www.aclweb.org/anthology/D18-1450 | |
| PWC | https://paperswithcode.com/paper/automatic-pyramid-evaluation-exploiting-edu |
| Repo | |
| Framework | |
A Bayesian Perspective on Generalization and Stochastic Gradient Descent
| Title | A Bayesian Perspective on Generalization and Stochastic Gradient Descent |
| Authors | Samuel L. Smith and Quoc V. Le |
| Abstract | We consider two questions at the heart of machine learning; how can we predict if a minimum will generalize to the test set, and why does stochastic gradient descent find minima that generalize well? Our work responds to \citet{zhang2016understanding}, who showed deep neural networks can easily memorize randomly labeled training data, despite generalizing well on real labels of the same inputs. We show that the same phenomenon occurs in small linear models. These observations are explained by the Bayesian evidence, which penalizes sharp minima but is invariant to model parameterization. We also demonstrate that, when one holds the learning rate fixed, there is an optimum batch size which maximizes the test set accuracy. We propose that the noise introduced by small mini-batches drives the parameters towards minima whose evidence is large. Interpreting stochastic gradient descent as a stochastic differential equation, we identify the ``noise scale” $g = \epsilon (\frac{N}{B} - 1) \approx \epsilon N/B$, where $\epsilon$ is the learning rate, $N$ the training set size and $B$ the batch size. Consequently the optimum batch size is proportional to both the learning rate and the size of the training set, $B_{opt} \propto \epsilon N$. We verify these predictions empirically. | |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=BJij4yg0Z |
| https://openreview.net/pdf?id=BJij4yg0Z | |
| PWC | https://paperswithcode.com/paper/a-bayesian-perspective-on-generalization-and-1 |
| Repo | |
| Framework | |
Automatic Detection of Code-switching Style from Acoustics
| Title | Automatic Detection of Code-switching Style from Acoustics |
| Authors | Rallab, SaiKrishna i, Sunayana Sitaram, Alan W Black |
| Abstract | Multilingual speakers switch between languages in an non-trivial fashion displaying inter sentential, intra sentential, and congruent lexicalization based transitions. While monolingual ASR systems may be capable of recognizing a few words from a foreign language, they are usually not robust enough to handle these varied styles of code-switching. There is also a lack of large code-switched speech corpora capturing all these styles making it difficult to build code-switched speech recognition systems. We hypothesize that it may be useful for an ASR system to be able to first detect the switching style of a particular utterance from acoustics, and then use specialized language models or other adaptation techniques for decoding the speech. In this paper, we look at the first problem of detecting code-switching style from acoustics. We classify code-switched Spanish-English and Hindi-English corpora using two metrics and show that features extracted from acoustics alone can distinguish between different kinds of code-switching in these language pairs. |
| Tasks | Language Identification, Speech Recognition |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3209/ |
| https://www.aclweb.org/anthology/W18-3209 | |
| PWC | https://paperswithcode.com/paper/automatic-detection-of-code-switching-style |
| Repo | |
| Framework | |
Simple Features for Strong Performance on Named Entity Recognition in Code-Switched Twitter Data
| Title | Simple Features for Strong Performance on Named Entity Recognition in Code-Switched Twitter Data |
| Authors | Devanshu Jain, Maria Kustikova, Mayank Darbari, Rishabh Gupta, Stephen Mayhew |
| Abstract | In this work, we address the problem of Named Entity Recognition (NER) in code-switched tweets as a part of the Workshop on Computational Approaches to Linguistic Code-switching (CALCS) at ACL{'}18. Code-switching is the phenomenon where a speaker switches between two languages or variants of the same language within or across utterances, known as intra-sentential or inter-sentential code-switching, respectively. Processing such data is challenging using state of the art methods since such technology is generally geared towards processing monolingual text. In this paper we explored ways to use language identification and translation to recognize named entities in such data, however, utilizing simple features (sans multi-lingual features) with Conditional Random Field (CRF) classifier achieved the best results. Our experiments were mainly aimed at the (ENG-SPA) English-Spanish dataset but we submitted a language-independent version of our system to the (MSA-EGY) Arabic-Egyptian dataset as well and achieved good results. |
| Tasks | Language Identification, Named Entity Recognition, Transliteration |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3213/ |
| https://www.aclweb.org/anthology/W18-3213 | |
| PWC | https://paperswithcode.com/paper/simple-features-for-strong-performance-on |
| Repo | |
| Framework | |
A Prospective-Performance Network to Alleviate Myopia in Beam Search for Response Generation
| Title | A Prospective-Performance Network to Alleviate Myopia in Beam Search for Response Generation |
| Authors | Zongsheng Wang, Yunzhi Bai, Bowen Wu, Zhen Xu, Zhuoran Wang, Baoxun Wang |
| Abstract | Generative dialog models usually adopt beam search as the inference method to generate responses. However, small-width beam search only focuses on the limited current optima. This deficiency named as myopic bias ultimately suppresses the diversity and probability of generated responses. Although increasing the beam width mitigates the myopic bias, it also proportionally slows down the inference efficiency. To alleviate the myopic bias in small-width beam search, this paper proposes a Prospective-Performance Network (PPN) to predict the future reward of the given partially-generated response, and the future reward is defined by the expectation of the partial response appearing in the top-ranked responses given by a larger-width beam search. Enhanced by PPN, the decoder can promote the results with great potential during the beam search phase. The experimental results on both Chinese and English corpora show that our method is promising to increase the quality and diversity of generated responses, with inference efficiency well maintained. |
| Tasks | Machine Translation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1306/ |
| https://www.aclweb.org/anthology/C18-1306 | |
| PWC | https://paperswithcode.com/paper/a-prospective-performance-network-to |
| Repo | |
| Framework | |
Named Entity Recognition on Code-Switched Data Using Conditional Random Fields
| Title | Named Entity Recognition on Code-Switched Data Using Conditional Random Fields |
| Authors | Utpal Kumar Sikdar, Biswanath Barik, Bj{"o}rn Gamb{"a}ck |
| Abstract | Named Entity Recognition is an important information extraction task that identifies proper names in unstructured texts and classifies them into some pre-defined categories. Identification of named entities in code-mixed social media texts is a more difficult and challenging task as the contexts are short, ambiguous and often noisy. This work proposes a Conditional Random Fields based named entity recognition system to identify proper names in code-switched data and classify them into nine categories. The system ranked fifth among nine participant systems and achieved a 59.25{%} F1-score. |
| Tasks | Language Identification, Named Entity Recognition |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3215/ |
| https://www.aclweb.org/anthology/W18-3215 | |
| PWC | https://paperswithcode.com/paper/named-entity-recognition-on-code-switched-1 |
| Repo | |
| Framework | |
Gamma-Poisson Dynamic Matrix Factorization Embedded with Metadata Influence
| Title | Gamma-Poisson Dynamic Matrix Factorization Embedded with Metadata Influence |
| Authors | Trong Dinh Thac Do, Longbing Cao |
| Abstract | A conjugate Gamma-Poisson model for Dynamic Matrix Factorization incorporated with metadata influence (mGDMF for short) is proposed to effectively and efficiently model massive, sparse and dynamic data in recommendations. Modeling recommendation problems with a massive number of ratings and very sparse or even no ratings on some users/items in a dynamic setting is very demanding and poses critical challenges to well-studied matrix factorization models due to the large-scale, sparse and dynamic nature of the data. Our proposed mGDMF tackles these challenges by introducing three strategies: (1) constructing a stable Gamma-Markov chain model that smoothly drifts over time by combining both static and dynamic latent features of data; (2) incorporating the user/item metadata into the model to tackle sparse ratings; and (3) undertaking stochastic variational inference to efficiently handle massive data. mGDMF is conjugate, dynamic and scalable. Experiments show that mGDMF significantly (both effectively and efficiently) outperforms the state-of-the-art static and dynamic models on large, sparse and dynamic data. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7824-gamma-poisson-dynamic-matrix-factorization-embedded-with-metadata-influence |
| http://papers.nips.cc/paper/7824-gamma-poisson-dynamic-matrix-factorization-embedded-with-metadata-influence.pdf | |
| PWC | https://paperswithcode.com/paper/gamma-poisson-dynamic-matrix-factorization |
| Repo | |
| Framework | |
Deep Reinforcement Learning with Iterative Shift for Visual Tracking
| Title | Deep Reinforcement Learning with Iterative Shift for Visual Tracking |
| Authors | Liangliang Ren, Xin Yuan, Jiwen Lu, Ming Yang, Jie Zhou |
| Abstract | Visual tracking is confronted by the dilemma to locate a target both}accurately and efficiently, and make decisions online whether and how to adapt the appearance model or even restart tracking. In this paper, we propose a deep reinforcement learning with iterative shift (DRL-IS) method for single object tracking, where an actor-critic network is introduced to predict the iterative shifts of object bounding boxes, and evaluate the shifts to take actions on whether to update object models or re-initialize tracking. Since locating an object is achieved by an iterative shift process, rather than online classification on many sampled locations, the proposed method is robust to cope with large deformations and abrupt motion, and computationally efficient since finding a target takes up to 10 shifts. In offline training, the critic network guides to learn how to make decisions jointly on motion estimation and tracking status in an end-to-end manner. Experimental results on the OTB benchmarks with large deformation improve the tracking precision by 1.7% and runs about 5 times faster than the competing state-of-the-art methods. |
| Tasks | Motion Estimation, Object Tracking, Visual Tracking |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Liangliang_Ren_Deep_Reinforcement_Learning_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Liangliang_Ren_Deep_Reinforcement_Learning_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-with-iterative |
| Repo | |
| Framework | |
