Paper Group NANR 237
Normalising Non-standardised Orthography in Algerian Code-switched User-generated Data. Multi-Channel Convolutional Neural Network for Twitter Emotion and Sentiment Recognition. Hyperspectral Imaging With Random Printed Mask. End-to-End Neural Context Reconstruction in Chinese Dialogue. Classification of Semantic Paraphasias: Optimization of a Word …
Normalising Non-standardised Orthography in Algerian Code-switched User-generated Data
| Title | Normalising Non-standardised Orthography in Algerian Code-switched User-generated Data |
| Authors | Wafia Adouane, Jean-Philippe Bernardy, Simon Dobnik |
| Abstract | We work with Algerian, an under-resourced non-standardised Arabic variety, for which we compile a new parallel corpus consisting of user-generated textual data matched with normalised and corrected human annotations following data-driven and our linguistically motivated standard. We use an end-to-end deep neural model designed to deal with context-dependent spelling correction and normalisation. Results indicate that a model with two CNN sub-network encoders and an LSTM decoder performs the best, and that word context matters. Additionally, pre-processing data token-by-token with an edit-distance based aligner significantly improves the performance. We get promising results for the spelling correction and normalisation, as a pre-processing step for downstream tasks, on detecting binary Semantic Textual Similarity. |
| Tasks | Semantic Textual Similarity, Spelling Correction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5518/ |
| https://www.aclweb.org/anthology/D19-5518 | |
| PWC | https://paperswithcode.com/paper/normalising-non-standardised-orthography-in |
| Repo | |
| Framework | |
Multi-Channel Convolutional Neural Network for Twitter Emotion and Sentiment Recognition
| Title | Multi-Channel Convolutional Neural Network for Twitter Emotion and Sentiment Recognition |
| Authors | Jumayel Islam, Robert E. Mercer, Lu Xiao |
| Abstract | The advent of micro-blogging sites has paved the way for researchers to collect and analyze huge volumes of data in recent years. Twitter, being one of the leading social networking sites worldwide, provides a great opportunity to its users for expressing their states of mind via short messages which are called tweets. The urgency of identifying emotions and sentiments conveyed through tweets has led to several research works. It provides a great way to understand human psychology and impose a challenge to researchers to analyze their content easily. In this paper, we propose a novel use of a multi-channel convolutional neural architecture which can effectively use different emotion and sentiment indicators such as hashtags, emoticons and emojis that are present in the tweets and improve the performance of emotion and sentiment identification. We also investigate the incorporation of different lexical features in the neural network model and its effect on the emotion and sentiment identification task. We analyze our model on some standard datasets and compare its effectiveness with existing techniques. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1137/ |
| https://www.aclweb.org/anthology/N19-1137 | |
| PWC | https://paperswithcode.com/paper/multi-channel-convolutional-neural-network |
| Repo | |
| Framework | |
Hyperspectral Imaging With Random Printed Mask
| Title | Hyperspectral Imaging With Random Printed Mask |
| Authors | Yuanyuan Zhao, Hui Guo, Zhan Ma, Xun Cao, Tao Yue, Xuemei Hu |
| Abstract | Hyperspectral images can provide rich clues for various computer vision tasks. However, the requirements of professional and expensive hardware for capturing hyperspectral images impede its wide applications. In this paper, based on a simple but not widely noticed phenomenon that the color printer can print color masks with a large number of independent spectral transmission responses, we propose a simple and low-budget scheme to capture the hyperspectral images with a random mask printed by the consumer-level color printer. Specifically, we notice that the printed dots with different colors are stacked together, forming multiplicative, instead of additive, spectral transmission responses. Therefore, new spectral transmission response uncorrelated with that of the original printer dyes are generated. With the random printed color mask, hyperspectral images could be captured in a snapshot way. A convolutional neural network (CNN) based method is developed to reconstruct the hyperspectral images from the captured image. The effectiveness and accuracy of the proposed system are verified on both synthetic and real captured images. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhao_Hyperspectral_Imaging_With_Random_Printed_Mask_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhao_Hyperspectral_Imaging_With_Random_Printed_Mask_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/hyperspectral-imaging-with-random-printed |
| Repo | |
| Framework | |
End-to-End Neural Context Reconstruction in Chinese Dialogue
| Title | End-to-End Neural Context Reconstruction in Chinese Dialogue |
| Authors | Wei Yang, Rui Qiao, Haocheng Qin, Amy Sun, Luchen Tan, Kun Xiong, Ming Li |
| Abstract | We tackle the problem of context reconstruction in Chinese dialogue, where the task is to replace pronouns, zero pronouns, and other referring expressions with their referent nouns so that sentences can be processed in isolation without context. Following a standard decomposition of the context reconstruction task into referring expression detection and coreference resolution, we propose a novel end-to-end architecture for separately and jointly accomplishing this task. Key features of this model include POS and position encoding using CNNs and a novel pronoun masking mechanism. One perennial problem in building such models is the paucity of training data, which we address by augmenting previously-proposed methods to generate a large amount of realistic training data. The combination of more data and better models yields accuracy higher than the state-of-the-art method in coreference resolution and end-to-end context reconstruction. |
| Tasks | Coreference Resolution |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4108/ |
| https://www.aclweb.org/anthology/W19-4108 | |
| PWC | https://paperswithcode.com/paper/end-to-end-neural-context-reconstruction-in |
| Repo | |
| Framework | |
Classification of Semantic Paraphasias: Optimization of a Word Embedding Model
| Title | Classification of Semantic Paraphasias: Optimization of a Word Embedding Model |
| Authors | Katy McKinney-Bock, Steven Bedrick |
| Abstract | In clinical assessment of people with aphasia, impairment in the ability to recall and produce words for objects (anomia) is assessed using a confrontation naming task, where a target stimulus is viewed and a corresponding label is spoken by the participant. Vector space word embedding models have had inital results in assessing semantic similarity of target-production pairs in order to automate scoring of this task; however, the resulting models are also highly dependent upon training parameters. To select an optimal family of models, we fit a beta regression model to the distribution of performance metrics on a set of 2,880 grid search models and evaluate the resultant first- and second-order effects to explore how parameterization affects model performance. Comparing to SimLex-999, we show that clinical data can be used in an evaluation task with comparable optimal parameter settings as standard NLP evaluation datasets. |
| Tasks | Semantic Similarity, Semantic Textual Similarity |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2007/ |
| https://www.aclweb.org/anthology/W19-2007 | |
| PWC | https://paperswithcode.com/paper/classification-of-semantic-paraphasias |
| Repo | |
| Framework | |
Modeling Uncertainty with Hedged Instance Embeddings
| Title | Modeling Uncertainty with Hedged Instance Embeddings |
| Authors | Seong Joon Oh, Kevin P. Murphy, Jiyan Pan, Joseph Roth, Florian Schroff, Andrew C. Gallagher |
| Abstract | Instance embeddings are an efficient and versatile image representation that facilitates applications like recognition, verification, retrieval, and clustering. Many metric learning methods represent the input as a single point in the embedding space. Often the distance between points is used as a proxy for match confidence. However, this can fail to represent uncertainty which can arise when the input is ambiguous, e.g., due to occlusion or blurriness. This work addresses this issue and explicitly models the uncertainty by “hedging” the location of each input in the embedding space. We introduce the hedged instance embedding (HIB) in which embeddings are modeled as random variables and the model is trained under the variational information bottleneck principle (Alemi et al., 2016; Achille & Soatto, 2018). Empirical results on our new N-digit MNIST dataset show that our method leads to the desired behavior of “hedging its bets” across the embedding space upon encountering ambiguous inputs. This results in improved performance for image matching and classification tasks, more structure in the learned embedding space, and an ability to compute a per-exemplar uncertainty measure which is correlated with downstream performance. |
| Tasks | Metric Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r1xQQhAqKX |
| https://openreview.net/pdf?id=r1xQQhAqKX | |
| PWC | https://paperswithcode.com/paper/modeling-uncertainty-with-hedged-instance-1 |
| Repo | |
| Framework | |
Aligning Discourse and Argumentation Structures using Subtrees and Redescription Mining
| Title | Aligning Discourse and Argumentation Structures using Subtrees and Redescription Mining |
| Authors | Laurine Huber, Yannick Toussaint, Charlotte Roze, Mathilde Dargnat, Chlo{'e} Braud |
| Abstract | In this paper, we investigate similarities between discourse and argumentation structures by aligning subtrees in a corpus containing both annotations. Contrary to previous works, we focus on comparing sub-structures and not only relations matches. Using data mining techniques, we show that discourse and argumentation most often align well, and the double annotation allows to derive a mapping between structures. Moreover, this approach enables the study of similarities between discourse structures and differences in their expressive power. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4504/ |
| https://www.aclweb.org/anthology/W19-4504 | |
| PWC | https://paperswithcode.com/paper/aligning-discourse-and-argumentation |
| Repo | |
| Framework | |
Advances in Argument Mining
| Title | Advances in Argument Mining |
| Authors | Katarzyna Budzynska, Chris Reed |
| Abstract | This course aims to introduce students to an exciting and dynamic area that has witnessed remarkable growth over the past 36 months. Argument mining builds on opinion mining, sentiment analysis and related to tasks to automatically extract not just what people think, but why they hold the opinions they do. From being largely beyond the state of the art barely five years ago, there are now many hundreds of papers on the topic, millions of dollars of commercial and research investment, and the 6th ACL workshop on the topic will be in Florence in 2019. The tutors have delivered tutorials on argument mining at ACL 2016, at IJCAI 2016 and at ESSLLI 2017; for ACL 2019, we have developed a tutorial that provides a synthesis of the major advances in the area over the past three years. |
| Tasks | Argument Mining, Opinion Mining, Sentiment Analysis |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-4008/ |
| https://www.aclweb.org/anthology/P19-4008 | |
| PWC | https://paperswithcode.com/paper/advances-in-argument-mining |
| Repo | |
| Framework | |
Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER)
| Title | Proceedings of the Second Workshop on Fact Extraction and VERification (FEVER) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6600/ |
| https://www.aclweb.org/anthology/D19-6600 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-second-workshop-on-fact |
| Repo | |
| Framework | |
Reevaluating Argument Component Extraction in Low Resource Settings
| Title | Reevaluating Argument Component Extraction in Low Resource Settings |
| Authors | Anirudh Joshi, Timothy Baldwin, Richard Sinnott, Cecile Paris |
| Abstract | Argument component extraction is a challenging and complex high-level semantic extraction task. As such, it is both expensive to annotate (meaning training data is limited and low-resource by nature), and hard for current-generation deep learning methods to model. In this paper, we reevaluate the performance of state-of-the-art approaches in both single- and multi-task learning settings using combinations of character-level, GloVe, ELMo, and BERT encodings using standard BiLSTM-CRF encoders. We use evaluation metrics that are more consistent with evaluation practice in named entity recognition to understand how well current baselines address this challenge and compare their performance to lower-level semantic tasks such as CoNLL named entity recognition. We find that performance utilizing various pre-trained representations and training methodologies often leaves a lot to be desired as it currently stands, and suggest future pathways for improvement. |
| Tasks | Multi-Task Learning, Named Entity Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6124/ |
| https://www.aclweb.org/anthology/D19-6124 | |
| PWC | https://paperswithcode.com/paper/reevaluating-argument-component-extraction-in |
| Repo | |
| Framework | |
Monolingual backtranslation in a medical speech translation system for diagnostic interviews - a NMT approach
| Title | Monolingual backtranslation in a medical speech translation system for diagnostic interviews - a NMT approach |
| Authors | Jonathan Mutal, Pierrette Bouillon, Johanna Gerlach, Paula Estrella, Herv{'e} Spechbach |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6734/ |
| https://www.aclweb.org/anthology/W19-6734 | |
| PWC | https://paperswithcode.com/paper/monolingual-backtranslation-in-a-medical |
| Repo | |
| Framework | |
Feed-forward Propagation in Probabilistic Neural Networks with Categorical and Max Layers
| Title | Feed-forward Propagation in Probabilistic Neural Networks with Categorical and Max Layers |
| Authors | Alexander Shekhovtsov, Boris Flach |
| Abstract | Probabilistic Neural Networks deal with various sources of stochasticity: input noise, dropout, stochastic neurons, parameter uncertainties modeled as random variables, etc. In this paper we revisit a feed-forward propagation approach that allows one to estimate for each neuron its mean and variance w.r.t. all mentioned sources of stochasticity. In contrast, standard NNs propagate only point estimates, discarding the uncertainty. Methods propagating also the variance have been proposed by several authors in different context. The view presented here attempts to clarify the assumptions and derivation behind such methods, relate them to classical NNs and broaden their scope of applicability. The main technical contributions are new approximations for the distributions of argmax and max-related transforms, which allow for fully analytic uncertainty propagation in networks with softmax and max-pooling layers as well as leaky ReLU activations. We evaluate the accuracy of the approximation and suggest a simple calibration. Applying the method to networks with dropout allows for faster training and gives improved test likelihoods without the need of sampling. |
| Tasks | Calibration |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SkMuPjRcKQ |
| https://openreview.net/pdf?id=SkMuPjRcKQ | |
| PWC | https://paperswithcode.com/paper/feed-forward-propagation-in-probabilistic |
| Repo | |
| Framework | |
A Framework for Annotating `Related Works’ to Support Feedback to Novice Writers
| Title | A Framework for Annotating `Related Works’ to Support Feedback to Novice Writers | |
| Authors | Arlene Casey, Bonnie Webber, Dorota Glowacka |
| Abstract | Understanding what is expected of academic writing can be difficult for novice writers to assimilate, and recent years have seen several automated tools become available to support academic writing. Our work presents a framework for annotating features of the Related Work section of academic writing, that supports writer feedback. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4011/ |
| https://www.aclweb.org/anthology/W19-4011 | |
| PWC | https://paperswithcode.com/paper/a-framework-for-annotating-related-works-to |
| Repo | |
| Framework | |
Gazetteer-Enhanced Attentive Neural Networks for Named Entity Recognition
| Title | Gazetteer-Enhanced Attentive Neural Networks for Named Entity Recognition |
| Authors | Hongyu Lin, Yaojie Lu, Xianpei Han, Le Sun, Bin Dong, Shanshan Jiang |
| Abstract | Current region-based NER models only rely on fully-annotated training data to learn effective region encoder, which often face the training data bottleneck. To alleviate this problem, this paper proposes Gazetteer-Enhanced Attentive Neural Networks, which can enhance region-based NER by learning name knowledge of entity mentions from easily-obtainable gazetteers, rather than only from fully-annotated data. Specially, we first propose an attentive neural network (ANN), which explicitly models the mention-context association and therefore is convenient for integrating externally-learned knowledge. Then we design an auxiliary gazetteer network, which can effectively encode name regularity of mentions only using gazetteers. Finally, the learned gazetteer network is incorporated into ANN for better NER. Experiments show that our ANN can achieve the state-of-the-art performance on ACE2005 named entity recognition benchmark. Besides, incorporating gazetteer network can further improve the performance and significantly reduce the requirement of training data. |
| Tasks | Named Entity Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1646/ |
| https://www.aclweb.org/anthology/D19-1646 | |
| PWC | https://paperswithcode.com/paper/gazetteer-enhanced-attentive-neural-networks |
| Repo | |
| Framework | |
MC^2: Multi-perspective Convolutional Cube for Conversational Machine Reading Comprehension
| Title | MC^2: Multi-perspective Convolutional Cube for Conversational Machine Reading Comprehension |
| Authors | Xuanyu Zhang |
| Abstract | Conversational machine reading comprehension (CMRC) extends traditional single-turn machine reading comprehension (MRC) by multi-turn interactions, which requires machines to consider the history of conversation. Most of models simply combine previous questions for conversation understanding and only employ recurrent neural networks (RNN) for reasoning. To comprehend context profoundly and efficiently from different perspectives, we propose a novel neural network model, Multi-perspective Convolutional Cube (MC{^{}}2). We regard each conversation as a cube. 1D and 2D convolutions are integrated with RNN in our model. To avoid models previewing the next turn of conversation, we also extend causal convolution partially to 2D. Experiments on the Conversational Question Answering (CoQA) dataset show that our model achieves state-of-the-art results. |
| Tasks | Machine Reading Comprehension, Question Answering, Reading Comprehension |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1622/ |
| https://www.aclweb.org/anthology/P19-1622 | |
| PWC | https://paperswithcode.com/paper/mc2-multi-perspective-convolutional-cube-for |
| Repo | |
| Framework | |
