Paper Group NANR 142
Mining the UK Web Archive for Semantic Change Detection. Developing without developers: choosing labor-saving tools for language documentation apps. Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting. Proceedings of the Combined Workshop on Spatial Language Understanding (SpLU) and Grounded Communication for Robotics …
Mining the UK Web Archive for Semantic Change Detection
| Title | Mining the UK Web Archive for Semantic Change Detection |
| Authors | Adam Tsakalidis, Marya Bazzi, Mihai Cucuringu, Pierpaolo Basile, Barbara McGillivray |
| Abstract | Semantic change detection (i.e., identifying words whose meaning has changed over time) started emerging as a growing area of research over the past decade, with important downstream applications in natural language processing, historical linguistics and computational social science. However, several obstacles make progress in the domain slow and difficult. These pertain primarily to the lack of well-established gold standard datasets, resources to study the problem at a fine-grained temporal resolution, and quantitative evaluation approaches. In this work, we aim to mitigate these issues by (a) releasing a new labelled dataset of more than 47K word vectors trained on the UK Web Archive over a short time-frame (2000-2013); (b) proposing a variant of Procrustes alignment to detect words that have undergone semantic shift; and (c) introducing a rank-based approach for evaluation purposes. Through extensive numerical experiments and validation, we illustrate the effectiveness of our approach against competitive baselines. Finally, we also make our resources publicly available to further enable research in the domain. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1139/ |
| https://www.aclweb.org/anthology/R19-1139 | |
| PWC | https://paperswithcode.com/paper/mining-the-uk-web-archive-for-semantic-change |
| Repo | |
| Framework | |
Developing without developers: choosing labor-saving tools for language documentation apps
| Title | Developing without developers: choosing labor-saving tools for language documentation apps |
| Authors | Luke Gessler |
| Abstract | |
| Tasks | |
| Published | 2019-02-01 |
| URL | https://www.aclweb.org/anthology/W19-6002/ |
| https://www.aclweb.org/anthology/W19-6002 | |
| PWC | https://paperswithcode.com/paper/developing-without-developers-choosing-labor |
| Repo | |
| Framework | |
Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting
| Title | Improved Lexically Constrained Decoding for Translation and Monolingual Rewriting |
| Authors | J. Edward Hu, Huda Khayrallah, Ryan Culkin, Patrick Xia, Tongfei Chen, Matt Post, Benjamin Van Durme |
| Abstract | Lexically-constrained sequence decoding allows for explicit positive or negative phrase-based constraints to be placed on target output strings in generation tasks such as machine translation or monolingual text rewriting. We describe vectorized dynamic beam allocation, which extends work in lexically-constrained decoding to work with batching, leading to a five-fold improvement in throughput when working with positive constraints. Faster decoding enables faster exploration of constraint strategies: we illustrate this via data augmentation experiments with a monolingual rewriter applied to the tasks of natural language inference, question answering and machine translation, showing improvements in all three. |
| Tasks | Data Augmentation, Machine Translation, Natural Language Inference, Question Answering |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1090/ |
| https://www.aclweb.org/anthology/N19-1090 | |
| PWC | https://paperswithcode.com/paper/improved-lexically-constrained-decoding-for |
| Repo | |
| Framework | |
Proceedings of the Combined Workshop on Spatial Language Understanding (SpLU) and Grounded Communication for Robotics (RoboNLP)
| Title | Proceedings of the Combined Workshop on Spatial Language Understanding (SpLU) and Grounded Communication for Robotics (RoboNLP) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1600/ |
| https://www.aclweb.org/anthology/W19-1600 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-combined-workshop-on |
| Repo | |
| Framework | |
Deep learning contextual models for prediction of sport event outcome from sportsman’s interviews
| Title | Deep learning contextual models for prediction of sport event outcome from sportsman’s interviews |
| Authors | Boris Velichkov, Ivan Koychev, Svetla Boytcheva |
| Abstract | This paper presents an approach for prediction of results for sport events. Usually the sport forecasting approaches are based on structured data. We test the hypothesis that the sports results can be predicted by using natural language processing and machine learning techniques applied over interviews with the players shortly before the sport events. The proposed method uses deep learning contextual models, applied over unstructured textual documents. Several experiments were performed for interviews with players in individual sports like boxing, martial arts, and tennis. The results from the conducted experiment confirmed our initial assumption that an interview from a sportsman before a match contains information that can be used for prediction the outcome from it. Furthermore, the results provide strong evidence in support of our research hypothesis, that is, we can predict the outcome from a sport match analyzing an interview, given before it. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1142/ |
| https://www.aclweb.org/anthology/R19-1142 | |
| PWC | https://paperswithcode.com/paper/deep-learning-contextual-models-for |
| Repo | |
| Framework | |
A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis
| Title | A Challenge Dataset and Effective Models for Aspect-Based Sentiment Analysis |
| Authors | Qingnan Jiang, Lei Chen, Ruifeng Xu, Xiang Ao, Min Yang |
| Abstract | Aspect-based sentiment analysis (ABSA) has attracted increasing attention recently due to its broad applications. In existing ABSA datasets, most sentences contain only one aspect or multiple aspects with the same sentiment polarity, which makes ABSA task degenerate to sentence-level sentiment analysis. In this paper, we present a new large-scale Multi-Aspect Multi-Sentiment (MAMS) dataset, in which each sentence contains at least two different aspects with different sentiment polarities. The release of this dataset would push forward the research in this field. In addition, we propose simple yet effective CapsNet and CapsNet-BERT models which combine the strengths of recent NLP advances. Experiments on our new dataset show that the proposed model significantly outperforms the state-of-the-art baseline methods |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1654/ |
| https://www.aclweb.org/anthology/D19-1654 | |
| PWC | https://paperswithcode.com/paper/a-challenge-dataset-and-effective-models-for |
| Repo | |
| Framework | |
Terminology-Aware Segmentation and Domain Feature for the WMT19 Biomedical Translation Task
| Title | Terminology-Aware Segmentation and Domain Feature for the WMT19 Biomedical Translation Task |
| Authors | Casimiro Pio Carrino, Bardia Rafieian, Marta R. Costa-juss{`a}, Jos{'e} A. R. Fonollosa |
| Abstract | In this work, we give a description of the TALP-UPC systems submitted for the WMT19 Biomedical Translation Task. Our proposed strategy is NMT model-independent and relies only on one ingredient, a biomedical terminology list. We first extracted such a terminology list by labelling biomedical words in our training dataset using the BabelNet API. Then, we designed a data preparation strategy to insert the terms information at a token level. Finally, we trained the Transformer model with this terms-informed data. Our best-submitted system ranked 2nd and 3rd for Spanish-English and English-Spanish translation directions, respectively. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5418/ |
| https://www.aclweb.org/anthology/W19-5418 | |
| PWC | https://paperswithcode.com/paper/terminology-aware-segmentation-and-domain |
| Repo | |
| Framework | |
MTPE in Patents: A Successful Business Story
| Title | MTPE in Patents: A Successful Business Story |
| Authors | Valeria Premoli, Elena Murgolo, Diego Cresceri |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6706/ |
| https://www.aclweb.org/anthology/W19-6706 | |
| PWC | https://paperswithcode.com/paper/mtpe-in-patents-a-successful-business-story |
| Repo | |
| Framework | |
Out-of-Sample Extrapolation with Neuron Editing
| Title | Out-of-Sample Extrapolation with Neuron Editing |
| Authors | Matthew Amodio, David van Dijk, Ruth Montgomery, Guy Wolf, Smita Krishnaswamy |
| Abstract | While neural networks can be trained to map from one specific dataset to another, they usually do not learn a generalized transformation that can extrapolate accurately outside the space of training. For instance, a generative adversarial network (GAN) exclusively trained to transform images of cars from light to dark might not have the same effect on images of horses. This is because neural networks are good at generation within the manifold of the data that they are trained on. However, generating new samples outside of the manifold or extrapolating “out-of-sample” is a much harder problem that has been less well studied. To address this, we introduce a technique called neuron editing that learns how neurons encode an edit for a particular transformation in a latent space. We use an autoencoder to decompose the variation within the dataset into activations of different neurons and generate transformed data by defining an editing transformation on those neurons. By performing the transformation in a latent trained space, we encode fairly complex and non-linear transformations to the data with much simpler distribution shifts to the neuron’s activations. We showcase our technique on image domain/style transfer and two biological applications: removal of batch artifacts representing unwanted noise and modeling the effect of drug treatments to predict synergy between drugs. |
| Tasks | Style Transfer |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rygZJ2RcF7 |
| https://openreview.net/pdf?id=rygZJ2RcF7 | |
| PWC | https://paperswithcode.com/paper/out-of-sample-extrapolation-with-neuron |
| Repo | |
| Framework | |
First order expansion of convex regularized estimators
| Title | First order expansion of convex regularized estimators |
| Authors | Pierre Bellec, Arun Kuchibhotla |
| Abstract | We consider first order expansions of convex penalized estimators in high-dimensional regression problems with random designs. Our setting includes linear regression and logistic regression as special cases. For a given penalty function $h$ and the corresponding penalized estimator $\hbeta$, we construct a quantity $\eta$, the first order expansion of $\hbeta$, such that the distance between $\hbeta$ and $\eta$ is an order of magnitude smaller than the estimation error $\hat{\beta} - \beta^*$. In this sense, the first order expansion $\eta$ can be thought of as a generalization of influence functions from the mathematical statistics literature to regularized estimators in high-dimensions. Such first order expansion implies that the risk of $\hat{\beta}$ is asymptotically the same as the risk of $\eta$ which leads to a precise characterization of the MSE of $\hbeta$; this characterization takes a particularly simple form for isotropic design. Such first order expansion also leads to inference results based on $\hat{\beta}$. We provide sufficient conditions for the existence of such first order expansion for three regularizers: the Lasso in its constrained form, the lasso in its penalized form, and the Group-Lasso. The results apply to general loss functions under some conditions and those conditions are satisfied for the squared loss in linear regression and for the logistic loss in the logistic model. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8606-first-order-expansion-of-convex-regularized-estimators |
| http://papers.nips.cc/paper/8606-first-order-expansion-of-convex-regularized-estimators.pdf | |
| PWC | https://paperswithcode.com/paper/first-order-expansion-of-convex-regularized-1 |
| Repo | |
| Framework | |
Learning Interpretable Negation Rules via Weak Supervision at Document Level: A Reinforcement Learning Approach
| Title | Learning Interpretable Negation Rules via Weak Supervision at Document Level: A Reinforcement Learning Approach |
| Authors | Nicolas Pr{"o}llochs, Stefan Feuerriegel, Dirk Neumann |
| Abstract | Negation scope detection is widely performed as a supervised learning task which relies upon negation labels at word level. This suffers from two key drawbacks: (1) such granular annotations are costly and (2) highly subjective, since, due to the absence of explicit linguistic resolution rules, human annotators often disagree in the perceived negation scopes. To the best of our knowledge, our work presents the first approach that eliminates the need for world-level negation labels, replacing it instead with document-level sentiment annotations. For this, we present a novel strategy for learning fully interpretable negation rules via weak supervision: we apply reinforcement learning to find a policy that reconstructs negation rules from sentiment predictions at document level. Our experiments demonstrate that our approach for weak supervision can effectively learn negation rules. Furthermore, an out-of-sample evaluation via sentiment analysis reveals consistent improvements (of up to 4.66{%}) over both a sentiment analysis with (i) no negation handling and (ii) the use of word-level annotations from humans. Moreover, the inferred negation rules are fully interpretable. |
| Tasks | Sentiment Analysis |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1038/ |
| https://www.aclweb.org/anthology/N19-1038 | |
| PWC | https://paperswithcode.com/paper/learning-interpretable-negation-rules-via |
| Repo | |
| Framework | |
Total Style Transfer with a Single Feed-Forward Network
| Title | Total Style Transfer with a Single Feed-Forward Network |
| Authors | Minseong Kim, Hyun-Chul Choi |
| Abstract | Recent image style transferring methods achieved arbitrary stylization with input content and style images. To transfer the style of an arbitrary image to a content image, these methods used a feed-forward network with a lowest-scaled feature transformer or a cascade of the networks with a feature transformer of a corresponding scale. However, their approaches did not consider either multi-scaled style in their single-scale feature transformer or dependency between the transformed feature statistics across the cascade networks. This shortcoming resulted in generating partially and inexactly transferred style in the generated images. To overcome this limitation of partial style transfer, we propose a total style transferring method which transfers multi-scaled feature statistics through a single feed-forward process. First, our method transforms multi-scaled feature maps of a content image into those of a target style image by considering both inter-channel correlations in each single scaled feature map and inter-scale correlations between multi-scaled feature maps. Second, each transformed feature map is inserted into the decoder layer of the corresponding scale using skip-connection. Finally, the skip-connected multi-scaled feature maps are decoded into a stylized image through our trained decoder network. |
| Tasks | Style Transfer |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BJ4AFsRcFQ |
| https://openreview.net/pdf?id=BJ4AFsRcFQ | |
| PWC | https://paperswithcode.com/paper/total-style-transfer-with-a-single-feed |
| Repo | |
| Framework | |
Content Modeling for Automated Oral Proficiency Scoring System
| Title | Content Modeling for Automated Oral Proficiency Scoring System |
| Authors | Su-Youn Yoon, Chong Min Lee |
| Abstract | We developed an automated oral proficiency scoring system for non-native English speakers{'} spontaneous speech. Automated systems that score holistic proficiency are expected to assess a wide range of performance categories, and the content is one of the core performance categories. In order to assess the quality of the content, we trained a Siamese convolutional neural network (CNN) to model the semantic relationship between key points generated by experts and a test response. The correlation between human scores and Siamese CNN scores was comparable to human-human agreement (r=0.63), and it was higher than the baseline content features. The inclusion of Siamese CNN-based feature to the existing state-of-the-art automated scoring model achieved a small but statistically significant improvement. However, the new model suffered from score inflation for long atypical responses with serious content issues. We investigated the reasons of this score inflation by analyzing the associations with linguistic features and identifying areas strongly associated with the score errors. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4441/ |
| https://www.aclweb.org/anthology/W19-4441 | |
| PWC | https://paperswithcode.com/paper/content-modeling-for-automated-oral |
| Repo | |
| Framework | |
Simplified Neural Unsupervised Domain Adaptation
| Title | Simplified Neural Unsupervised Domain Adaptation |
| Authors | Timothy Miller |
| Abstract | Unsupervised domain adaptation (UDA) is the task of training a statistical model on labeled data from a source domain to achieve better performance on data from a target domain, with access to only unlabeled data in the target domain. Existing state-of-the-art UDA approaches use neural networks to learn representations that are trained to predict the values of subset of important features called {}pivot features{''} on combined data from the source and target domains. In this work, we show that it is possible to improve on existing neural domain adaptation algorithms by 1) jointly training the representation learner with the task learner; and 2) removing the need for heuristically-selected {}pivot features.{''} Our results show competitive performance with a simpler model. |
| Tasks | Domain Adaptation, Unsupervised Domain Adaptation |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1039/ |
| https://www.aclweb.org/anthology/N19-1039 | |
| PWC | https://paperswithcode.com/paper/simplified-neural-unsupervised-domain-1 |
| Repo | |
| Framework | |
Multiple-Attribute Text Rewriting
| Title | Multiple-Attribute Text Rewriting |
| Authors | Guillaume Lample, Sandeep Subramanian, Eric Smith, Ludovic Denoyer, Marc’Aurelio Ranzato, Y-Lan Boureau |
| Abstract | The dominant approach to unsupervised “style transfer” in text is based on the idea of learning a latent representation, which is independent of the attributes specifying its “style”. In this paper, we show that this condition is not necessary and is not always met in practice, even with domain adversarial training, that explicitly aims at learning such disentangled representations. We thus propose a new model that controls several factors of variation in textual data where this condition on disentanglement is replaced with a simpler mechanism based on back-translation. Our method allows control over multiple attributes, like gender, sentiment, product type, etc., and a more fine-grained control on the trade-off between content preservation and change of style with a pooling operator in the latent space. Our experiments demonstrate that the fully entangled model produces better generations, even when tested on new and more challenging benchmarks comprising reviews with multiple sentences and multiple attributes. |
| Tasks | Style Transfer |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1g2NhC5KQ |
| https://openreview.net/pdf?id=H1g2NhC5KQ | |
| PWC | https://paperswithcode.com/paper/multiple-attribute-text-rewriting |
| Repo | |
| Framework | |
