Paper Group NANR 215
Meaningless yet meaningful: Morphology grounded subword-level NMT. Learning multiview embeddings for assessing dementia. Integrating Predictions from Neural-Network Relation Classifiers into Coreference and Bridging Resolution. The Word Analogy Testing Caveat. Towards Bridging Resolution in German: Data Analysis and Rule-based Experiments. Sisyphus …
Meaningless yet meaningful: Morphology grounded subword-level NMT
| Title | Meaningless yet meaningful: Morphology grounded subword-level NMT |
| Authors | Tamali Banerjee, Pushpak Bhattacharyya |
| Abstract | We explore the use of two independent subsystems Byte Pair Encoding (BPE) and Morfessor as basic units for subword-level neural machine translation (NMT). We show that, for linguistically distant language-pairs Morfessor-based segmentation algorithm produces significantly better quality translation than BPE. However, for close language-pairs BPE-based subword-NMT may translate better than Morfessor-based subword-NMT. We propose a combined approach of these two segmentation algorithms Morfessor-BPE (M-BPE) which outperforms these two baseline systems in terms of BLEU score. Our results are supported by experiments on three language-pairs: English-Hindi, Bengali-Hindi and English-Bengali. |
| Tasks | Machine Translation, Transliteration |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1207/ |
| https://www.aclweb.org/anthology/W18-1207 | |
| PWC | https://paperswithcode.com/paper/meaningless-yet-meaningful-morphology |
| Repo | |
| Framework | |
Learning multiview embeddings for assessing dementia
| Title | Learning multiview embeddings for assessing dementia |
| Authors | Chlo{'e} Pou-Prom, Frank Rudzicz |
| Abstract | As the incidence of Alzheimer{'}s Disease (AD) increases, early detection becomes crucial. Unfortunately, datasets for AD assessment are often sparse and incomplete. In this work, we leverage the multiview nature of a small AD dataset, DementiaBank, to learn an embedding that captures different modes of cognitive impairment. We apply generalized canonical correlation analysis (GCCA) to our dataset and demonstrate the added benefit of using multiview embeddings in two downstream tasks: identifying AD and predicting clinical scores. By including multiview embeddings, we obtain an F1 score of 0.82 in the classification task and a mean absolute error of 3.42 in the regression task. Furthermore, we show that multiview embeddings can be obtained from other datasets as well. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1304/ |
| https://www.aclweb.org/anthology/D18-1304 | |
| PWC | https://paperswithcode.com/paper/learning-multiview-embeddings-for-assessing |
| Repo | |
| Framework | |
Integrating Predictions from Neural-Network Relation Classifiers into Coreference and Bridging Resolution
| Title | Integrating Predictions from Neural-Network Relation Classifiers into Coreference and Bridging Resolution |
| Authors | Ina Roesiger, Maximilian K{"o}per, Kim Anh Nguyen, Sabine Schulte im Walde |
| Abstract | Cases of coreference and bridging resolution often require knowledge about semantic relations between anaphors and antecedents. We suggest state-of-the-art neural-network classifiers trained on relation benchmarks to predict and integrate likelihoods for relations. Two experiments with representations differing in noise and complexity improve our bridging but not our coreference resolver. |
| Tasks | Coreference Resolution |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0705/ |
| https://www.aclweb.org/anthology/W18-0705 | |
| PWC | https://paperswithcode.com/paper/integrating-predictions-from-neural-network |
| Repo | |
| Framework | |
The Word Analogy Testing Caveat
| Title | The Word Analogy Testing Caveat |
| Authors | Natalie Schluter |
| Abstract | There are some important problems in the evaluation of word embeddings using standard word analogy tests. In particular, in virtue of the assumptions made by systems generating the embeddings, these remain tests over randomness. We show that even supposing there were such word analogy regularities that should be detected in the word embeddings obtained via unsupervised means, standard word analogy test implementation practices provide distorted or contrived results. We raise concerns regarding the use of Principal Component Analysis to 2 or 3 dimensions as a provision of visual evidence for the existence of word analogy relations in embeddings. Finally, we propose some solutions to these problems. |
| Tasks | Semantic Textual Similarity, Transfer Learning, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2039/ |
| https://www.aclweb.org/anthology/N18-2039 | |
| PWC | https://paperswithcode.com/paper/the-word-analogy-testing-caveat |
| Repo | |
| Framework | |
Towards Bridging Resolution in German: Data Analysis and Rule-based Experiments
| Title | Towards Bridging Resolution in German: Data Analysis and Rule-based Experiments |
| Authors | Janis Pagel, Ina Roesiger |
| Abstract | Bridging resolution is the task of recognising bridging anaphors and linking them to their antecedents. While there is some work on bridging resolution for English, there is only little work for German. We present two datasets which contain bridging annotations, namely DIRNDL and GRAIN, and compare the performance of a rule-based system with a simple baseline approach on these two corpora. The performance for full bridging resolution ranges between an F1 score of 13.6{%} for DIRNDL and 11.8{%} for GRAIN. An analysis using oracle lists suggests that the system could, to a certain extent, benefit from ranking and re-ranking antecedent candidates. Furthermore, we investigate the importance of single features and show that the features used in our work seem promising for future bridging resolution approaches. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0706/ |
| https://www.aclweb.org/anthology/W18-0706 | |
| PWC | https://paperswithcode.com/paper/towards-bridging-resolution-in-german-data |
| Repo | |
| Framework | |
Sisyphus, a Workflow Manager Designed for Machine Translation and Automatic Speech Recognition
| Title | Sisyphus, a Workflow Manager Designed for Machine Translation and Automatic Speech Recognition |
| Authors | Jan-Thorsten Peter, Eugen Beck, Hermann Ney |
| Abstract | Training and testing many possible parameters or model architectures of state-of-the-art machine translation or automatic speech recognition system is a cumbersome task. They usually require a long pipeline of commands reaching from pre-processing the training data to post-processing and evaluating the output. |
| Tasks | Machine Translation, Speech Recognition |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/D18-2015/ |
| https://www.aclweb.org/anthology/D18-2015 | |
| PWC | https://paperswithcode.com/paper/sisyphus-a-workflow-manager-designed-for |
| Repo | |
| Framework | |
Deep Domain Generalization via Conditional Invariant Adversarial Networks
| Title | Deep Domain Generalization via Conditional Invariant Adversarial Networks |
| Authors | Ya Li, Xinmei Tian, Mingming Gong, Yajing Liu, Tongliang Liu, Kun Zhang, Dacheng Tao |
| Abstract | Domain generalization aims to learn a classification model from multiple source domains and generalize it to unseen target domains. A critical problem in domain generalization involves learning domain-invariant representations. Let $X$ and $Y$ denote the features and the labels, respectively. Under the assumption that the conditional distribution $P(YX)$ remains unchanged across domains, earlier approaches to domain generalization learned the invariant representation $T(X)$ by minimizing the discrepancy of the marginal distribution $P(T(X))$. However, such an assumption of stable $P(YX)$ does not necessarily hold in practice. In addition, the representation learning function $T(X)$ is usually constrained to a simple linear transformation or shallow networks. To address the above two drawbacks, we propose an end-to-end conditional invariant deep domain generalization approach by leveraging deep neural networks for domain-invariant representation learning. The domain-invariance property is guaranteed through a conditional invariant adversarial network that can learn domain-invariant representations w.r.t. the joint distribution $P(T(X),Y)$ if the target domain data are not severely class unbalanced. We perform various experiments to demonstrate the effectiveness of the proposed method. |
| Tasks | Domain Generalization, Representation Learning |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Ya_Li_Deep_Domain_Generalization_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Ya_Li_Deep_Domain_Generalization_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-domain-generalization-via-conditional |
| Repo | |
| Framework | |
Indra: A Word Embedding and Semantic Relatedness Server
| Title | Indra: A Word Embedding and Semantic Relatedness Server |
| Authors | Juliano Efson Sales, Leonardo Souza, Siamak Barzegar, Brian Davis, Andr{'e} Freitas, H, Siegfried schuh |
| Abstract | |
| Tasks | Semantic Textual Similarity |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1211/ |
| https://www.aclweb.org/anthology/L18-1211 | |
| PWC | https://paperswithcode.com/paper/indra-a-word-embedding-and-semantic |
| Repo | |
| Framework | |
A Corpus of Drug Usage Guidelines Annotated with Type of Advice
| Title | A Corpus of Drug Usage Guidelines Annotated with Type of Advice |
| Authors | Sarah Masud Preum, Md. Rizwan Parvez, Kai-Wei Chang, John Stankovic |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1190/ |
| https://www.aclweb.org/anthology/L18-1190 | |
| PWC | https://paperswithcode.com/paper/a-corpus-of-drug-usage-guidelines-annotated |
| Repo | |
| Framework | |
Mesoscopic Facial Geometry Inference Using Deep Neural Networks
| Title | Mesoscopic Facial Geometry Inference Using Deep Neural Networks |
| Authors | Loc Huynh, Weikai Chen, Shunsuke Saito, Jun Xing, Koki Nagano, Andrew Jones, Paul Debevec, Hao Li |
| Abstract | We present a learning-based approach for synthesizing facial geometry at medium and fine scales from diffusely-lit facial texture maps. When applied to an image sequence, the synthesized detail is temporally coherent. Unlike current state-of-the-art methods, which assume “dark is deep”, our model is trained with measured facial detail collected using polarized gradient illumination in a Light Stage. This enables us to produce plausible facial detail across the entire face, including where previous approaches may incorrectly interpret dark features as concavities such as at moles, hair stubble, and occluded pores. Instead of directly inferring 3D geometry, we propose to encode fine details in high-resolution displacement maps which are learned through a hybrid network adopting the state-of-the-art image-to-image translation network and super resolution network. To effectively capture geometric detail at both mid- and high frequencies, we factorize the learning into two separate sub-networks, enabling the full range of facial detail to be modeled. Results from our learning-based approach compare favorably with a high-quality active facial scanning technique, and require only a single passive lighting condition without a complex scanning setup. |
| Tasks | Image-to-Image Translation, Super-Resolution |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Huynh_Mesoscopic_Facial_Geometry_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Huynh_Mesoscopic_Facial_Geometry_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/mesoscopic-facial-geometry-inference-using |
| Repo | |
| Framework | |
Variable Ring Light Imaging: Capturing Transient Subsurface Scattering with An Ordinary Camera
| Title | Variable Ring Light Imaging: Capturing Transient Subsurface Scattering with An Ordinary Camera |
| Authors | Ko Nishino, Art Subpa-asa, Yuta Asano, Mihoko Shimano, Imari Sato |
| Abstract | Subsurface scattering plays a significant role in determining the appearance of real-world surfaces. A light ray penetrating into the subsurface is repeatedly scattered and absorbed by particles along its path before reemerging from the outer interface, which determines its spectral radiance. We introduce a novel imaging method that enables the decomposition of the appearance of a fronto-parallel real-world surface into images of light with bounded path lengths, i.e., transient subsurface light transport. Our key idea is to observe each surface point under a variable ring light: a circular illumination pattern of increasingly larger radius centered on it. We show that the path length of light captured in each of these observations is naturally lower-bounded by the ring light radius. By taking the difference of ring light images of incrementally larger radii, we compute transient images that encode light with bounded path lengths. Experimental results on synthetic and complex real-world surfaces demonstrate that the recovered transient images reveal the subsurface structure of general translucent inhomogeneous surfaces. We further show that their differences reveal the surface colors at different surface depths. The proposed method is the first to enable the unveiling of dense and continuous subsurface structures from steady-state external appearance using ordinary camera and illumination. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Ko_Nishino_Variable_Ring_Light_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Ko_Nishino_Variable_Ring_Light_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/variable-ring-light-imaging-capturing |
| Repo | |
| Framework | |
Parsivar: A Language Processing Toolkit for Persian
| Title | Parsivar: A Language Processing Toolkit for Persian |
| Authors | Salar Mohtaj, Behnam Roshanfekr, Atefeh Zafarian, Habibollah Asghari |
| Abstract | |
| Tasks | Morphological Analysis, Tokenization |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1179/ |
| https://www.aclweb.org/anthology/L18-1179 | |
| PWC | https://paperswithcode.com/paper/parsivar-a-language-processing-toolkit-for |
| Repo | |
| Framework | |
QUD-Based Annotation of Discourse Structure and Information Structure: Tool and Evaluation
| Title | QUD-Based Annotation of Discourse Structure and Information Structure: Tool and Evaluation |
| Authors | Kordula De Kuthy, Nils Reiter, Arndt Riester |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1304/ |
| https://www.aclweb.org/anthology/L18-1304 | |
| PWC | https://paperswithcode.com/paper/qud-based-annotation-of-discourse-structure |
| Repo | |
| Framework | |
Automatically Extracting Qualia Relations for the Rich Event Ontology
| Title | Automatically Extracting Qualia Relations for the Rich Event Ontology |
| Authors | Ghazaleh Kazeminejad, Claire Bonial, Susan Windisch Brown, Martha Palmer |
| Abstract | Commonsense, real-world knowledge about the events that entities or {``}things in the world{''} are typically involved in, as well as part-whole relationships, is valuable for allowing computational systems to draw everyday inferences about the world. Here, we focus on automatically extracting information about (1) the events that typically bring about certain entities (origins), (2) the events that are the typical functions of entities, and (3) part-whole relationships in entities. These correspond to the agentive, telic and constitutive qualia central to the Generative Lexicon. We describe our motivations and methods for extracting these qualia relations from the Suggested Upper Merged Ontology (SUMO) and show that human annotators overwhelmingly find the information extracted to be reasonable. Because ontologies provide a way of structuring this information and making it accessible to agents and computational systems generally, efforts are underway to incorporate the extracted information to an ontology hub of Natural Language Processing semantic role labeling resources, the Rich Event Ontology. | |
| Tasks | Semantic Role Labeling |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1224/ |
| https://www.aclweb.org/anthology/C18-1224 | |
| PWC | https://paperswithcode.com/paper/automatically-extracting-qualia-relations-for |
| Repo | |
| Framework | |
A dataset for identifying actionable feedback in collaborative software development
| Title | A dataset for identifying actionable feedback in collaborative software development |
| Authors | Benjamin S. Meyers, Nuthan Munaiah, Emily Prud{'}hommeaux, Andrew Meneely, Josephine Wolff, Cecilia Ovesdotter Alm, Pradeep Murukannaiah |
| Abstract | Software developers and testers have long struggled with how to elicit proactive responses from their coworkers when reviewing code for security vulnerabilities and errors. For a code review to be successful, it must not only identify potential problems but also elicit an active response from the colleague responsible for modifying the code. To understand the factors that contribute to this outcome, we analyze a novel dataset of more than one million code reviews for the Google Chromium project, from which we extract linguistic features of feedback that elicited responsive actions from coworkers. Using a manually-labeled subset of reviewer comments, we trained a highly accurate classifier to identify acted-upon comments (AUC = 0.85). Our results demonstrate the utility of our dataset, the feasibility of using NLP for this new task, and the potential of NLP to improve our understanding of how communications between colleagues can be authored to elicit positive, proactive responses. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2021/ |
| https://www.aclweb.org/anthology/P18-2021 | |
| PWC | https://paperswithcode.com/paper/a-dataset-for-identifying-actionable-feedback |
| Repo | |
| Framework | |
