Paper Group NANR 15
SACR: A Drag-and-Drop Based Tool for Coreference Annotation. Learning to Map Natural Language Statements into Knowledge Base Representations for Knowledge Base Construction. Translation Crowdsourcing: Creating a Multilingual Corpus of Online Educational Content. Preserving Workflow Reproducibility: The RePlay-DH Client as a Tool for Process Documen …
SACR: A Drag-and-Drop Based Tool for Coreference Annotation
| Title | SACR: A Drag-and-Drop Based Tool for Coreference Annotation |
| Authors | Bruno Oberle |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1059/ |
| https://www.aclweb.org/anthology/L18-1059 | |
| PWC | https://paperswithcode.com/paper/sacr-a-drag-and-drop-based-tool-for |
| Repo | |
| Framework | |
Learning to Map Natural Language Statements into Knowledge Base Representations for Knowledge Base Construction
| Title | Learning to Map Natural Language Statements into Knowledge Base Representations for Knowledge Base Construction |
| Authors | Chin-Ho Lin, Hen-Hsen Huang, Hsin-Hsi Chen |
| Abstract | |
| Tasks | Graph Embedding, Knowledge Graph Embedding, Open Information Extraction, Question Answering |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1541/ |
| https://www.aclweb.org/anthology/L18-1541 | |
| PWC | https://paperswithcode.com/paper/learning-to-map-natural-language-statements |
| Repo | |
| Framework | |
Translation Crowdsourcing: Creating a Multilingual Corpus of Online Educational Content
| Title | Translation Crowdsourcing: Creating a Multilingual Corpus of Online Educational Content |
| Authors | Vilelmini Sosoni, Katia Lida Kermanidis, Maria Stasimioti, Thanasis Naskos, Eirini Takoulidou, Menno van Zaanen, Sheila Castilho, Panayota Georgakopoulou, Valia Kordoni, Markus Egg |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1075/ |
| https://www.aclweb.org/anthology/L18-1075 | |
| PWC | https://paperswithcode.com/paper/translation-crowdsourcing-creating-a |
| Repo | |
| Framework | |
Preserving Workflow Reproducibility: The RePlay-DH Client as a Tool for Process Documentation
| Title | Preserving Workflow Reproducibility: The RePlay-DH Client as a Tool for Process Documentation |
| Authors | Markus G{"a}rtner, Uli Hahn, Sibylle Hermann |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1089/ |
| https://www.aclweb.org/anthology/L18-1089 | |
| PWC | https://paperswithcode.com/paper/preserving-workflow-reproducibility-the |
| Repo | |
| Framework | |
Towards a Gold Standard Corpus for Variable Detection and Linking in Social Science Publications
| Title | Towards a Gold Standard Corpus for Variable Detection and Linking in Social Science Publications |
| Authors | Andrea Zielinski, Peter Mutschke |
| Abstract | |
| Tasks | Entity Linking, Natural Language Inference, Semantic Textual Similarity, Text Classification |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1084/ |
| https://www.aclweb.org/anthology/L18-1084 | |
| PWC | https://paperswithcode.com/paper/towards-a-gold-standard-corpus-for-variable |
| Repo | |
| Framework | |
Joint autoencoders: a flexible meta-learning framework
| Title | Joint autoencoders: a flexible meta-learning framework |
| Authors | Baruch Epstein, Ron Meir, Tomer Michaeli |
| Abstract | The incorporation of prior knowledge into learning is essential in achieving good performance based on small noisy samples. Such knowledge is often incorporated through the availability of related data arising from domains and tasks similar to the one of current interest. Ideally one would like to allow both the data for the current task and for previous related tasks to self-organize the learning system in such a way that commonalities and differences between the tasks are learned in a data-driven fashion. We develop a framework for learning multiple tasks simultaneously, based on sharing features that are common to all tasks, achieved through the use of a modular deep feedforward neural network consisting of shared branches, dealing with the common features of all tasks, and private branches, learning the specific unique aspects of each task. Once an appropriate weight sharing architecture has been established, learning takes place through standard algorithms for feedforward networks, e.g., stochastic gradient descent and its variations. The method deals with meta-learning (such as domain adaptation, transfer and multi-task learning) in a unified fashion, and can easily deal with data arising from different types of sources. Numerical experiments demonstrate the effectiveness of learning in domain adaptation and transfer learning setups, and provide evidence for the flexible and task-oriented representations arising in the network. |
| Tasks | Domain Adaptation, Meta-Learning, Multi-Task Learning, Transfer Learning |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=S1tWRJ-R- |
| https://openreview.net/pdf?id=S1tWRJ-R- | |
| PWC | https://paperswithcode.com/paper/joint-autoencoders-a-flexible-meta-learning |
| Repo | |
| Framework | |
Data Augmentation for Neural Online Chats Response Selection
| Title | Data Augmentation for Neural Online Chats Response Selection |
| Authors | Wenchao Du, Alan Black |
| Abstract | Data augmentation seeks to manipulate the available data for training to improve the generalization ability of models. We investigate two data augmentation proxies, permutation and flipping, for neural dialog response selection task on various models over multiple datasets, including both Chinese and English languages. Different from standard data augmentation techniques, our method combines the original and synthesized data for prediction. Empirical results show that our approach can gain 1 to 3 recall-at-1 points over baseline models in both full-scale and small-scale settings. |
| Tasks | Data Augmentation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5708/ |
| https://www.aclweb.org/anthology/W18-5708 | |
| PWC | https://paperswithcode.com/paper/data-augmentation-for-neural-online-chats |
| Repo | |
| Framework | |
Continuous Word Embedding Fusion via Spectral Decomposition
| Title | Continuous Word Embedding Fusion via Spectral Decomposition |
| Authors | Tianfan Fu, Cheng Zhang, M, Stephan t |
| Abstract | Word embeddings have become a mainstream tool in statistical natural language processing. Practitioners often use pre-trained word vectors, which were trained on large generic text corpora, and which are readily available on the web. However, pre-trained word vectors oftentimes lack important words from specific domains. It is therefore often desirable to extend the vocabulary and embed new words into a set of pre-trained word vectors. In this paper, we present an efficient method for including new words from a specialized corpus, containing new words, into pre-trained generic word embeddings. We build on the established view of word embeddings as matrix factorizations to present a spectral algorithm for this task. Experiments on several domain-specific corpora with specialized vocabularies demonstrate that our method is able to embed the new words efficiently into the original embedding space. Compared to competing methods, our method is faster, parameter-free, and deterministic. |
| Tasks | Machine Translation, Transfer Learning, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-1002/ |
| https://www.aclweb.org/anthology/K18-1002 | |
| PWC | https://paperswithcode.com/paper/continuous-word-embedding-fusion-via-spectral |
| Repo | |
| Framework | |
SMILE Swiss German Sign Language Dataset
| Title | SMILE Swiss German Sign Language Dataset |
| Authors | Sarah Ebling, Necati Cihan Camg{"o}z, Penny Boyes Braem, Katja Tissi, S Sidler-Miserez, ra, Stephanie Stoll, Simon Hadfield, Tobias Haug, Richard Bowden, S Tornay, rine, Marzieh Razavi, Mathew Magimai-Doss |
| Abstract | |
| Tasks | Sign Language Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1666/ |
| https://www.aclweb.org/anthology/L18-1666 | |
| PWC | https://paperswithcode.com/paper/smile-swiss-german-sign-language-dataset |
| Repo | |
| Framework | |
A Corpus to Learn Refer-to-as Relations for Nominals
| Title | A Corpus to Learn Refer-to-as Relations for Nominals |
| Authors | Wasi Ahmad, Kai-Wei Chang |
| Abstract | |
| Tasks | Coreference Resolution, Learning Semantic Representations, Question Answering, Text Summarization |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1062/ |
| https://www.aclweb.org/anthology/L18-1062 | |
| PWC | https://paperswithcode.com/paper/a-corpus-to-learn-refer-to-as-relations-for |
| Repo | |
| Framework | |
CRUISE: Cold-Start New Skill Development via Iterative Utterance Generation
| Title | CRUISE: Cold-Start New Skill Development via Iterative Utterance Generation |
| Authors | Yilin Shen, Avik Ray, Abhishek Patel, Hongxia Jin |
| Abstract | We present a system, CRUISE, that guides ordinary software developers to build a high quality natural language understanding (NLU) engine from scratch. This is the fundamental step of building a new skill in personal assistants. Unlike existing solutions that require either developers or crowdsourcing to manually generate and annotate a large number of utterances, we design a hybrid rule-based and data-driven approach with the capability to iteratively generate more and more utterances. Our system only requires light human workload to iteratively prune incorrect utterances. CRUISE outputs a well trained NLU engine and a large scale annotated utterance corpus that third parties can use to develop their custom skills. Using both benchmark dataset and custom datasets we collected in real-world settings, we validate the high quality of CRUISE generated utterances via both competitive NLU performance and human evaluation. We also show the largely reduced human workload in terms of both cognitive load and human pruning time consumption. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-4018/ |
| https://www.aclweb.org/anthology/P18-4018 | |
| PWC | https://paperswithcode.com/paper/cruise-cold-start-new-skill-development-via |
| Repo | |
| Framework | |
Sensitivity to Input Order: Evaluation of an Incremental and Memory-Limited Bayesian Cross-Situational Word Learning Model
| Title | Sensitivity to Input Order: Evaluation of an Incremental and Memory-Limited Bayesian Cross-Situational Word Learning Model |
| Authors | Sepideh Sadeghi, Matthias Scheutz |
| Abstract | We present a variation of the incremental and memory-limited algorithm in (Sadeghi et al., 2017) for Bayesian cross-situational word learning and evaluate the model in terms of its functional performance and its sensitivity to input order. We show that the functional performance of our sub-optimal model on corpus data is close to that of its optimal counterpart (Frank et al., 2009), while only the sub-optimal model is capable of predicting the input order effects reported in experimental studies. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1268/ |
| https://www.aclweb.org/anthology/C18-1268 | |
| PWC | https://paperswithcode.com/paper/sensitivity-to-input-order-evaluation-of-an |
| Repo | |
| Framework | |
ReSyf: a French lexicon with ranked synonyms
| Title | ReSyf: a French lexicon with ranked synonyms |
| Authors | Mokhtar B. Billami, Thomas Fran{\c{c}}ois, N{'u}ria Gala |
| Abstract | In this article, we present ReSyf, a lexical resource of monolingual synonyms ranked according to their difficulty to be read and understood by native learners of French. The synonyms come from an existing lexical network and they have been semantically disambiguated and refined. A ranking algorithm, based on a wide range of linguistic features and validated through an evaluation campaign with human annotators, automatically sorts the synonyms corresponding to a given word sense by reading difficulty. ReSyf is freely available and will be integrated into a web platform for reading assistance. It can also be applied to perform lexical simplification of French texts. |
| Tasks | Lexical Simplification, Part-Of-Speech Tagging, Text Simplification |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1218/ |
| https://www.aclweb.org/anthology/C18-1218 | |
| PWC | https://paperswithcode.com/paper/resyf-a-french-lexicon-with-ranked-synonyms |
| Repo | |
| Framework | |
Bilateral Ordinal Relevance Multi-Instance Regression for Facial Action Unit Intensity Estimation
| Title | Bilateral Ordinal Relevance Multi-Instance Regression for Facial Action Unit Intensity Estimation |
| Authors | Yong Zhang, Rui Zhao, Weiming Dong, Bao-Gang Hu, Qiang Ji |
| Abstract | Automatic intensity estimation of facial action units (AUs) is challenging in two aspects. First, capturing subtle changes of facial appearance is quiet difficult. Second, the annotation of AU intensity is scarce and expensive. Intensity annotation requires strong domain knowledge thus only experts are qualified. The majority of methods directly apply supervised learning techniques to AU intensity estimation while few methods exploit unlabeled samples to improve the performance. In this paper, we propose a novel weakly supervised regression model-Bilateral Ordinal Relevance Multi-instance Regression (BORMIR), which learns a frame-level intensity estimator with weakly labeled sequences. From a new perspective, we introduce relevance to model sequential data and consider two bag labels for each bag. The AU intensity estimation is formulated as a joint regressor and relevance learning problem. Temporal dynamics of both relevance and AU intensity are leveraged to build connections among labeled and unlabeled image frames to provide weak supervision. We also develop an efficient algorithm for optimization based on the alternating minimization framework. Evaluations on three expression databases demonstrate the effectiveness of the proposed model. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zhang_Bilateral_Ordinal_Relevance_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Bilateral_Ordinal_Relevance_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/bilateral-ordinal-relevance-multi-instance |
| Repo | |
| Framework | |
Learning Simplifications for Specific Target Audiences
| Title | Learning Simplifications for Specific Target Audiences |
| Authors | Carolina Scarton, Lucia Specia |
| Abstract | Text simplification (TS) is a monolingual text-to-text transformation task where an original (complex) text is transformed into a target (simpler) text. Most recent work is based on sequence-to-sequence neural models similar to those used for machine translation (MT). Different from MT, TS data comprises more elaborate transformations, such as sentence splitting. It can also contain multiple simplifications of the same original text targeting different audiences, such as school grade levels. We explore these two features of TS to build models tailored for specific grade levels. Our approach uses a standard sequence-to-sequence architecture where the original sequence is annotated with information about the target audience and/or the (predicted) type of simplification operation. We show that it outperforms state-of-the-art TS approaches (up to 3 and 12 BLEU and SARI points, respectively), including when training data for the specific complex-simple combination of grade levels is not available, i.e. zero-shot learning. |
| Tasks | Lexical Simplification, Machine Translation, Text Simplification, Zero-Shot Learning |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2113/ |
| https://www.aclweb.org/anthology/P18-2113 | |
| PWC | https://paperswithcode.com/paper/learning-simplifications-for-specific-target |
| Repo | |
| Framework | |
