Paper Group NANR 101
Statistical Machine Transliteration Baselines for NEWS 2018. Named-Entity Tagging and Domain adaptation for Better Customized Translation. Leveraging Meta-Embeddings for Bilingual Lexicon Extraction from Specialized Comparable Corpora. Sim2Real Viewpoint Invariant Visual Servoing by Recurrent Control. Conditions on abruptness in a gradient-ascent M …
Statistical Machine Transliteration Baselines for NEWS 2018
| Title | Statistical Machine Transliteration Baselines for NEWS 2018 |
| Authors | Snigdha Singhania, Minh Nguyen, Gia H. Ngo, Nancy Chen |
| Abstract | This paper reports the results of our trans-literation experiments conducted on NEWS 2018 Shared Task dataset. We focus on creating the baseline systems trained using two open-source, statistical transliteration tools, namely Sequitur and Moses. We discuss the pre-processing steps performed on this dataset for both the systems. We also provide a re-ranking system which uses top hypotheses from Sequitur and Moses to create a consolidated list of transliterations. The results obtained from each of these models can be used to present a good starting point for the participating teams. |
| Tasks | Information Retrieval, Machine Translation, Transliteration |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2410/ |
| https://www.aclweb.org/anthology/W18-2410 | |
| PWC | https://paperswithcode.com/paper/statistical-machine-transliteration-baselines |
| Repo | |
| Framework | |
Named-Entity Tagging and Domain adaptation for Better Customized Translation
| Title | Named-Entity Tagging and Domain adaptation for Better Customized Translation |
| Authors | Zhongwei Li, Xuancong Wang, Ai Ti Aw, Eng Siong Chng, Haizhou Li |
| Abstract | Customized translation need pay spe-cial attention to the target domain ter-minology especially the named-entities for the domain. Adding linguistic features to neural machine translation (NMT) has been shown to benefit translation in many studies. In this paper, we further demonstrate that adding named-entity (NE) feature with named-entity recognition (NER) into the source language produces better translation with NMT. Our experiments show that by just including the different NE classes and boundary tags, we can increase the BLEU score by around 1 to 2 points using the standard test sets from WMT2017. We also show that adding NE tags using NER and applying in-domain adaptation can be combined to further improve customized machine translation. |
| Tasks | Domain Adaptation, Machine Translation, Named Entity Recognition, Sentence Embedding |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2407/ |
| https://www.aclweb.org/anthology/W18-2407 | |
| PWC | https://paperswithcode.com/paper/named-entity-tagging-and-domain-adaptation |
| Repo | |
| Framework | |
Leveraging Meta-Embeddings for Bilingual Lexicon Extraction from Specialized Comparable Corpora
| Title | Leveraging Meta-Embeddings for Bilingual Lexicon Extraction from Specialized Comparable Corpora |
| Authors | Amir Hazem, Emmanuel Morin |
| Abstract | Recent evaluations on bilingual lexicon extraction from specialized comparable corpora have shown contrasted performance while using word embedding models. This can be partially explained by the lack of large specialized comparable corpora to build efficient representations. Within this context, we try to answer the following questions: First, (i) among the state-of-the-art embedding models, whether trained on specialized corpora or pre-trained on large general data sets, which one is the most appropriate model for bilingual terminology extraction? Second (ii) is it worth it to combine multiple embeddings trained on different data sets? For that purpose, we propose the first systematic evaluation of different word embedding models for bilingual terminology extraction from specialized comparable corpora. We emphasize how the character-based embedding model outperforms other models on the quality of the extracted bilingual lexicons. Further more, we propose a new efficient way to combine different embedding models learned from specialized and general-domain data sets. Our approach leads to higher performance than the best individual embedding model. |
| Tasks | Information Retrieval, Machine Translation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1080/ |
| https://www.aclweb.org/anthology/C18-1080 | |
| PWC | https://paperswithcode.com/paper/leveraging-meta-embeddings-for-bilingual |
| Repo | |
| Framework | |
Sim2Real Viewpoint Invariant Visual Servoing by Recurrent Control
| Title | Sim2Real Viewpoint Invariant Visual Servoing by Recurrent Control |
| Authors | Fereshteh Sadeghi, Alexander Toshev, Eric Jang, Sergey Levine |
| Abstract | Humans are remarkably proficient at controlling their limbs and tools from a wide range of viewpoints. In robotics, this ability is referred to as visual servoing: moving a tool or end-point to a desired location using primarily visual feedback. In this paper, we propose learning viewpoint invariant visual servoing skills in a robot manipulation task. We train a deep recurrent controller that can automatically determine which actions move the end-effector of a robotic arm to a desired object. This problem is fundamentally ambiguous: under severe variation in viewpoint, it may be impossible to determine the actions in a single feedforward operation. Instead, our visual servoing approach uses its memory of past movements to understand how the actions affect the robot motion from the current viewpoint, correcting mistakes and gradually moving closer to the target. This ability is in stark contrast to previous visual servoing methods, which assume known dynamics or require a calibration phase. We learn our recurrent controller using simulated data, synthetic demonstrations and reinforcement learning. We then describe how the resulting model can be transferred to a real-world robot by disentangling perception from control and only adapting the visual layers. The adapted model can servo to previously unseen objects from novel viewpoints on a real-world Kuka IIWA robotic arm. For supplementary videos, see: href{https://www.youtube.com/watch?v=oLgM2Bnb7fo}{https://www.youtube.com/watch?v=oLgM2Bnb7fo} |
| Tasks | Calibration |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Sadeghi_Sim2Real_Viewpoint_Invariant_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Sadeghi_Sim2Real_Viewpoint_Invariant_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/sim2real-viewpoint-invariant-visual-servoing |
| Repo | |
| Framework | |
Conditions on abruptness in a gradient-ascent Maximum Entropy learner
| Title | Conditions on abruptness in a gradient-ascent Maximum Entropy learner |
| Authors | Elliott Moreton |
| Abstract | |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/W18-0312/ |
| https://www.aclweb.org/anthology/W18-0312 | |
| PWC | https://paperswithcode.com/paper/conditions-on-abruptness-in-a-gradient-ascent |
| Repo | |
| Framework | |
The University of Edinburgh’s Submissions to the WMT18 News Translation Task
| Title | The University of Edinburgh’s Submissions to the WMT18 News Translation Task |
| Authors | Barry Haddow, Nikolay Bogoychev, Denis Emelin, Ulrich Germann, Roman Grundkiewicz, Kenneth Heafield, Antonio Valerio Miceli Barone, Rico Sennrich |
| Abstract | The University of Edinburgh made submissions to all 14 language pairs in the news translation task, with strong performances in most pairs. We introduce new RNN-variant, mixed RNN/Transformer ensembles, data selection and weighting, and extensions to back-translation. |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6412/ |
| https://www.aclweb.org/anthology/W18-6412 | |
| PWC | https://paperswithcode.com/paper/the-university-of-edinburghas-submissions-to |
| Repo | |
| Framework | |
Inducing a lexicon of sociolinguistic variables from code-mixed text
| Title | Inducing a lexicon of sociolinguistic variables from code-mixed text |
| Authors | Philippa Shoemark, James Kirby, Sharon Goldwater |
| Abstract | Sociolinguistics is often concerned with how variants of a linguistic item (e.g., \textit{nothing} vs. \textit{nothin{'}}) are used by different groups or in different situations. We introduce the task of inducing lexical variables from code-mixed text: that is, identifying equivalence pairs such as (\textit{football}, \textit{fitba}) along with their linguistic code (\textit{football}→British, \textit{fitba}→Scottish). We adapt a framework for identifying gender-biased word pairs to this new task, and present results on three different pairs of English dialects, using tweets as the code-mixed text. Our system achieves precision of over 70{%} for two of these three datasets, and produces useful results even without extensive parameter tuning. Our success in adapting this framework from gender to language variety suggests that it could be used to discover other types of analogous pairs as well. |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6101/ |
| https://www.aclweb.org/anthology/W18-6101 | |
| PWC | https://paperswithcode.com/paper/inducing-a-lexicon-of-sociolinguistic |
| Repo | |
| Framework | |
A Corpus of Corporate Annual and Social Responsibility Reports: 280 Million Tokens of Balanced Organizational Writing
| Title | A Corpus of Corporate Annual and Social Responsibility Reports: 280 Million Tokens of Balanced Organizational Writing |
| Authors | Sebastian G.M. H{"a}ndschke, Sven Buechel, Jan Goldenstein, Philipp Poschmann, Tinghui Duan, Peter Walgenbach, Udo Hahn |
| Abstract | We introduce JOCo, a novel text corpus for NLP analytics in the field of economics, business and management. This corpus is composed of corporate annual and social responsibility reports of the top 30 US, UK and German companies in the major (DJIA, FTSE 100, DAX), middle-sized (S{&}P 500, FTSE 250, MDAX) and technology (NASDAQ, FTSE AIM 100, TECDAX) stock indices, respectively. Altogether, this adds up to 5,000 reports from 270 companies headquartered in three of the world{'}s most important economies. The corpus spans a time frame from 2000 up to 2015 and contains, in total, 282M tokens. We also feature JOCo in a small-scale experiment to demonstrate its potential for NLP-fueled studies in economics, business and management research. |
| Tasks | Tokenization |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3103/ |
| https://www.aclweb.org/anthology/W18-3103 | |
| PWC | https://paperswithcode.com/paper/a-corpus-of-corporate-annual-and-social |
| Repo | |
| Framework | |
Context-Aware Neural Model for Temporal Information Extraction
| Title | Context-Aware Neural Model for Temporal Information Extraction |
| Authors | Yuanliang Meng, Anna Rumshisky |
| Abstract | We propose a context-aware neural network model for temporal information extraction. This model has a uniform architecture for event-event, event-timex and timex-timex pairs. A Global Context Layer (GCL), inspired by Neural Turing Machine (NTM), stores processed temporal relations in narrative order, and retrieves them for use when relevant entities come in. Relations are then classified in context. The GCL model has long-term memory and attention mechanisms to resolve irregular long-distance dependencies that regular RNNs such as LSTM cannot recognize. It does not require any new input features, while outperforming the existing models in literature. To our knowledge it is also the first model to use NTM-like architecture to process the information from global context in discourse-scale natural text processing. We are going to release the source code in the future. |
| Tasks | Information Retrieval, Question Answering, Temporal Information Extraction |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1049/ |
| https://www.aclweb.org/anthology/P18-1049 | |
| PWC | https://paperswithcode.com/paper/context-aware-neural-model-for-temporal |
| Repo | |
| Framework | |
A Graph-theoretic Summary Evaluation for ROUGE
| Title | A Graph-theoretic Summary Evaluation for ROUGE |
| Authors | Elaheh ShafieiBavani, Mohammad Ebrahimi, Raymond Wong, Fang Chen |
| Abstract | ROUGE is one of the first and most widely used evaluation metrics for text summarization. However, its assessment merely relies on surface similarities between peer and model summaries. Consequently, ROUGE is unable to fairly evaluate summaries including lexical variations and paraphrasing. We propose a graph-based approach adopted into ROUGE to evaluate summaries based on both lexical and semantic similarities. Experiment results over TAC AESOP datasets show that exploiting the lexico-semantic similarity of the words used in summaries would significantly help ROUGE correlate better with human judgments. |
| Tasks | Abstractive Text Summarization, Semantic Similarity, Semantic Textual Similarity, Text Summarization |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1085/ |
| https://www.aclweb.org/anthology/D18-1085 | |
| PWC | https://paperswithcode.com/paper/a-graph-theoretic-summary-evaluation-for |
| Repo | |
| Framework | |
Language-Guided Adaptive Perception for Efficient Grounded Communication with Robotic Manipulators in Cluttered Environments
| Title | Language-Guided Adaptive Perception for Efficient Grounded Communication with Robotic Manipulators in Cluttered Environments |
| Authors | Siddharth Patki, Thomas Howard |
| Abstract | The utility of collaborative manipulators for shared tasks is highly dependent on the speed and accuracy of communication between the human and the robot. The run-time of recently developed probabilistic inference models for situated symbol grounding of natural language instructions depends on the complexity of the representation of the environment in which they reason. As we move towards more complex bi-directional interactions, tasks, and environments, we need intelligent perception models that can selectively infer precise pose, semantics, and affordances of the objects when inferring exhaustively detailed world models is inefficient and prohibits real-time interaction with these robots. In this paper we propose a model of language and perception for the problem of adapting the configuration of the robot perception pipeline for tasks where constructing exhaustively detailed models of the environment is inefficient and inconsequential for symbol grounding. We present experimental results from a synthetic corpus of natural language instructions for robot manipulation in example environments. The results demonstrate that by adapting perception we get significant gains in terms of run-time for perception and situated symbol grounding of the language instructions without a loss in the accuracy of the latter. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-5016/ |
| https://www.aclweb.org/anthology/W18-5016 | |
| PWC | https://paperswithcode.com/paper/language-guided-adaptive-perception-for |
| Repo | |
| Framework | |
An Evaluation of Two Vocabulary Reduction Methods for Neural Machine Translation
| Title | An Evaluation of Two Vocabulary Reduction Methods for Neural Machine Translation |
| Authors | Duygu Ataman, Marcello Federico |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1810/ |
| https://www.aclweb.org/anthology/W18-1810 | |
| PWC | https://paperswithcode.com/paper/an-evaluation-of-two-vocabulary-reduction |
| Repo | |
| Framework | |
Distantly Supervised Attribute Detection from Reviews
| Title | Distantly Supervised Attribute Detection from Reviews |
| Authors | Lisheng Fu, Pablo Barrio |
| Abstract | This work aims to detect specific attributes of a place (e.g., if it has a romantic atmosphere, or if it offers outdoor seating) from its user reviews via distant supervision: without direct annotation of the review text, we use the crowdsourced attribute labels of the place as labels of the review text. We then use review-level attention to pay more attention to those reviews related to the attributes. The experimental results show that our attention-based model predicts attributes for places from reviews with over 98{%} accuracy. The attention weights assigned to each review provide explanation of capturing relevant reviews. |
| Tasks | Entity Extraction, Sentiment Analysis |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6110/ |
| https://www.aclweb.org/anthology/W18-6110 | |
| PWC | https://paperswithcode.com/paper/distantly-supervised-attribute-detection-from |
| Repo | |
| Framework | |
Multimodal image alignment through a multiscale chain of neural networks with application to remote sensing
| Title | Multimodal image alignment through a multiscale chain of neural networks with application to remote sensing |
| Authors | Armand Zampieri, Guillaume Charpiat, Nicolas Girard, Yuliya Tarabalka |
| Abstract | We tackle here the problem of multimodal image non-rigid registration, which is of prime importance in remote sensing and medical imaging. The difficulties encountered by classical registration approaches include feature design and slow optimization by gradient descent. By analyzing these methods, we note the significance of the notion of scale. We design easy-to-train, fully-convolutional neural networks able to learn scale-specific features. Once chained appropriately, they perform global registration in linear time, getting rid of gradient descent schemes by predicting directly the deformation. We show their performance in terms of quality and speed through various tasks of remote sensing multimodal image alignment. In particular, we are able to register correctly cadastral maps of buildings as well as road polylines onto RGB images, and outperform current keypoint matching methods. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Armand_Zampieri_Multimodal_image_alignment_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Armand_Zampieri_Multimodal_image_alignment_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/multimodal-image-alignment-through-a |
| Repo | |
| Framework | |
Automated Essay Scoring in the Presence of Biased Ratings
| Title | Automated Essay Scoring in the Presence of Biased Ratings |
| Authors | Evelin Amorim, Marcia Can{\c{c}}ado, Adriano Veloso |
| Abstract | Studies in Social Sciences have revealed that when people evaluate someone else, their evaluations often reflect their biases. As a result, rater bias may introduce highly subjective factors that make their evaluations inaccurate. This may affect automated essay scoring models in many ways, as these models are typically designed to model (potentially biased) essay raters. While there is sizeable literature on rater effects in general settings, it remains unknown how rater bias affects automated essay scoring. To this end, we present a new annotated corpus containing essays and their respective scores. Different from existing corpora, our corpus also contains comments provided by the raters in order to ground their scores. We present features to quantify rater bias based on their comments, and we found that rater bias plays an important role in automated essay scoring. We investigated the extent to which rater bias affects models based on hand-crafted features. Finally, we propose to rectify the training set by removing essays associated with potentially biased scores while learning the scoring model. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1021/ |
| https://www.aclweb.org/anthology/N18-1021 | |
| PWC | https://paperswithcode.com/paper/automated-essay-scoring-in-the-presence-of |
| Repo | |
| Framework | |
