Paper Group NANR 7
Improving cross-domain n-gram language modelling with skipgrams. DCU-UvA Multimodal MT System Report. A Shared Task on Multimodal Machine Translation and Crosslingual Image Description. Evaluating Interactive System Adaptation. Transitivity in Light Verb Variations in Mandarin Chinese – A Comparable Corpus-based Statistical Approach. DalGTM at Sem …
Improving cross-domain n-gram language modelling with skipgrams
| Title | Improving cross-domain n-gram language modelling with skipgrams |
| Authors | Louis Onrust, Antal van den Bosch, Hugo Van hamme |
| Abstract | |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2023/ |
| https://www.aclweb.org/anthology/P16-2023 | |
| PWC | https://paperswithcode.com/paper/improving-cross-domain-n-gram-language |
| Repo | |
| Framework | |
DCU-UvA Multimodal MT System Report
| Title | DCU-UvA Multimodal MT System Report |
| Authors | Iacer Calixto, Desmond Elliott, Stella Frank |
| Abstract | |
| Tasks | Machine Translation, Multimodal Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2359/ |
| https://www.aclweb.org/anthology/W16-2359 | |
| PWC | https://paperswithcode.com/paper/dcu-uva-multimodal-mt-system-report |
| Repo | |
| Framework | |
A Shared Task on Multimodal Machine Translation and Crosslingual Image Description
| Title | A Shared Task on Multimodal Machine Translation and Crosslingual Image Description |
| Authors | Lucia Specia, Stella Frank, Khalil Sima{'}an, Desmond Elliott |
| Abstract | |
| Tasks | Image Retrieval, Machine Translation, Multimodal Machine Translation, Question Answering, Video Captioning, Visual Question Answering |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2346/ |
| https://www.aclweb.org/anthology/W16-2346 | |
| PWC | https://paperswithcode.com/paper/a-shared-task-on-multimodal-machine |
| Repo | |
| Framework | |
Evaluating Interactive System Adaptation
| Title | Evaluating Interactive System Adaptation |
| Authors | Edouard Geoffrois |
| Abstract | Enabling users of intelligent systems to enhance the system performance by providing feedback on their errors is an important need. However, the ability of systems to learn from user feedback is difficult to evaluate in an objective and comparative way. Indeed, the involvement of real users in the adaptation process is an impediment to objective evaluation. This issue can be solved by using an oracle approach, where users are simulated by oracles having access to the reference test data. Another difficulty is to find a meaningful metric despite the fact that system improvements depend on the feedback provided and on the system itself. A solution is to measure the minimal amount of information needed to correct all system errors. It can be shown that for any well defined non interactive task, the interactively supervised version of the task can be evaluated by combining such an oracle-based approach and a minimum supervision rate metric. This new evaluation protocol for adaptive systems is not only expected to drive progress for such systems, but also to pave the way for a specialisation of actors along the value chain of their technological development. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1039/ |
| https://www.aclweb.org/anthology/L16-1039 | |
| PWC | https://paperswithcode.com/paper/evaluating-interactive-system-adaptation |
| Repo | |
| Framework | |
Transitivity in Light Verb Variations in Mandarin Chinese – A Comparable Corpus-based Statistical Approach
| Title | Transitivity in Light Verb Variations in Mandarin Chinese – A Comparable Corpus-based Statistical Approach |
| Authors | Menghan Jiang, Dingxu Shi, Chu-Ren Huang |
| Abstract | |
| Tasks | |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/Y16-3018/ |
| https://www.aclweb.org/anthology/Y16-3018 | |
| PWC | https://paperswithcode.com/paper/transitivity-in-light-verb-variations-in |
| Repo | |
| Framework | |
DalGTM at SemEval-2016 Task 1: Importance-Aware Compositional Approach to Short Text Similarity
| Title | DalGTM at SemEval-2016 Task 1: Importance-Aware Compositional Approach to Short Text Similarity |
| Authors | Jie Mei, Aminul Islam, Evangelos Milios |
| Abstract | |
| Tasks | Information Retrieval, Semantic Textual Similarity |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1118/ |
| https://www.aclweb.org/anthology/S16-1118 | |
| PWC | https://paperswithcode.com/paper/dalgtm-at-semeval-2016-task-1-importance |
| Repo | |
| Framework | |
Nederlab: Towards a Single Portal and Research Environment for Diachronic Dutch Text Corpora
| Title | Nederlab: Towards a Single Portal and Research Environment for Diachronic Dutch Text Corpora |
| Authors | Hennie Brugman, Martin Reynaert, Nicoline van der Sijs, Ren{'e} van Stipriaan, Erik Tjong Kim Sang, Antal van den Bosch |
| Abstract | The Nederlab project aims to bring together all digitized texts relevant to the Dutch national heritage, the history of the Dutch language and culture (circa 800 {–} present) in one user friendly and tool enriched open access web interface. This paper describes Nederlab halfway through the project period and discusses the collections incorporated, back-office processes, system back-end as well as the Nederlab Research Portal end-user web application. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1203/ |
| https://www.aclweb.org/anthology/L16-1203 | |
| PWC | https://paperswithcode.com/paper/nederlab-towards-a-single-portal-and-research |
| Repo | |
| Framework | |
Detecting Level of Belief in Chinese and Spanish
| Title | Detecting Level of Belief in Chinese and Spanish |
| Authors | Juan Pablo Colomer, Keyu Lai, Owen Rambow |
| Abstract | There has been extensive work on detecting the level of committed belief (also known as {``}factuality{''}) that an author is expressing towards the propositions in his or her utterances. Previous work on English has revealed that this can be done as a sequence tagging task. In this paper, we investigate the same task for Chinese and Spanish, two very different languages from English and from each other. | |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5003/ |
| https://www.aclweb.org/anthology/W16-5003 | |
| PWC | https://paperswithcode.com/paper/detecting-level-of-belief-in-chinese-and |
| Repo | |
| Framework | |
The ILSP/ARC submission to the WMT 2016 Bilingual Document Alignment Shared Task
| Title | The ILSP/ARC submission to the WMT 2016 Bilingual Document Alignment Shared Task |
| Authors | Vassilis Papavassiliou, Prokopis Prokopidis, Stelios Piperidis |
| Abstract | |
| Tasks | Language Identification, Machine Translation, Text Classification |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2375/ |
| https://www.aclweb.org/anthology/W16-2375 | |
| PWC | https://paperswithcode.com/paper/the-ilsparc-submission-to-the-wmt-2016 |
| Repo | |
| Framework | |
Complementarity, F-score, and NLP Evaluation
| Title | Complementarity, F-score, and NLP Evaluation |
| Authors | Leon Derczynski |
| Abstract | This paper addresses the problem of quantifying the differences between entity extraction systems, where in general only a small proportion a document should be selected. Comparing overall accuracy is not very useful in these cases, as small differences in accuracy may correspond to huge differences in selections over the target minority class. Conventionally, one may use per-token complementarity to describe these differences, but it is not very useful when the set is heavily skewed. In such situations, which are common in information retrieval and entity recognition, metrics like precision and recall are typically used to describe performance. However, precision and recall fail to describe the differences between sets of objects selected by different decision strategies, instead just describing the proportional amount of correct and incorrect objects selected. This paper presents a method for measuring complementarity for precision, recall and F-score, quantifying the difference between entity extraction approaches. |
| Tasks | Entity Extraction, Information Retrieval |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1040/ |
| https://www.aclweb.org/anthology/L16-1040 | |
| PWC | https://paperswithcode.com/paper/complementarity-f-score-and-nlp-evaluation |
| Repo | |
| Framework | |
Detection and Accurate Localization of Circular Fiducials Under Highly Challenging Conditions
| Title | Detection and Accurate Localization of Circular Fiducials Under Highly Challenging Conditions |
| Authors | Lilian Calvet, Pierre Gurdjos, Carsten Griwodz, Simone Gasparini |
| Abstract | Using fiducial markers ensures reliable detection and identification of planar features in images. Fiducials are used in a wide range of applications, especially when a reliable visual reference is needed, e.g., to track the camera in cluttered or textureless environments. A marker designed for such applications must be robust to partial occlusions, varying distances and angles of view, and fast camera motions. In this paper, we present a robust, highly accurate fiducial system, whose markers consist of concentric rings, along with its theoretical foundations. Relying on projective properties, it allows to robustly localize the imaged marker and to accurately detect the position of the image of the (common) circle center. We demonstrate that our system can detect and accurately localize these circular fiducials under very challenging conditions and the experimental results reveal that it outperforms other recent fiducial systems. |
| Tasks | |
| Published | 2016-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2016/html/Calvet_Detection_and_Accurate_CVPR_2016_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2016/papers/Calvet_Detection_and_Accurate_CVPR_2016_paper.pdf | |
| PWC | https://paperswithcode.com/paper/detection-and-accurate-localization-of |
| Repo | |
| Framework | |
Which Tumblr Post Should I Read Next?
| Title | Which Tumblr Post Should I Read Next? |
| Authors | Zornitsa Kozareva, Makoto Yamada |
| Abstract | |
| Tasks | Matrix Completion, Recommendation Systems |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2054/ |
| https://www.aclweb.org/anthology/P16-2054 | |
| PWC | https://paperswithcode.com/paper/which-tumblr-post-should-i-read-next |
| Repo | |
| Framework | |
Finding Optimists and Pessimists on Twitter
| Title | Finding Optimists and Pessimists on Twitter |
| Authors | Xianzhi Ruan, Steven Wilson, Rada Mihalcea |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2052/ |
| https://www.aclweb.org/anthology/P16-2052 | |
| PWC | https://paperswithcode.com/paper/finding-optimists-and-pessimists-on-twitter |
| Repo | |
| Framework | |
Bootstrapped Text-level Named Entity Recognition for Literature
| Title | Bootstrapped Text-level Named Entity Recognition for Literature |
| Authors | Julian Brooke, Adam Hammond, Timothy Baldwin |
| Abstract | |
| Tasks | Named Entity Recognition |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2056/ |
| https://www.aclweb.org/anthology/P16-2056 | |
| PWC | https://paperswithcode.com/paper/bootstrapped-text-level-named-entity |
| Repo | |
| Framework | |
Learning Monolingual Compositional Representations via Bilingual Supervision
| Title | Learning Monolingual Compositional Representations via Bilingual Supervision |
| Authors | Ahmed Elgohary, Marine Carpuat |
| Abstract | |
| Tasks | Cross-Lingual Document Classification, Cross-Lingual Transfer, Document Classification, Machine Translation, Representation Learning, Semantic Textual Similarity |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2059/ |
| https://www.aclweb.org/anthology/P16-2059 | |
| PWC | https://paperswithcode.com/paper/learning-monolingual-compositional |
| Repo | |
| Framework | |
