Paper Group NANR 55
SHEF-Multimodal: Grounding Machine Translation on Images. Learning Semantic Relatedness in Community Question Answering Using Neural Models. A Search-Based Dynamic Reranking Model for Dependency Parsing. The COPLE2 corpus: a learner corpus for Portuguese. iLab-Edinburgh at SemEval-2016 Task 7: A Hybrid Approach for Determining Sentiment Intensity o …
SHEF-Multimodal: Grounding Machine Translation on Images
| Title | SHEF-Multimodal: Grounding Machine Translation on Images |
| Authors | Kashif Shah, Josiah Wang, Lucia Specia |
| Abstract | |
| Tasks | Machine Translation, Multimodal Machine Translation, Question Answering, Video Description |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2363/ |
| https://www.aclweb.org/anthology/W16-2363 | |
| PWC | https://paperswithcode.com/paper/shef-multimodal-grounding-machine-translation |
| Repo | |
| Framework | |
Learning Semantic Relatedness in Community Question Answering Using Neural Models
| Title | Learning Semantic Relatedness in Community Question Answering Using Neural Models |
| Authors | Henry Nassif, Mitra Mohtarami, James Glass |
| Abstract | |
| Tasks | Answer Selection, Community Question Answering, Question Answering, Question Similarity, Representation Learning, Semantic Textual Similarity |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1616/ |
| https://www.aclweb.org/anthology/W16-1616 | |
| PWC | https://paperswithcode.com/paper/learning-semantic-relatedness-in-community |
| Repo | |
| Framework | |
A Search-Based Dynamic Reranking Model for Dependency Parsing
| Title | A Search-Based Dynamic Reranking Model for Dependency Parsing |
| Authors | Hao Zhou, Yue Zhang, Shujian Huang, Junsheng Zhou, Xin-Yu Dai, Jiajun Chen |
| Abstract | |
| Tasks | Dependency Parsing, Transition-Based Dependency Parsing |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1132/ |
| https://www.aclweb.org/anthology/P16-1132 | |
| PWC | https://paperswithcode.com/paper/a-search-based-dynamic-reranking-model-for |
| Repo | |
| Framework | |
The COPLE2 corpus: a learner corpus for Portuguese
| Title | The COPLE2 corpus: a learner corpus for Portuguese |
| Authors | Am{'a}lia Mendes, S Antunes, ra, Maarten Janssen, Anabela Gon{\c{c}}alves |
| Abstract | We present the COPLE2 corpus, a learner corpus of Portuguese that includes written and spoken texts produced by learners of Portuguese as a second or foreign language. The corpus includes at the moment a total of 182,474 tokens and 978 texts, classified according to the CEFR scales. The original handwritten productions are transcribed in TEI compliant XML format and keep record of all the original information, such as reformulations, insertions and corrections made by the teacher, while the recordings are transcribed and aligned with EXMARaLDA. The TEITOK environment enables different views of the same document (XML, student version, corrected version), a CQP-based search interface, the POS, lemmatization and normalization of the tokens, and will soon be used for error annotation in stand-off format. The corpus has already been a source of data for phonological, lexical and syntactic interlanguage studies and will be used for a data-informed selection of language features for each proficiency level. |
| Tasks | Lemmatization |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1511/ |
| https://www.aclweb.org/anthology/L16-1511 | |
| PWC | https://paperswithcode.com/paper/the-cople2-corpus-a-learner-corpus-for |
| Repo | |
| Framework | |
iLab-Edinburgh at SemEval-2016 Task 7: A Hybrid Approach for Determining Sentiment Intensity of Arabic Twitter Phrases
| Title | iLab-Edinburgh at SemEval-2016 Task 7: A Hybrid Approach for Determining Sentiment Intensity of Arabic Twitter Phrases |
| Authors | Eshrag Refaee, Verena Rieser |
| Abstract | |
| Tasks | Dialogue State Tracking, Sentiment Analysis |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1077/ |
| https://www.aclweb.org/anthology/S16-1077 | |
| PWC | https://paperswithcode.com/paper/ilab-edinburgh-at-semeval-2016-task-7-a |
| Repo | |
| Framework | |
Graph Clustering: Block-models and model free results
| Title | Graph Clustering: Block-models and model free results |
| Authors | Yali Wan, Marina Meila |
| Abstract | Clustering graphs under the Stochastic Block Model (SBM) and extensions are well studied. Guarantees of correctness exist under the assumption that the data is sampled from a model. In this paper, we propose a framework, in which we obtain “correctness” guarantees without assuming the data comes from a model. The guarantees we obtain depend instead on the statistics of the data that can be checked. We also show that this framework ties in with the existing model-based framework, and that we can exploit results in model-based recovery, as well as strengthen the results existing in that area of research. |
| Tasks | Graph Clustering |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6140-graph-clustering-block-models-and-model-free-results |
| http://papers.nips.cc/paper/6140-graph-clustering-block-models-and-model-free-results.pdf | |
| PWC | https://paperswithcode.com/paper/graph-clustering-block-models-and-model-free |
| Repo | |
| Framework | |
Training & Quality Assessment of an Optical Character Recognition Model for Northern Haida
| Title | Training & Quality Assessment of an Optical Character Recognition Model for Northern Haida |
| Authors | Isabell Hubert, Antti Arppe, Jordan Lachler, Eddie Antonio Santos |
| Abstract | We are presenting our work on the creation of the first optical character recognition (OCR) model for Northern Haida, also known as Masset or Xaad Kil, a nearly extinct First Nations language spoken in the Haida Gwaii archipelago in British Columbia, Canada. We are addressing the challenges of training an OCR model for a language with an extensive, non-standard Latin character set as follows: (1) We have compared various training approaches and present the results of practical analyses to maximize recognition accuracy and minimize manual labor. An approach using just one or two pages of Source Images directly performed better than the Image Generation approach, and better than models based on three or more pages. Analyses also suggest that a character{'}s frequency is directly correlated with its recognition accuracy. (2) We present an overview of current OCR accuracy analysis tools available. (3) We have ported the once de-facto standardized OCR accuracy tools to be able to cope with Unicode input. Our work adds to a growing body of research on OCR for particularly challenging character sets, and contributes to creating the largest electronic corpus for this severely endangered language. |
| Tasks | Image Generation, Optical Character Recognition |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1514/ |
| https://www.aclweb.org/anthology/L16-1514 | |
| PWC | https://paperswithcode.com/paper/training-quality-assessment-of-an-optical |
| Repo | |
| Framework | |
Adaptive 3D Face Reconstruction From Unconstrained Photo Collections
| Title | Adaptive 3D Face Reconstruction From Unconstrained Photo Collections |
| Authors | Joseph Roth, Yiying Tong, Xiaoming Liu |
| Abstract | Given a collection of “in-the-wild” face images captured under a variety of unknown pose, expression, and illumination conditions, this paper presents a method for reconstructing a 3D face surface model of an individual along with albedo information. Motivated by the success of recent face reconstruction techniques on large photo collections, we extend prior work to adapt to low quality photo collections with fewer images. We achieve this by fitting a 3D Morphable Model to form a personalized template and developing a novel photometric stereo formulation, under a coarse-to-fine scheme. Superior experimental results are reported on synthetic and real-world photo collections. |
| Tasks | 3D Face Reconstruction, Face Reconstruction |
| Published | 2016-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2016/html/Roth_Adaptive_3D_Face_CVPR_2016_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2016/papers/Roth_Adaptive_3D_Face_CVPR_2016_paper.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-3d-face-reconstruction-from |
| Repo | |
| Framework | |
There Is No Logical Negation Here, But There Are Alternatives: Modeling Conversational Negation with Distributional Semantics
| Title | There Is No Logical Negation Here, But There Are Alternatives: Modeling Conversational Negation with Distributional Semantics |
| Authors | Germ{'a}n Kruszewski, Denis Paperno, Raffaella Bernardi, Marco Baroni |
| Abstract | |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/J16-4003/ |
| https://www.aclweb.org/anthology/J16-4003 | |
| PWC | https://paperswithcode.com/paper/there-is-no-logical-negation-here-but-there |
| Repo | |
| Framework | |
Proceedings of the Fourth Workshop on Events
| Title | Proceedings of the Fourth Workshop on Events |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1000/ |
| https://www.aclweb.org/anthology/W16-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-fourth-workshop-on-events |
| Repo | |
| Framework | |
NaCTeM at SemEval-2016 Task 1: Inferring sentence-level semantic similarity from an ensemble of complementary lexical and sentence-level features
| Title | NaCTeM at SemEval-2016 Task 1: Inferring sentence-level semantic similarity from an ensemble of complementary lexical and sentence-level features |
| Authors | Piotr Przyby{\l}a, Nhung T. H. Nguyen, Matthew Shardlow, Georgios Kontonatsios, Sophia Ananiadou |
| Abstract | |
| Tasks | Semantic Similarity, Semantic Textual Similarity, Topic Models |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1093/ |
| https://www.aclweb.org/anthology/S16-1093 | |
| PWC | https://paperswithcode.com/paper/nactem-at-semeval-2016-task-1-inferring |
| Repo | |
| Framework | |
Emotion Analysis on Twitter: The Hidden Challenge
| Title | Emotion Analysis on Twitter: The Hidden Challenge |
| Authors | Luca Dini, Andr{'e} Bittar |
| Abstract | In this paper, we present an experiment to detect emotions in tweets. Unlike much previous research, we draw the important distinction between the tasks of emotion detection in a closed world assumption (i.e. every tweet is emotional) and the complicated task of identifying emotional versus non-emotional tweets. Given an apparent lack of appropriately annotated data, we created two corpora for these tasks. We describe two systems, one symbolic and one based on machine learning, which we evaluated on our datasets. Our evaluation shows that a machine learning classifier performs best on emotion detection, while a symbolic approach is better for identifying relevant (i.e. emotional) tweets. |
| Tasks | Emotion Recognition |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1624/ |
| https://www.aclweb.org/anthology/L16-1624 | |
| PWC | https://paperswithcode.com/paper/emotion-analysis-on-twitter-the-hidden |
| Repo | |
| Framework | |
From Noisy Questions to Minecraft Texts: Annotation Challenges in Extreme Syntax Scenario
| Title | From Noisy Questions to Minecraft Texts: Annotation Challenges in Extreme Syntax Scenario |
| Authors | H{'e}ctor Mart{'\i}nez Alonso, Djam{'e} Seddah, Beno{^\i}t Sagot |
| Abstract | User-generated content presents many challenges for its automatic processing. While many of them do come from out-of-vocabulary effects, others spawn from different linguistic phenomena such as unusual syntax. In this work we present a French three-domain data set made up of question headlines from a cooking forum, game chat logs and associated forums from two popular online games (MINECRAFT {&} LEAGUE OF LEGENDS). We chose these domains because they encompass different degrees of lexical and syntactic compliance with canonical language. We conduct an automatic and manual evaluation of the difficulties of processing these domains for part-of-speech prediction, and introduce a pilot study to determine whether dependency analysis lends itself well to annotate these data. We also discuss the development cost of our data set. |
| Tasks | League of Legends |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-3905/ |
| https://www.aclweb.org/anthology/W16-3905 | |
| PWC | https://paperswithcode.com/paper/from-noisy-questions-to-minecraft-texts |
| Repo | |
| Framework | |
Bridge-Language Capitalization Inference in Western Iranian: Sorani, Kurmanji, Zazaki, and Tajik
| Title | Bridge-Language Capitalization Inference in Western Iranian: Sorani, Kurmanji, Zazaki, and Tajik |
| Authors | Patrick Littell, David R. Mortensen, Kartik Goyal, Chris Dyer, Lori Levin |
| Abstract | In Sorani Kurdish, one of the most useful orthographic features in named-entity recognition {–} capitalization {–} is absent, as the language{'}s Perso-Arabic script does not make a distinction between uppercase and lowercase letters. We describe a system for deriving an inferred capitalization value from closely related languages by phonological similarity, and illustrate the system using several related Western Iranian languages. |
| Tasks | Named Entity Recognition |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1529/ |
| https://www.aclweb.org/anthology/L16-1529 | |
| PWC | https://paperswithcode.com/paper/bridge-language-capitalization-inference-in |
| Repo | |
| Framework | |
Modelling the ziji Blocking Effect and Constraining Bound Variable Derivations in MC-TAG with Delayed Locality
| Title | Modelling the ziji Blocking Effect and Constraining Bound Variable Derivations in MC-TAG with Delayed Locality |
| Authors | Dennis Ryan Storoshenko |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-3307/ |
| https://www.aclweb.org/anthology/W16-3307 | |
| PWC | https://paperswithcode.com/paper/modelling-the-ziji-blocking-effect-and |
| Repo | |
| Framework | |
