Paper Group NANR 170
Corpus vs. Lexicon Supervision in Morphosyntactic Tagging: the Case of Slovene. Detection of Reformulations in Spoken French. Fostering digital representation of EU regional and minority languages: the Digital Language Diversity Project. Deep ADMM-Net for Compressive Sensing MRI. Multimodal Semantic Learning from Child-Directed Input. The Sensitivi …
Corpus vs. Lexicon Supervision in Morphosyntactic Tagging: the Case of Slovene
| Title | Corpus vs. Lexicon Supervision in Morphosyntactic Tagging: the Case of Slovene |
| Authors | Nikola Ljube{\v{s}}i{'c}, Toma{\v{z}} Erjavec |
| Abstract | In this paper we present a tagger developed for inflectionally rich languages for which both a training corpus and a lexicon are available. We do not constrain the tagger by the lexicon entries, allowing both for lexicon incompleteness and noisiness. By using the lexicon indirectly through features we allow for known and unknown words to be tagged in the same manner. We test our tagger on Slovene data, obtaining a 25{%} error reduction of the best previous results both on known and unknown words. Given that Slovene is, in comparison to some other Slavic languages, a well-resourced language, we perform experiments on the impact of token (corpus) vs. type (lexicon) supervision, obtaining useful insights in how to balance the effort of extending resources to yield better tagging results. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1242/ |
| https://www.aclweb.org/anthology/L16-1242 | |
| PWC | https://paperswithcode.com/paper/corpus-vs-lexicon-supervision-in |
| Repo | |
| Framework | |
Detection of Reformulations in Spoken French
| Title | Detection of Reformulations in Spoken French |
| Authors | Natalia Grabar, Iris Eshkol-Taravela |
| Abstract | Our work addresses automatic detection of enunciations and segments with reformulations in French spoken corpora. The proposed approach is syntagmatic. It is based on reformulation markers and specificities of spoken language. The reference data are built manually and have gone through consensus. Automatic methods, based on rules and CRF machine learning, are proposed in order to detect the enunciations and segments that contain reformulations. With the CRF models, different features are exploited within a window of various sizes. Detection of enunciations with reformulations shows up to 0.66 precision. The tests performed for the detection of reformulated segments indicate that the task remains difficult. The best average performance values reach up to 0.65 F-measure, 0.75 precision, and 0.63 recall. We have several perspectives to this work for improving the detection of reformulated segments and for studying the data from other points of view. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1596/ |
| https://www.aclweb.org/anthology/L16-1596 | |
| PWC | https://paperswithcode.com/paper/detection-of-reformulations-in-spoken-french |
| Repo | |
| Framework | |
Fostering digital representation of EU regional and minority languages: the Digital Language Diversity Project
| Title | Fostering digital representation of EU regional and minority languages: the Digital Language Diversity Project |
| Authors | Claudia Soria, Irene Russo, Valeria Quochi, Davyth Hicks, Antton Gurrutxaga, Anneli Sarhimaa, Matti Tuomisto |
| Abstract | Poor digital representation of minority languages further prevents their usability on digital media and devices. The Digital Language Diversity Project, a three-year project funded under the Erasmus+ programme, aims at addressing the problem of low digital representation of EU regional and minority languages by giving their speakers the intellectual an practical skills to create, share, and reuse online digital content. Availability of digital content and technical support to use it are essential prerequisites for the development of language-based digital applications, which in turn can boost digital usage of these languages. In this paper we introduce the project, its aims, objectives and current activities for sustaining digital usability of minority languages through adult education. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1518/ |
| https://www.aclweb.org/anthology/L16-1518 | |
| PWC | https://paperswithcode.com/paper/fostering-digital-representation-of-eu |
| Repo | |
| Framework | |
Deep ADMM-Net for Compressive Sensing MRI
| Title | Deep ADMM-Net for Compressive Sensing MRI |
| Authors | Yan Yang, Jian Sun, Huibin Li, Zongben Xu |
| Abstract | Compressive Sensing (CS) is an effective approach for fast Magnetic Resonance Imaging (MRI). It aims at reconstructing MR image from a small number of under-sampled data in k-space, and accelerating the data acquisition in MRI. To improve the current MRI system in reconstruction accuracy and computational speed, in this paper, we propose a novel deep architecture, dubbed ADMM-Net. ADMM-Net is defined over a data flow graph, which is derived from the iterative procedures in Alternating Direction Method of Multipliers (ADMM) algorithm for optimizing a CS-based MRI model. In the training phase, all parameters of the net, e.g., image transforms, shrinkage functions, etc., are discriminatively trained end-to-end using L-BFGS algorithm. In the testing phase, it has computational overhead similar to ADMM but uses optimized parameters learned from the training data for CS-based reconstruction task. Experiments on MRI image reconstruction under different sampling ratios in k-space demonstrate that it significantly improves the baseline ADMM algorithm and achieves high reconstruction accuracies with fast computational speed. |
| Tasks | Compressive Sensing, Image Reconstruction |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6406-deep-admm-net-for-compressive-sensing-mri |
| http://papers.nips.cc/paper/6406-deep-admm-net-for-compressive-sensing-mri.pdf | |
| PWC | https://paperswithcode.com/paper/deep-admm-net-for-compressive-sensing-mri |
| Repo | |
| Framework | |
Multimodal Semantic Learning from Child-Directed Input
| Title | Multimodal Semantic Learning from Child-Directed Input |
| Authors | Angeliki Lazaridou, Grzegorz Chrupa{\l}a, Raquel Fern{'a}ndez, Marco Baroni |
| Abstract | |
| Tasks | Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1043/ |
| https://www.aclweb.org/anthology/N16-1043 | |
| PWC | https://paperswithcode.com/paper/multimodal-semantic-learning-from-child |
| Repo | |
| Framework | |
The Sensitivity of Topic Coherence Evaluation to Topic Cardinality
| Title | The Sensitivity of Topic Coherence Evaluation to Topic Cardinality |
| Authors | Jey Han Lau, Timothy Baldwin |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1057/ |
| https://www.aclweb.org/anthology/N16-1057 | |
| PWC | https://paperswithcode.com/paper/the-sensitivity-of-topic-coherence-evaluation |
| Repo | |
| Framework | |
Predictive Incremental Parsing Helps Language Modeling
| Title | Predictive Incremental Parsing Helps Language Modeling |
| Authors | Arne K{"o}hn, Timo Baumann |
| Abstract | Predictive incremental parsing produces syntactic representations of sentences as they are produced, e.g. by typing or speaking. In order to generate connected parses for such unfinished sentences, upcoming word types can be hypothesized and structurally integrated with already realized words. For example, the presence of a determiner as the last word of a sentence prefix may indicate that a noun will appear somewhere in the completion of that sentence, and the determiner can be attached to the predicted noun. We combine the forward-looking parser predictions with backward-looking N-gram histories and analyze in a set of experiments the impact on language models, i.e. stronger discriminative power but also higher data sparsity. Conditioning N-gram models, MaxEnt models or RNN-LMs on parser predictions yields perplexity reductions of about 6{%}. Our method (a) retains online decoding capabilities and (b) incurs relatively little computational overhead which sets it apart from previous approaches that use syntax for language modeling. Our method is particularly attractive for modular systems that make use of a syntax parser anyway, e.g. as part of an understanding pipeline where predictive parsing improves language modeling at no additional cost. |
| Tasks | Language Modelling |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1026/ |
| https://www.aclweb.org/anthology/C16-1026 | |
| PWC | https://paperswithcode.com/paper/predictive-incremental-parsing-helps-language |
| Repo | |
| Framework | |
PRIMT: A Pick-Revise Framework for Interactive Machine Translation
| Title | PRIMT: A Pick-Revise Framework for Interactive Machine Translation |
| Authors | Shanbo Cheng, Shujian Huang, Huadong Chen, Xin-Yu Dai, Jiajun Chen |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1148/ |
| https://www.aclweb.org/anthology/N16-1148 | |
| PWC | https://paperswithcode.com/paper/primt-a-pick-revise-framework-for-interactive |
| Repo | |
| Framework | |
SoNLP-DP System for ConLL-2016 English Shallow Discourse Parsing
| Title | SoNLP-DP System for ConLL-2016 English Shallow Discourse Parsing |
| Authors | Fang Kong, Sheng Li, Junhui Li, Muhua Zhu, Guodong Zhou |
| Abstract | |
| Tasks | Machine Translation, Text Summarization |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/K16-2009/ |
| https://www.aclweb.org/anthology/K16-2009 | |
| PWC | https://paperswithcode.com/paper/sonlp-dp-system-for-conll-2016-english |
| Repo | |
| Framework | |
Clustering Paraphrases by Word Sense
| Title | Clustering Paraphrases by Word Sense |
| Authors | Anne Cocos, Chris Callison-Burch |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1172/ |
| https://www.aclweb.org/anthology/N16-1172 | |
| PWC | https://paperswithcode.com/paper/clustering-paraphrases-by-word-sense |
| Repo | |
| Framework | |
An End-to-end Approach to Learning Semantic Frames with Feedforward Neural Network
| Title | An End-to-end Approach to Learning Semantic Frames with Feedforward Neural Network |
| Authors | Yukun Feng, Yipei Xu, Dong Yu |
| Abstract | |
| Tasks | Dependency Parsing, Machine Translation, Part-Of-Speech Tagging, Question Answering |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-2001/ |
| https://www.aclweb.org/anthology/N16-2001 | |
| PWC | https://paperswithcode.com/paper/an-end-to-end-approach-to-learning-semantic |
| Repo | |
| Framework | |
Text-based experiments for Predicting mental health emergencies in online web forum posts
| Title | Text-based experiments for Predicting mental health emergencies in online web forum posts |
| Authors | Hector-Hugo Franco-Penya, Liliana Mamani Sanchez |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0327/ |
| https://www.aclweb.org/anthology/W16-0327 | |
| PWC | https://paperswithcode.com/paper/text-based-experiments-for-predicting-mental |
| Repo | |
| Framework | |
Proceedings of the Workshop on Human-Computer Question Answering
| Title | Proceedings of the Workshop on Human-Computer Question Answering |
| Authors | |
| Abstract | |
| Tasks | Question Answering |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0100/ |
| https://www.aclweb.org/anthology/W16-0100 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-workshop-on-human-computer |
| Repo | |
| Framework | |
Evaluating vector space models using human semantic priming results
| Title | Evaluating vector space models using human semantic priming results |
| Authors | Allyson Ettinger, Tal Linzen |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2513/ |
| https://www.aclweb.org/anthology/W16-2513 | |
| PWC | https://paperswithcode.com/paper/evaluating-vector-space-models-using-human |
| Repo | |
| Framework | |
HMC at SemEval-2016 Task 11: Identifying Complex Words Using Depth-limited Decision Trees
| Title | HMC at SemEval-2016 Task 11: Identifying Complex Words Using Depth-limited Decision Trees |
| Authors | Maury Quijada, Julie Medero |
| Abstract | |
| Tasks | Complex Word Identification, Lexical Simplification, Text Simplification |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1161/ |
| https://www.aclweb.org/anthology/S16-1161 | |
| PWC | https://paperswithcode.com/paper/hmc-at-semeval-2016-task-11-identifying |
| Repo | |
| Framework | |
