Paper Group NANR 177
plWordNet 3.0 – a Comprehensive Lexical-Semantic Resource. MediaGist: A Cross-lingual Analyser of Aggregated News and Commentaries. UMD-TTIC-UW at SemEval-2016 Task 1: Attention-Based Multi-Perspective Convolutional Neural Networks for Textual Similarity Measurement. Empirical Determination of Basic Heuristics for Narrative Content Planning. Proce …
plWordNet 3.0 – a Comprehensive Lexical-Semantic Resource
| Title | plWordNet 3.0 – a Comprehensive Lexical-Semantic Resource |
| Authors | Marek Maziarz, Maciej Piasecki, Ewa Rudnicka, Stan Szpakowicz, Pawe{\l} K{\k{e}}dzia |
| Abstract | We have released plWordNet 3.0, a very large wordnet for Polish. In addition to what is expected in wordnets {–} richly interrelated synsets {–} it contains sentiment and emotion annotations, a large set of multi-word expressions, and a mapping onto WordNet 3.1. Part of the release is enWordNet 1.0, a substantially enlarged copy of WordNet 3.1, with material added to allow for a more complete mapping. The paper discusses the design principles of plWordNet, its content, its statistical portrait, a comparison with similar resources, and a partial list of applications. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1213/ |
| https://www.aclweb.org/anthology/C16-1213 | |
| PWC | https://paperswithcode.com/paper/plwordnet-30-a-a-comprehensive-lexical |
| Repo | |
| Framework | |
MediaGist: A Cross-lingual Analyser of Aggregated News and Commentaries
| Title | MediaGist: A Cross-lingual Analyser of Aggregated News and Commentaries |
| Authors | Josef Steinberger |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-4025/ |
| https://www.aclweb.org/anthology/P16-4025 | |
| PWC | https://paperswithcode.com/paper/mediagist-a-cross-lingual-analyser-of |
| Repo | |
| Framework | |
UMD-TTIC-UW at SemEval-2016 Task 1: Attention-Based Multi-Perspective Convolutional Neural Networks for Textual Similarity Measurement
| Title | UMD-TTIC-UW at SemEval-2016 Task 1: Attention-Based Multi-Perspective Convolutional Neural Networks for Textual Similarity Measurement |
| Authors | Hua He, John Wieting, Kevin Gimpel, Jinfeng Rao, Jimmy Lin |
| Abstract | |
| Tasks | Feature Engineering, Question Answering, Semantic Textual Similarity, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1170/ |
| https://www.aclweb.org/anthology/S16-1170 | |
| PWC | https://paperswithcode.com/paper/umd-ttic-uw-at-semeval-2016-task-1-attention |
| Repo | |
| Framework | |
Empirical Determination of Basic Heuristics for Narrative Content Planning
| Title | Empirical Determination of Basic Heuristics for Narrative Content Planning |
| Authors | Pablo Gerv{'a}s |
| Abstract | |
| Tasks | Text Generation |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-5503/ |
| https://www.aclweb.org/anthology/W16-5503 | |
| PWC | https://paperswithcode.com/paper/empirical-determination-of-basic-heuristics |
| Repo | |
| Framework | |
Proceedings of the 2nd International Workshop on Natural Language Generation and the Semantic Web (WebNLG 2016)
| Title | Proceedings of the 2nd International Workshop on Natural Language Generation and the Semantic Web (WebNLG 2016) |
| Authors | |
| Abstract | |
| Tasks | Text Generation |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-3500/ |
| https://www.aclweb.org/anthology/W16-3500 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2nd-international-workshop |
| Repo | |
| Framework | |
Learning User Perceived Clusters with Feature-Level Supervision
| Title | Learning User Perceived Clusters with Feature-Level Supervision |
| Authors | Ting-Yu Cheng, Guiguan Lin, Xinyang Gong, Kang-Jun Liu, Shan-Hung Wu |
| Abstract | Semi-supervised clustering algorithms have been proposed to identify data clusters that align with user perceived ones via the aid of side information such as seeds or pairwise constrains. However, traditional side information is mostly at the instance level and subject to the sampling bias, where non-randomly sampled instances in the supervision can mislead the algorithms to wrong clusters. In this paper, we propose learning from the feature-level supervision. We show that this kind of supervision can be easily obtained in the form of perception vectors in many applications. Then we present novel algorithms, called Perception Embedded (PE) clustering, that exploit the perception vectors as well as traditional side information to find clusters perceived by the user. Extensive experiments are conducted on real datasets and the results demonstrate the effectiveness of PE empirically. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6260-learning-user-perceived-clusters-with-feature-level-supervision |
| http://papers.nips.cc/paper/6260-learning-user-perceived-clusters-with-feature-level-supervision.pdf | |
| PWC | https://paperswithcode.com/paper/learning-user-perceived-clusters-with-feature |
| Repo | |
| Framework | |
Convex Two-Layer Modeling with Latent Structure
| Title | Convex Two-Layer Modeling with Latent Structure |
| Authors | Vignesh Ganapathiraman, Xinhua Zhang, Yaoliang Yu, Junfeng Wen |
| Abstract | Unsupervised learning of structured predictors has been a long standing pursuit in machine learning. Recently a conditional random field auto-encoder has been proposed in a two-layer setting, allowing latent structured representation to be automatically inferred. Aside from being nonconvex, it also requires the demanding inference of normalization. In this paper, we develop a convex relaxation of two-layer conditional model which captures latent structure and estimates model parameters, jointly and optimally. We further expand its applicability by resorting to a weaker form of inference—maximum a-posteriori. The flexibility of the model is demonstrated on two structures based on total unimodularity—graph matching and linear chain. Experimental results confirm the promise of the method. |
| Tasks | Graph Matching |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6314-convex-two-layer-modeling-with-latent-structure |
| http://papers.nips.cc/paper/6314-convex-two-layer-modeling-with-latent-structure.pdf | |
| PWC | https://paperswithcode.com/paper/convex-two-layer-modeling-with-latent |
| Repo | |
| Framework | |
A Neural Network Architecture for Multilingual Punctuation Generation
| Title | A Neural Network Architecture for Multilingual Punctuation Generation |
| Authors | Miguel Ballesteros, Leo Wanner |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1111/ |
| https://www.aclweb.org/anthology/D16-1111 | |
| PWC | https://paperswithcode.com/paper/a-neural-network-architecture-for |
| Repo | |
| Framework | |
The SI TEDx-UM speech database: a new Slovenian Spoken Language Resource
| Title | The SI TEDx-UM speech database: a new Slovenian Spoken Language Resource |
| Authors | Andrej {\v{Z}}gank, Mirjam Sepesy Mau{\v{c}}ec, Darinka Verdonik |
| Abstract | This paper presents a new Slovenian spoken language resource built from TEDx Talks. The speech database contains 242 talks in total duration of 54 hours. The annotation and transcription of acquired spoken material was generated automatically, applying acoustic segmentation and automatic speech recognition. The development and evaluation subset was also manually transcribed using the guidelines specified for the Slovenian GOS corpus. The manual transcriptions were used to evaluate the quality of unsupervised transcriptions. The average word error rate for the SI TEDx-UM evaluation subset was 50.7{%}, with out of vocabulary rate of 24{%} and language model perplexity of 390. The unsupervised transcriptions contain 372k tokens, where 32k of them were different. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1740/ |
| https://www.aclweb.org/anthology/L16-1740 | |
| PWC | https://paperswithcode.com/paper/the-si-tedx-um-speech-database-a-new |
| Repo | |
| Framework | |
Generation from Abstract Meaning Representation using Tree Transducers
| Title | Generation from Abstract Meaning Representation using Tree Transducers |
| Authors | Jeffrey Flanigan, Chris Dyer, Noah A. Smith, Jaime Carbonell |
| Abstract | |
| Tasks | Language Modelling, Machine Translation, Text Generation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1087/ |
| https://www.aclweb.org/anthology/N16-1087 | |
| PWC | https://paperswithcode.com/paper/generation-from-abstract-meaning |
| Repo | |
| Framework | |
Process Based Evaluation of Computer Generated Poetry
| Title | Process Based Evaluation of Computer Generated Poetry |
| Authors | Stephen McGregor, Matthew Purver, Geraint Wiggins |
| Abstract | |
| Tasks | Text Generation |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-5508/ |
| https://www.aclweb.org/anthology/W16-5508 | |
| PWC | https://paperswithcode.com/paper/process-based-evaluation-of-computer |
| Repo | |
| Framework | |
Identifying Teacher Questions Using Automatic Speech Recognition in Classrooms
| Title | Identifying Teacher Questions Using Automatic Speech Recognition in Classrooms |
| Authors | Nathaniel Blanchard, Patrick Donnelly, Andrew M. Olney, Samei Borhan, Brooke Ward, Xiaoyi Sun, Sean Kelly, Martin Nystrand, Sidney K. D’Mello |
| Abstract | |
| Tasks | Speech Recognition |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/papers/W16-3623/w16-3623 |
| https://www.aclweb.org/anthology/W16-3623 | |
| PWC | https://paperswithcode.com/paper/identifying-teacher-questions-using-automatic |
| Repo | |
| Framework | |
International Journal of Computational Linguistics & Chinese Language Processing, Volume 21, Number 2, December 2016
| Title | International Journal of Computational Linguistics & Chinese Language Processing, Volume 21, Number 2, December 2016 |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/O16-3000/ |
| https://www.aclweb.org/anthology/O16-3000 | |
| PWC | https://paperswithcode.com/paper/international-journal-of-computational-3 |
| Repo | |
| Framework | |
Syllable based DNN-HMM Cantonese Speech to Text System
| Title | Syllable based DNN-HMM Cantonese Speech to Text System |
| Authors | Timothy Wong, Claire Li, Sam Lam, Billy Chiu, Qin Lu, Minglei Li, Dan Xiong, Roy Shing Yu, Vincent T.Y. Ng |
| Abstract | This paper reports our work on building up a Cantonese Speech-to-Text (STT) system with a syllable based acoustic model. This is a part of an effort in building a STT system to aid dyslexic students who have cognitive deficiency in writing skills but have no problem expressing their ideas through speech. For Cantonese speech recognition, the basic unit of acoustic models can either be the conventional Initial-Final (IF) syllables, or the Onset-Nucleus-Coda (ONC) syllables where finals are further split into nucleus and coda to reflect the intra-syllable variations in Cantonese. By using the Kaldi toolkit, our system is trained using the stochastic gradient descent optimization model with the aid of GPUs for the hybrid Deep Neural Network and Hidden Markov Model (DNN-HMM) with and without I-vector based speaker adaptive training technique. The input features of the same Gaussian Mixture Model with speaker adaptive training (GMM-SAT) to DNN are used in all cases. Experiments show that the ONC-based syllable acoustic modeling with I-vector based DNN-HMM achieves the best performance with the word error rate (WER) of 9.66{%} and the real time factor (RTF) of 1.38812. |
| Tasks | Speech Recognition |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1610/ |
| https://www.aclweb.org/anthology/L16-1610 | |
| PWC | https://paperswithcode.com/paper/syllable-based-dnn-hmm-cantonese-speech-to |
| Repo | |
| Framework | |
TextPro-AL: An Active Learning Platform for Flexible and Efficient Production of Training Data for NLP Tasks
| Title | TextPro-AL: An Active Learning Platform for Flexible and Efficient Production of Training Data for NLP Tasks |
| Authors | Bernardo Magnini, Anne-Lyse Minard, Mohammed R. H. Qwaider, Manuela Speranza |
| Abstract | This paper presents TextPro-AL (Active Learning for Text Processing), a platform where human annotators can efficiently work to produce high quality training data for new domains and new languages exploiting Active Learning methodologies. TextPro-AL is a web-based application integrating four components: a machine learning based NLP pipeline, an annotation editor for task definition and text annotations, an incremental re-training procedure based on active learning selection from a large pool of unannotated data, and a graphical visualization of the learning status of the system. |
| Tasks | Active Learning, Domain Adaptation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2028/ |
| https://www.aclweb.org/anthology/C16-2028 | |
| PWC | https://paperswithcode.com/paper/textpro-al-an-active-learning-platform-for |
| Repo | |
| Framework | |
