Paper Group NANR 124
Finite-Dimensional BFRY Priors and Variational Bayesian Inference for Power Law Models. 1 Million Captioned Dutch Newspaper Images. ECNU at SemEval-2016 Task 1: Leveraging Word Embedding From Macro and Micro Views to Boost Performance for Semantic Textual Similarity. IISCNLP at SemEval-2016 Task 2: Interpretable STS with ILP based Multiple Chunk Al …
Finite-Dimensional BFRY Priors and Variational Bayesian Inference for Power Law Models
| Title | Finite-Dimensional BFRY Priors and Variational Bayesian Inference for Power Law Models |
| Authors | Juho Lee, Lancelot F. James, Seungjin Choi |
| Abstract | Bayesian nonparametric methods based on the Dirichlet process (DP), gamma process and beta process, have proven effective in capturing aspects of various datasets arising in machine learning. However, it is now recognized that such processes have their limitations in terms of the ability to capture power law behavior. As such there is now considerable interest in models based on the Stable Processs (SP), Generalized Gamma process (GGP) and Stable-beta process (SBP). These models present new challenges in terms of practical statistical implementation. In analogy to tractable processes such as the finite-dimensional Dirichlet process, we describe a class of random processes, we call iid finite-dimensional BFRY processes, that enables one to begin to develop efficient posterior inference algorithms such as variational Bayes that readily scale to massive datasets. For illustrative purposes, we describe a simple variational Bayes algorithm for normalized SP mixture models, and demonstrate its usefulness with experiments on synthetic and real-world datasets. |
| Tasks | Bayesian Inference |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6348-finite-dimensional-bfry-priors-and-variational-bayesian-inference-for-power-law-models |
| http://papers.nips.cc/paper/6348-finite-dimensional-bfry-priors-and-variational-bayesian-inference-for-power-law-models.pdf | |
| PWC | https://paperswithcode.com/paper/finite-dimensional-bfry-priors-and |
| Repo | |
| Framework | |
1 Million Captioned Dutch Newspaper Images
| Title | 1 Million Captioned Dutch Newspaper Images |
| Authors | Desmond Elliott, Martijn Kleppe |
| Abstract | Images naturally appear alongside text in a wide variety of media, such as books, magazines, newspapers, and in online articles. This type of multi-modal data offers an interesting basis for vision and language research but most existing datasets use crowdsourced text, which removes the images from their original context. In this paper, we introduce the KBK-1M dataset of 1.6 million images in their original context, with co-occurring texts found in Dutch newspapers from 1922 - 1994. The images are digitally scanned photographs, cartoons, sketches, and weather forecasts; the text is generated from OCR scanned blocks. The dataset is suitable for experiments in automatic image captioning, image―article matching, object recognition, and data-to-text generation for weather forecasting. It can also be used by humanities scholars to analyse photographic style changes, the representation of people and societal issues, and new tools for exploring photograph reuse via image-similarity-based search. |
| Tasks | Data-to-Text Generation, Image Captioning, Object Recognition, Optical Character Recognition, Text Generation, Weather Forecasting |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1488/ |
| https://www.aclweb.org/anthology/L16-1488 | |
| PWC | https://paperswithcode.com/paper/1-million-captioned-dutch-newspaper-images |
| Repo | |
| Framework | |
ECNU at SemEval-2016 Task 1: Leveraging Word Embedding From Macro and Micro Views to Boost Performance for Semantic Textual Similarity
| Title | ECNU at SemEval-2016 Task 1: Leveraging Word Embedding From Macro and Micro Views to Boost Performance for Semantic Textual Similarity |
| Authors | Junfeng Tian, Man Lan |
| Abstract | |
| Tasks | Feature Engineering, Machine Translation, Natural Language Inference, Question Answering, Semantic Textual Similarity, Text Summarization, Word Alignment |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1094/ |
| https://www.aclweb.org/anthology/S16-1094 | |
| PWC | https://paperswithcode.com/paper/ecnu-at-semeval-2016-task-1-leveraging-word |
| Repo | |
| Framework | |
IISCNLP at SemEval-2016 Task 2: Interpretable STS with ILP based Multiple Chunk Aligner
| Title | IISCNLP at SemEval-2016 Task 2: Interpretable STS with ILP based Multiple Chunk Aligner |
| Authors | Lavanya Tekumalla, Sharmistha Jat |
| Abstract | |
| Tasks | Information Retrieval, Question Answering, Semantic Textual Similarity, Word Alignment |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1122/ |
| https://www.aclweb.org/anthology/S16-1122 | |
| PWC | https://paperswithcode.com/paper/iiscnlp-at-semeval-2016-task-2-interpretable |
| Repo | |
| Framework | |
NICT-2 Translation System for WAT2016: Applying Domain Adaptation to Phrase-based Statistical Machine Translation
| Title | NICT-2 Translation System for WAT2016: Applying Domain Adaptation to Phrase-based Statistical Machine Translation |
| Authors | Kenji Imamura, Eiichiro Sumita |
| Abstract | This paper describes the NICT-2 translation system for the 3rd Workshop on Asian Translation. The proposed system employs a domain adaptation method based on feature augmentation. We regarded the Japan Patent Office Corpus as a mixture of four domain corpora and improved the translation quality of each domain. In addition, we incorporated language models constructed from Google n-grams as external knowledge. Our domain adaptation method can naturally incorporate such external knowledge that contributes to translation quality. |
| Tasks | Domain Adaptation, Machine Translation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4611/ |
| https://www.aclweb.org/anthology/W16-4611 | |
| PWC | https://paperswithcode.com/paper/nict-2-translation-system-for-wat2016 |
| Repo | |
| Framework | |
Introducing the SEA_AP: an Enhanced Tool for Automatic Prosodic Analysis
| Title | Introducing the SEA_AP: an Enhanced Tool for Automatic Prosodic Analysis |
| Authors | Marta Mart{'\i}nez, Roc{'\i}o Varela, Carmen Garc{'\i}a Mateo, Elisa Fern{'a}ndez Rei, Adela Mart{'\i}nez Calvo |
| Abstract | SEA{_}AP (Segmentador e Etiquetador Autom{'a}tico para An{'a}lise Pros{'o}dica, Automatic Segmentation and Labelling for Prosodic Analysis) toolkit is an application that performs audio segmentation and labelling to create a TextGrid file which will be used to launch a prosodic analysis using Praat. In this paper, we want to describe the improved functionality of the tool achieved by adding a dialectometric analysis module using R scripts. The dialectometric analysis includes computing correlations among F0 curves and it obtains prosodic distances among the different variables of interest (location, speaker, structure, etc.). The dialectometric analysis requires large databases in order to be adequately computed, and automatic segmentation and labelling can create them thanks to a procedure less costly than the manual alternative. Thus, the integration of these tools into the SEA{_}AP allows to propose a distribution of geoprosodic areas by means of a quantitative method, which completes the traditional dialectological point of view. The current version of the SEA{_}AP toolkit is capable of analysing Galician, Spanish and Brazilian Portuguese data, and hence the distances between several prosodic linguistic varieties can be measured at present. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1311/ |
| https://www.aclweb.org/anthology/L16-1311 | |
| PWC | https://paperswithcode.com/paper/introducing-the-sea_ap-an-enhanced-tool-for |
| Repo | |
| Framework | |
Document-level Sentiment Inference with Social, Faction, and Discourse Context
| Title | Document-level Sentiment Inference with Social, Faction, and Discourse Context |
| Authors | Eunsol Choi, Hannah Rashkin, Luke Zettlemoyer, Yejin Choi |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1032/ |
| https://www.aclweb.org/anthology/P16-1032 | |
| PWC | https://paperswithcode.com/paper/document-level-sentiment-inference-with |
| Repo | |
| Framework | |
Combining Natural Logic and Shallow Reasoning for Question Answering
| Title | Combining Natural Logic and Shallow Reasoning for Question Answering |
| Authors | Gabor Angeli, Neha Nayak, Christopher D. Manning |
| Abstract | |
| Tasks | Natural Language Inference, Question Answering |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1042/ |
| https://www.aclweb.org/anthology/P16-1042 | |
| PWC | https://paperswithcode.com/paper/combining-natural-logic-and-shallow-reasoning |
| Repo | |
| Framework | |
Cross-genre Event Extraction with Knowledge Enrichment
| Title | Cross-genre Event Extraction with Knowledge Enrichment |
| Authors | Hao Li, Heng Ji |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1137/ |
| https://www.aclweb.org/anthology/N16-1137 | |
| PWC | https://paperswithcode.com/paper/cross-genre-event-extraction-with-knowledge |
| Repo | |
| Framework | |
SemEval-2016 Task 7: Determining Sentiment Intensity of English and Arabic Phrases
| Title | SemEval-2016 Task 7: Determining Sentiment Intensity of English and Arabic Phrases |
| Authors | Svetlana Kiritchenko, Saif Mohammad, Mohammad Salameh |
| Abstract | |
| Tasks | Sentiment Analysis, Stance Detection |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1004/ |
| https://www.aclweb.org/anthology/S16-1004 | |
| PWC | https://paperswithcode.com/paper/semeval-2016-task-7-determining-sentiment |
| Repo | |
| Framework | |
Improving Zero-Shot-Learning for German Particle Verbs by using Training-Space Restrictions and Local Scaling
| Title | Improving Zero-Shot-Learning for German Particle Verbs by using Training-Space Restrictions and Local Scaling |
| Authors | Maximilian K{"o}per, Sabine Schulte im Walde, Max Kisselew, Sebastian Pad{'o} |
| Abstract | |
| Tasks | Zero-Shot Learning |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/S16-2010/ |
| https://www.aclweb.org/anthology/S16-2010 | |
| PWC | https://paperswithcode.com/paper/improving-zero-shot-learning-for-german |
| Repo | |
| Framework | |
Building RDF Content for Data-to-Text Generation
| Title | Building RDF Content for Data-to-Text Generation |
| Authors | Laura Perez-Beltrachini, Rania Sayed, Claire Gardent |
| Abstract | In Natural Language Generation (NLG), one important limitation is the lack of common benchmarks on which to train, evaluate and compare data-to-text generators. In this paper, we make one step in that direction and introduce a method for automatically creating an arbitrary large repertoire of data units that could serve as input for generation. Using both automated metrics and a human evaluation, we show that the data units produced by our method are both diverse and coherent. |
| Tasks | Data-to-Text Generation, Text Generation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1141/ |
| https://www.aclweb.org/anthology/C16-1141 | |
| PWC | https://paperswithcode.com/paper/building-rdf-content-for-data-to-text |
| Repo | |
| Framework | |
Modeling verbal inflection for English to German SMT
| Title | Modeling verbal inflection for English to German SMT |
| Authors | Anita Ramm, Alex Fraser, er |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2203/ |
| https://www.aclweb.org/anthology/W16-2203 | |
| PWC | https://paperswithcode.com/paper/modeling-verbal-inflection-for-english-to |
| Repo | |
| Framework | |
Riddle Generation using Word Associations
| Title | Riddle Generation using Word Associations |
| Authors | Paloma Galv{'a}n, Virginia Francisco, Raquel Herv{'a}s, Gonzalo M{'e}ndez |
| Abstract | In knowledge bases where concepts have associated properties, there is a large amount of comparative information that is implicitly encoded in the values of the properties these concepts share. Although there have been previous approaches to generating riddles, none of them seem to take advantage of structured information stored in knowledge bases such as Thesaurus Rex, which organizes concepts according to the fine grained ad-hoc categories they are placed into by speakers in everyday language, along with associated properties or modifiers. Taking advantage of these shared properties, we have developed a riddle generator that creates riddles about concepts represented as common nouns. The base of these riddles are comparisons between the target concept and other entities that share some of its properties. In this paper, we describe the process we have followed to generate the riddles starting from the target concept and we show the results of the first evaluation we have carried out to test the quality of the resulting riddles. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1381/ |
| https://www.aclweb.org/anthology/L16-1381 | |
| PWC | https://paperswithcode.com/paper/riddle-generation-using-word-associations |
| Repo | |
| Framework | |
Integrating Selectional Constraints and Subcategorization Frames in a Dependency Parser
| Title | Integrating Selectional Constraints and Subcategorization Frames in a Dependency Parser |
| Authors | Mirrosh, Seyed Abolghasem el, Alexis Nasr |
| Abstract | |
| Tasks | |
| Published | 2016-03-01 |
| URL | https://www.aclweb.org/anthology/J16-1002/ |
| https://www.aclweb.org/anthology/J16-1002 | |
| PWC | https://paperswithcode.com/paper/integrating-selectional-constraints-and |
| Repo | |
| Framework | |
