Paper Group NANR 125
NTOUA at IJCNLP-2017 Task 2: Predicting Sentiment Scores of Chinese Words and Phrases. Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation. A Survey on Intelligent Poetry Generation: Languages, Features, Techniques, Reutilisation and Evaluation. Defeasible AceRules: A Prototype. Discourse Relation …
NTOUA at IJCNLP-2017 Task 2: Predicting Sentiment Scores of Chinese Words and Phrases
| Title | NTOUA at IJCNLP-2017 Task 2: Predicting Sentiment Scores of Chinese Words and Phrases |
| Authors | Chuan-Jie Lin, Hao-Tsung Chang |
| Abstract | This paper describes the approaches of sentimental score prediction in the NTOU DSA system participating in DSAP this year. The modules to predict scores for words are adapted from our system last year. The approach to predict scores for phrases is keyword-based machine learning method. The performance of our system is good in predicting scores of phrases. |
| Tasks | Sentiment Analysis |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4021/ |
| https://www.aclweb.org/anthology/I17-4021 | |
| PWC | https://paperswithcode.com/paper/ntoua-at-ijcnlp-2017-task-2-predicting |
| Repo | |
| Framework | |
Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation
| Title | Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation |
| Authors | Thiago Castro Ferreira, Iacer Calixto, S Wubben, er, Emiel Krahmer |
| Abstract | In this paper, we study AMR-to-text generation, framing it as a translation task and comparing two different MT approaches (Phrase-based and Neural MT). We systematically study the effects of 3 AMR preprocessing steps (Delexicalisation, Compression, and Linearisation) applied before the MT phase. Our results show that preprocessing indeed helps, although the benefits differ for the two MT models. |
| Tasks | Machine Translation, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3501/ |
| https://www.aclweb.org/anthology/W17-3501 | |
| PWC | https://paperswithcode.com/paper/linguistic-realisation-as-machine-translation |
| Repo | |
| Framework | |
A Survey on Intelligent Poetry Generation: Languages, Features, Techniques, Reutilisation and Evaluation
| Title | A Survey on Intelligent Poetry Generation: Languages, Features, Techniques, Reutilisation and Evaluation |
| Authors | Hugo Gon{\c{c}}alo Oliveira |
| Abstract | Poetry generation is becoming popular among researchers of Natural Language Generation, Computational Creativity and, broadly, Artificial Intelligence. To produce text that may be regarded as poetry, poetry generation systems are typically knowledge-intensive and have to deal with several levels of language, from lexical to semantics. Interest on the topic resulted in the development of several poetry generators described in the literature, with different features covered or handled differently, by a broad range of alternative approaches, as well as different perspectives on evaluation, another challenging aspect due the underlying subjectivity. This paper surveys intelligent poetry generators around a set of relevant axis for poetry generation {–} targeted languages, form and content features, techniques, reutilisation of material, and evaluation {–} and aims to organise work developed on this topic so far. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3502/ |
| https://www.aclweb.org/anthology/W17-3502 | |
| PWC | https://paperswithcode.com/paper/a-survey-on-intelligent-poetry-generation |
| Repo | |
| Framework | |
Defeasible AceRules: A Prototype
| Title | Defeasible AceRules: A Prototype |
| Authors | Martin Diller, Adam Wyner, Hannes Strass |
| Abstract | |
| Tasks | Abstract Argumentation, Argument Mining |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6805/ |
| https://www.aclweb.org/anthology/W17-6805 | |
| PWC | https://paperswithcode.com/paper/defeasible-acerules-a-prototype |
| Repo | |
| Framework | |
Discourse Relations and Conjoined VPs: Automated Sense Recognition
| Title | Discourse Relations and Conjoined VPs: Automated Sense Recognition |
| Authors | Valentina Pyatkin, Bonnie Webber |
| Abstract | Sense classification of discourse relations is a sub-task of shallow discourse parsing. Discourse relations can occur both across sentences (\textit{inter-sentential}) and within sentences (\textit{intra-sentential}),and more than one discourse relation can hold between the same units. Using anewly available corpus of discourse-annotated intra-sentential conjoined verbphrases,we demonstrate a sequential classification pipeline for their multi-label senseclassification.We assess the importance of each feature used in the classification, thefeature scope, and what is lost in movingfrom gold standard manual parses to the output of an off-the-shelf parser. |
| Tasks | Multi-Label Classification |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-4004/ |
| https://www.aclweb.org/anthology/E17-4004 | |
| PWC | https://paperswithcode.com/paper/discourse-relations-and-conjoined-vps |
| Repo | |
| Framework | |
Evaluation of a Runyankore grammar engine for healthcare messages
| Title | Evaluation of a Runyankore grammar engine for healthcare messages |
| Authors | Joan Byamugisha, C. Maria Keet, Brian DeRenzi |
| Abstract | Natural Language Generation (NLG) can be used to generate personalized health information, which is especially useful when provided in one{'}s own language. However, the NLG technique widely used in different domains and languages{—}templates{—}was shown to be inapplicable to Bantu languages, due to their characteristic agglutinative structure. We present here our use of the grammar engine NLG technique to generate text in Runyankore, a Bantu language indigenous to Uganda. Our grammar engine adds to previous work in this field with new rules for cardinality constraints, prepositions in roles, the passive, and phonological conditioning. We evaluated the generated text with linguists and non-linguists, who regarded most text as grammatically correct and understandable; and over 60{%} of them regarded all the text generated by our system to have been authored by a human being. |
| Tasks | Machine Translation, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3514/ |
| https://www.aclweb.org/anthology/W17-3514 | |
| PWC | https://paperswithcode.com/paper/evaluation-of-a-runyankore-grammar-engine-for |
| Repo | |
| Framework | |
Talking about the world with a distributed model
| Title | Talking about the world with a distributed model |
| Authors | Gemma Boleda |
| Abstract | We use language to talk about the world, and so reference is a crucial property of language. However, modeling reference is particularly difficult, as it involves both continuous and discrete as-pects of language. For instance, referring expressions like {}the big mug{''} or {}it{''} typically contain content words ({}big{''}, {}mug{''}), which are notoriously fuzzy or vague in their meaning, and also fun-ction words ({}the{''}, {}it{''}) that largely serve as discrete pointers. Data-driven, distributed models based on distributional semantics or deep learning excel at the former, but struggle with the latter, and the reverse is true for symbolic models. I present ongoing work on modeling reference with a distribu-ted model aimed at capturing both aspects, and learns to refer directly from reference acts. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3515/ |
| https://www.aclweb.org/anthology/W17-3515 | |
| PWC | https://paperswithcode.com/paper/talking-about-the-world-with-a-distributed |
| Repo | |
| Framework | |
G-TUNA: a corpus of referring expressions in German, including duration information
| Title | G-TUNA: a corpus of referring expressions in German, including duration information |
| Authors | David Howcroft, Jorrig Vogels, Vera Demberg |
| Abstract | Corpora of referring expressions elicited from human participants in a controlled environment are an important resource for research on automatic referring expression generation. We here present G-TUNA, a new corpus of referring expressions for German. Using the furniture stimuli set developed for the TUNA and D-TUNA corpora, our corpus extends on these corpora by providing data collected in a simulated driving dual-task setting, and additionally provides exact duration annotations for the spoken referring expressions. This corpus will hence allow researchers to analyze the interaction between referring expression length and speech rate, under conditions where the listener is under high vs. low cognitive load. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3522/ |
| https://www.aclweb.org/anthology/W17-3522 | |
| PWC | https://paperswithcode.com/paper/g-tuna-a-corpus-of-referring-expressions-in |
| Repo | |
| Framework | |
A Commercial Perspective on Reference
| Title | A Commercial Perspective on Reference |
| Authors | Ehud Reiter |
| Abstract | I briefly describe some of the commercial work which XXX is doing in referring expression algorithms, and highlight differences between what is commercially important (at least to XXX) and the NLG research literature. In particular, XXX is less interested in generic reference algorithms than in high-quality algorithms for specific types of references, such as components of machines, named entities, and dates. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3519/ |
| https://www.aclweb.org/anthology/W17-3519 | |
| PWC | https://paperswithcode.com/paper/a-commercial-perspective-on-reference |
| Repo | |
| Framework | |
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing
| Title | Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1000/ |
| https://www.aclweb.org/anthology/D17-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2017-conference-on |
| Repo | |
| Framework | |
Corner-Based Geometric Calibration of Multi-Focus Plenoptic Cameras
| Title | Corner-Based Geometric Calibration of Multi-Focus Plenoptic Cameras |
| Authors | Sotiris Nousias, Francois Chadebecq, Jonas Pichat, Pearse Keane, Sebastien Ourselin, Christos Bergeles |
| Abstract | We propose a method for geometric calibration of multi-focus plenoptic cameras using raw images. Multi-focus plenoptic cameras feature several types of micro-lenses spatially aligned in front of the camera sensor to generate micro-images at different magnifications. This multi-lens arrangement provides computational-photography benefits but complicates calibration. Our methodology achieves the detection of the type of micro-lenses, the retrieval of their spatial arrangement, and the estimation of intrinsic and extrinsic camera parameters therefore fully characterising this specialised camera class. Motivated from classic pinhole camera calibration, the presented algorithm operates based on a checker-board’s corners, retrieved by a custom micro-image corner detector. This approach enables the introduction of a re-projection error that is used in a minimisation framework. Our algorithm compares favourably to the state-of-the-art, as demonstrated by controlled and free-hand experiments, making it a first step towards accurate 3D reconstruction and Structure-from-Motion. |
| Tasks | 3D Reconstruction, Calibration |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Nousias_Corner-Based_Geometric_Calibration_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Nousias_Corner-Based_Geometric_Calibration_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/corner-based-geometric-calibration-of-multi |
| Repo | |
| Framework | |
Towards Automatic Generation of Product Reviews from Aspect-Sentiment Scores
| Title | Towards Automatic Generation of Product Reviews from Aspect-Sentiment Scores |
| Authors | Hongyu Zang, Xiaojun Wan |
| Abstract | Data-to-text generation is very essential and important in machine writing applications. The recent deep learning models, like Recurrent Neural Networks (RNNs), have shown a bright future for relevant text generation tasks. However, rare work has been done for automatic generation of long reviews from user opinions. In this paper, we introduce a deep neural network model to generate long Chinese reviews from aspect-sentiment scores representing users{'} opinions. We conduct our study within the framework of encoder-decoder networks, and we propose a hierarchical structure with aligned attention in the Long-Short Term Memory (LSTM) decoder. Experiments show that our model outperforms retrieval based baseline methods, and also beats the sequential generation models in qualitative evaluations. |
| Tasks | Data-to-Text Generation, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3526/ |
| https://www.aclweb.org/anthology/W17-3526 | |
| PWC | https://paperswithcode.com/paper/towards-automatic-generation-of-product |
| Repo | |
| Framework | |
Adversarial Training for Cross-Domain Universal Dependency Parsing
| Title | Adversarial Training for Cross-Domain Universal Dependency Parsing |
| Authors | Motoki Sato, Hitoshi Manabe, Hiroshi Noji, Yuji Matsumoto |
| Abstract | We describe our submission to the CoNLL 2017 shared task, which exploits the shared common knowledge of a language across different domains via a domain adaptation technique. Our approach is an extension to the recently proposed adversarial training technique for domain adaptation, which we apply on top of a graph-based neural dependency parsing model on bidirectional LSTMs. In our experiments, we find our baseline graph-based parser already outperforms the official baseline model (UDPipe) by a large margin. Further, by applying our technique to the treebanks of the same language with different domains, we observe an additional gain in the performance, in particular for the domains with less training data. |
| Tasks | Dependency Parsing, Domain Adaptation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-3007/ |
| https://www.aclweb.org/anthology/K17-3007 | |
| PWC | https://paperswithcode.com/paper/adversarial-training-for-cross-domain |
| Repo | |
| Framework | |
A model of suspense for narrative generation
| Title | A model of suspense for narrative generation |
| Authors | Richard Doust, Paul Piwek |
| Abstract | Most work on automatic generation of narratives, and more specifically suspenseful narrative, has focused on detailed domain-specific modelling of character psychology and plot structure. Recent work in computational linguistics on the automatic learning of narrative schemas suggests an alternative approach that exploits such schemas as a starting point for modelling and measuring suspense. We propose a domain-independent model for tracking suspense in a story which can be used to predict the audience{'}s suspense response on a sentence-by-sentence basis at the content determination stage of narrative generation. The model lends itself as the theoretical foundation for a suspense module that is compatible with alternative narrative generation theories. The proposal is evaluated by human judges{'} normalised average scores correlate strongly with predicted values. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3527/ |
| https://www.aclweb.org/anthology/W17-3527 | |
| PWC | https://paperswithcode.com/paper/a-model-of-suspense-for-narrative-generation |
| Repo | |
| Framework | |
Volatility Prediction using Financial Disclosures Sentiments with Word Embedding-based IR Models
| Title | Volatility Prediction using Financial Disclosures Sentiments with Word Embedding-based IR Models |
| Authors | Navid Rekabsaz, Mihai Lupu, Artem Baklanov, Alex D{"u}r, er, Linda Andersson, Allan Hanbury |
| Abstract | Volatility prediction{—}an essential concept in financial markets{—}has recently been addressed using sentiment analysis methods. We investigate the sentiment of annual disclosures of companies in stock markets to forecast volatility. We specifically explore the use of recent Information Retrieval (IR) term weighting models that are effectively extended by related terms using word embeddings. In parallel to textual information, factual market data have been widely used as the mainstream approach to forecast market risk. We therefore study different fusion methods to combine text and market data resources. Our word embedding-based approach significantly outperforms state-of-the-art methods. In addition, we investigate the characteristics of the reports of the companies in different financial sectors. |
| Tasks | Information Retrieval, Sentiment Analysis, Word Embeddings |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1157/ |
| https://www.aclweb.org/anthology/P17-1157 | |
| PWC | https://paperswithcode.com/paper/volatility-prediction-using-financial |
| Repo | |
| Framework | |
