Paper Group NANR 64
Sofrer uma ofensa, Receber uma advert^encia: Verbos-suporte Conversos de Fazer' no Portugu\^es do Brasil (Suffering an offense, Receiving a citation: Supporting Vectors Converted from To do’ in Brazilian Portuguese)[In Portuguese]. Creating Training Corpora for NLG Micro-Planners. IWCS 2017 - 12th International Conference on Computational Semant …
Sofrer uma ofensa, Receber uma advert^encia: Verbos-suporte Conversos de Fazer' no Portugu\^es do Brasil (Suffering an offense, Receiving a citation: Supporting Vectors Converted from To do’ in Brazilian Portuguese)[In Portuguese]
| Title | Sofrer uma ofensa, Receber uma advert^encia: Verbos-suporte Conversos de Fazer' no Portugu\^es do Brasil (Suffering an offense, Receiving a citation: Supporting Vectors Converted from To do’ in Brazilian Portuguese)[In Portuguese] |
| Authors | Cla{'u}dia D. Barros, Nathalia P. Calcia, Oto A. Vale |
| Abstract | |
| Tasks | |
| Published | 2017-10-01 |
| URL | https://www.aclweb.org/anthology/W17-6628/ |
| https://www.aclweb.org/anthology/W17-6628 | |
| PWC | https://paperswithcode.com/paper/sofrer-uma-ofensa-receber-uma-advertaancia |
| Repo | |
| Framework | |
Creating Training Corpora for NLG Micro-Planners
| Title | Creating Training Corpora for NLG Micro-Planners |
| Authors | Claire Gardent, Anastasia Shimorina, Shashi Narayan, Laura Perez-Beltrachini |
| Abstract | In this paper, we present a novel framework for semi-automatically creating linguistically challenging micro-planning data-to-text corpora from existing Knowledge Bases. Because our method pairs data of varying size and shape with texts ranging from simple clauses to short texts, a dataset created using this framework provides a challenging benchmark for microplanning. Another feature of this framework is that it can be applied to any large scale knowledge base and can therefore be used to train and learn KB verbalisers. We apply our framework to DBpedia data and compare the resulting dataset with Wen et al. 2016{'}s. We show that while Wen et al.{'}s dataset is more than twice larger than ours, it is less diverse both in terms of input and in terms of text. We thus propose our corpus generation framework as a novel method for creating challenging data sets from which NLG models can be learned which are capable of handling the complex interactions occurring during in micro-planning between lexicalisation, aggregation, surface realisation, referring expression generation and sentence segmentation. To encourage researchers to take up this challenge, we made available a dataset of 21,855 data/text pairs created using this framework in the context of the WebNLG shared task. |
| Tasks | Data-to-Text Generation, Text Generation |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1017/ |
| https://www.aclweb.org/anthology/P17-1017 | |
| PWC | https://paperswithcode.com/paper/creating-training-corpora-for-nlg-micro |
| Repo | |
| Framework | |
IWCS 2017 - 12th International Conference on Computational Semantics - Long papers
| Title | IWCS 2017 - 12th International Conference on Computational Semantics - Long papers |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6800/ |
| https://www.aclweb.org/anthology/W17-6800 | |
| PWC | https://paperswithcode.com/paper/iwcs-2017-12th-international-conference-on |
| Repo | |
| Framework | |
A Simpler and More Generalizable Story Detector using Verb and Character Features
| Title | A Simpler and More Generalizable Story Detector using Verb and Character Features |
| Authors | Joshua Eisenberg, Mark Finlayson |
| Abstract | Story detection is the task of determining whether or not a unit of text contains a story. Prior approaches achieved a maximum performance of 0.66 F1, and did not generalize well across different corpora. We present a new state-of-the-art detector that achieves a maximum performance of 0.75 F1 (a 14{%} improvement), with significantly greater generalizability than previous work. In particular, our detector achieves performance above 0.70 F1 across a variety of combinations of lexically different corpora for training and testing, as well as dramatic improvements (up to 4,000{%}) in performance when trained on a small, disfluent data set. The new detector uses two basic types of features{–}ones related to events, and ones related to characters{–}totaling 283 specific features overall; previous detectors used tens of thousands of features, and so this detector represents a significant simplification along with increased performance. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1287/ |
| https://www.aclweb.org/anthology/D17-1287 | |
| PWC | https://paperswithcode.com/paper/a-simpler-and-more-generalizable-story |
| Repo | |
| Framework | |
Network Visualisations for Exploring Political Concepts
| Title | Network Visualisations for Exploring Political Concepts |
| Authors | Paul Nulty |
| Abstract | |
| Tasks | Community Detection, Topic Models |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6930/ |
| https://www.aclweb.org/anthology/W17-6930 | |
| PWC | https://paperswithcode.com/paper/network-visualisations-for-exploring |
| Repo | |
| Framework | |
Exploring Multi-Modal Text+Image Models to Distinguish between Abstract and Concrete Nouns
| Title | Exploring Multi-Modal Text+Image Models to Distinguish between Abstract and Concrete Nouns |
| Authors | Sai Abishek Bhaskar, Maximilian K{"o}per, Sabine Schulte Im Walde, Diego Frassinelli |
| Abstract | |
| Tasks | Language Acquisition |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7101/ |
| https://www.aclweb.org/anthology/W17-7101 | |
| PWC | https://paperswithcode.com/paper/exploring-multi-modal-textimage-models-to |
| Repo | |
| Framework | |
Explicative Path Finding in a Semantic Network
| Title | Explicative Path Finding in a Semantic Network |
| Authors | K{'e}vin Cousot, Mathieu Lafourcade |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7204/ |
| https://www.aclweb.org/anthology/W17-7204 | |
| PWC | https://paperswithcode.com/paper/explicative-path-finding-in-a-semantic |
| Repo | |
| Framework | |
Proceedings of the 13th Joint ISO-ACL Workshop on Interoperable Semantic Annotation (ISA-13)
| Title | Proceedings of the 13th Joint ISO-ACL Workshop on Interoperable Semantic Annotation (ISA-13) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7400/ |
| https://www.aclweb.org/anthology/W17-7400 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-13th-joint-iso-acl |
| Repo | |
| Framework | |
Temporal@ODIL project: Adapting ISO-TimeML to syntactic treebanks for the temporal annotation of spoken speech
| Title | Temporal@ODIL project: Adapting ISO-TimeML to syntactic treebanks for the temporal annotation of spoken speech |
| Authors | Jean-Yves Antoine, Jakub Wasczuk, Ana{"\i}s Lefeuvre-Haftermeyer, Lotfi Abouda, Emmanuel Schang, Agata Savary |
| Abstract | |
| Tasks | Constituency Parsing |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7413/ |
| https://www.aclweb.org/anthology/W17-7413 | |
| PWC | https://paperswithcode.com/paper/temporalodil-project-adapting-iso-timeml-to |
| Repo | |
| Framework | |
Multi-task Attention-based Neural Networks for Implicit Discourse Relationship Representation and Identification
| Title | Multi-task Attention-based Neural Networks for Implicit Discourse Relationship Representation and Identification |
| Authors | Man Lan, Jianxiang Wang, Yuanbin Wu, Zheng-Yu Niu, Haifeng Wang |
| Abstract | We present a novel multi-task attention based neural network model to address implicit discourse relationship representation and identification through two types of representation learning, an attention based neural network for learning discourse relationship representation with two arguments and a multi-task framework for learning knowledge from annotated and unannotated corpora. The extensive experiments have been performed on two benchmark corpora (i.e., PDTB and CoNLL-2016 datasets). Experimental results show that our proposed model outperforms the state-of-the-art systems on benchmark corpora. |
| Tasks | Multi-Task Learning, Reading Comprehension, Representation Learning, Sentiment Analysis, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1134/ |
| https://www.aclweb.org/anthology/D17-1134 | |
| PWC | https://paperswithcode.com/paper/multi-task-attention-based-neural-networks |
| Repo | |
| Framework | |
Natural Language Programing with Automatic Code Generation towards Solving Addition-Subtraction Word Problems
| Title | Natural Language Programing with Automatic Code Generation towards Solving Addition-Subtraction Word Problems |
| Authors | M, Sourav al, Sudip Kumar Naskar |
| Abstract | |
| Tasks | Code Generation |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7519/ |
| https://www.aclweb.org/anthology/W17-7519 | |
| PWC | https://paperswithcode.com/paper/natural-language-programing-with-automatic |
| Repo | |
| Framework | |
Keynote Lecture 3: Towards Abstractive Summarization
| Title | Keynote Lecture 3: Towards Abstractive Summarization |
| Authors | Vasudeva Varma |
| Abstract | |
| Tasks | Abstractive Text Summarization |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7551/ |
| https://www.aclweb.org/anthology/W17-7551 | |
| PWC | https://paperswithcode.com/paper/keynote-lecture-3-towards-abstractive |
| Repo | |
| Framework | |
Demystifying Topology of Autopilot Thoughts: A Computational Analysis of Linguistic Patterns of Psychological Aspects in Mental Health
| Title | Demystifying Topology of Autopilot Thoughts: A Computational Analysis of Linguistic Patterns of Psychological Aspects in Mental Health |
| Authors | Bibekan Kundu, a, Sanjay Choudhury |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7554/ |
| https://www.aclweb.org/anthology/W17-7554 | |
| PWC | https://paperswithcode.com/paper/demystifying-topology-of-autopilot-thoughts-a |
| Repo | |
| Framework | |
A Telugu treebank based on a grammar book
| Title | A Telugu treebank based on a grammar book |
| Authors | Taraka Rama, Sowmya Vajjala |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7616/ |
| https://www.aclweb.org/anthology/W17-7616 | |
| PWC | https://paperswithcode.com/paper/a-telugu-treebank-based-on-a-grammar-book |
| Repo | |
| Framework | |
Recent Developments within BulTreeBank
| Title | Recent Developments within BulTreeBank |
| Authors | Petya Osenova, Kiril Simov |
| Abstract | |
| Tasks | Word Embeddings |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7617/ |
| https://www.aclweb.org/anthology/W17-7617 | |
| PWC | https://paperswithcode.com/paper/recent-developments-within-bultreebank |
| Repo | |
| Framework | |
