Paper Group NANR 123
Evaluating Context Selection Strategies to Build Emotive Vector Space Models. Cross-lingual Linking of Multi-word Entities and their corresponding Acronyms. Universal Dependencies v1: A Multilingual Treebank Collection. Design of an Input Method for Taiwanese Hokkien using Unsupervized Word Segmentation for Language Modeling. Evaluating embeddings …
Evaluating Context Selection Strategies to Build Emotive Vector Space Models
| Title | Evaluating Context Selection Strategies to Build Emotive Vector Space Models |
| Authors | Lucia C. Passaro, Aless Lenci, ro |
| Abstract | In this paper we compare different context selection approaches to improve the creation of Emotive Vector Space Models (VSMs). The system is based on the results of an existing approach that showed the possibility to create and update VSMs by exploiting crowdsourcing and human annotation. Here, we introduce a method to manipulate the contexts of the VSMs under the assumption that the emotive connotation of a target word is a function of both its syntagmatic and paradigmatic association with the various emotions. To study the differences among the proposed spaces and to confirm the reliability of the system, we report on two experiments: in the first one we validated the best candidates extracted from each model, and in the second one we compared the models{'} performance on a random sample of target words. Both experiments have been implemented as crowdsourcing tasks. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1347/ |
| https://www.aclweb.org/anthology/L16-1347 | |
| PWC | https://paperswithcode.com/paper/evaluating-context-selection-strategies-to |
| Repo | |
| Framework | |
Cross-lingual Linking of Multi-word Entities and their corresponding Acronyms
| Title | Cross-lingual Linking of Multi-word Entities and their corresponding Acronyms |
| Authors | Guillaume Jacquet, Maud Ehrmann, Ralf Steinberger, Jaakko V{"a}yrynen |
| Abstract | This paper reports on an approach and experiments to automatically build a cross-lingual multi-word entity resource. Starting from a collection of millions of acronym/expansion pairs for 22 languages where expansion variants were grouped into monolingual clusters, we experiment with several aggregation strategies to link these clusters across languages. Aggregation strategies make use of string similarity distances and translation probabilities and they are based on vector space and graph representations. The accuracy of the approach is evaluated against Wikipedia{'}s redirection and cross-lingual linking tables. The resulting multi-word entity resource contains 64,000 multi-word entities with unique identifiers and their 600,000 multilingual lexical variants. We intend to make this new resource publicly available. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1084/ |
| https://www.aclweb.org/anthology/L16-1084 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-linking-of-multi-word-entities |
| Repo | |
| Framework | |
Universal Dependencies v1: A Multilingual Treebank Collection
| Title | Universal Dependencies v1: A Multilingual Treebank Collection |
| Authors | Joakim Nivre, Marie-Catherine de Marneffe, Filip Ginter, Yoav Goldberg, Jan Haji{\v{c}}, Christopher D. Manning, Ryan McDonald, Slav Petrov, Sampo Pyysalo, Natalia Silveira, Reut Tsarfaty, Daniel Zeman |
| Abstract | Cross-linguistically consistent annotation is necessary for sound comparative evaluation and cross-lingual learning experiments. It is also useful for multilingual system development and comparative linguistic studies. Universal Dependencies is an open community effort to create cross-linguistically consistent treebank annotation for many languages within a dependency-based lexicalist framework. In this paper, we describe v1 of the universal guidelines, the underlying design principles, and the currently available treebanks for 33 languages. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1262/ |
| https://www.aclweb.org/anthology/L16-1262 | |
| PWC | https://paperswithcode.com/paper/universal-dependencies-v1-a-multilingual |
| Repo | |
| Framework | |
Design of an Input Method for Taiwanese Hokkien using Unsupervized Word Segmentation for Language Modeling
| Title | Design of an Input Method for Taiwanese Hokkien using Unsupervized Word Segmentation for Language Modeling |
| Authors | Pierre Magistry |
| Abstract | |
| Tasks | Language Modelling |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/O16-1026/ |
| https://www.aclweb.org/anthology/O16-1026 | |
| PWC | https://paperswithcode.com/paper/design-of-an-input-method-for-taiwanese |
| Repo | |
| Framework | |
Evaluating embeddings on dictionary-based similarity
| Title | Evaluating embeddings on dictionary-based similarity |
| Authors | Judit {'A}cs, Andr{'a}s Kornai |
| Abstract | |
| Tasks | Information Retrieval, Word Sense Disambiguation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2514/ |
| https://www.aclweb.org/anthology/W16-2514 | |
| PWC | https://paperswithcode.com/paper/evaluating-embeddings-on-dictionary-based |
| Repo | |
| Framework | |
Learning Orthographic Features in Bi-directional LSTM for Biomedical Named Entity Recognition
| Title | Learning Orthographic Features in Bi-directional LSTM for Biomedical Named Entity Recognition |
| Authors | Nut Limsopatham, Nigel Collier |
| Abstract | End-to-end neural network models for named entity recognition (NER) have shown to achieve effective performances on general domain datasets (e.g. newswire), without requiring additional hand-crafted features. However, in biomedical domain, recent studies have shown that hand-engineered features (e.g. orthographic features) should be used to attain effective performance, due to the complexity of biomedical terminology (e.g. the use of acronyms and complex gene names). In this work, we propose a novel approach that allows a neural network model based on a long short-term memory (LSTM) to automatically learn orthographic features and incorporate them into a model for biomedical NER. Importantly, our bi-directional LSTM model learns and leverages orthographic features on an end-to-end basis. We evaluate our approach by comparing against existing neural network models for NER using three well-established biomedical datasets. Our experimental results show that the proposed approach consistently outperforms these strong baselines across all of the three datasets. |
| Tasks | Feature Engineering, Named Entity Recognition, Word Embeddings |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5102/ |
| https://www.aclweb.org/anthology/W16-5102 | |
| PWC | https://paperswithcode.com/paper/learning-orthographic-features-in-bi |
| Repo | |
| Framework | |
When Annotation Schemes Change Rules Help: A Configurable Approach to Coreference Resolution beyond OntoNotes
| Title | When Annotation Schemes Change Rules Help: A Configurable Approach to Coreference Resolution beyond OntoNotes |
| Authors | Amir Zeldes, Shuo Zhang |
| Abstract | |
| Tasks | Coreference Resolution, Domain Adaptation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0713/ |
| https://www.aclweb.org/anthology/W16-0713 | |
| PWC | https://paperswithcode.com/paper/when-annotation-schemes-change-rules-help-a |
| Repo | |
| Framework | |
Crowdsourced Corpus with Entity Salience Annotations
| Title | Crowdsourced Corpus with Entity Salience Annotations |
| Authors | Milan Dojchinovski, Dinesh Reddy, Tom{'a}{\v{s}} Kliegr, Tom{'a}{\v{s}} Vitvar, Harald Sack |
| Abstract | In this paper, we present a crowdsourced dataset which adds entity salience (importance) annotations to the Reuters-128 dataset, which is subset of Reuters-21578. The dataset is distributed under a free license and publish in the NLP Interchange Format, which fosters interoperability and re-use. We show the potential of the dataset on the task of learning an entity salience classifier and report on the results from several experiments. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1527/ |
| https://www.aclweb.org/anthology/L16-1527 | |
| PWC | https://paperswithcode.com/paper/crowdsourced-corpus-with-entity-salience |
| Repo | |
| Framework | |
Improving Temporal Relation Extraction with Training Instance Augmentation
| Title | Improving Temporal Relation Extraction with Training Instance Augmentation |
| Authors | Chen Lin, Timothy Miller, Dmitriy Dligach, Steven Bethard, Guergana Savova |
| Abstract | |
| Tasks | Data Augmentation, Question Answering, Relation Extraction, Temporal Information Extraction |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2914/ |
| https://www.aclweb.org/anthology/W16-2914 | |
| PWC | https://paperswithcode.com/paper/improving-temporal-relation-extraction-with |
| Repo | |
| Framework | |
Predict Anchor Links across Social Networks via an Embedding Approach
| Title | Predict Anchor Links across Social Networks via an Embedding Approach |
| Authors | Tong Man, Huawei Shen, Shenghua Liu, Xiaolong Jin, and Xueqi Cheng |
| Abstract | Predicting anchor links across social networks has important implications to an array of applications, including cross-network information diffusion and cross-domain recommendation. One challenging problem is: whether and to what extent we can address the anchor link prediction problem, if only structural information of networks is available. Most existing methods, unsupervised or supervised, directly work on networks themselves rather than on their intrinsic structural regularities, and thus their effectiveness is sensitive to the high dimension and sparsity of networks. To offer a robust method, we propose a novel supervised model, called PALE, which employs network embedding with awareness of observed anchor links as supervised information to capture the major and specific structural regularities and further learns a stable cross-network mapping for predicting anchor links. Through extensive experiments on two realistic datasets, we demonstrate that PALE significantly outperforms the state-of-the-art methods |
| Tasks | Link Prediction, Network Embedding |
| Published | 2016-06-25 |
| URL | http://www.bigdatalab.ac.cn/~shenhuawei/publications/2016/ijcai-man.pdf |
| http://www.bigdatalab.ac.cn/~shenhuawei/publications/2016/ijcai-man.pdf | |
| PWC | https://paperswithcode.com/paper/predict-anchor-links-across-social-networks |
| Repo | |
| Framework | |
Small Talk Improves User Impressions of Interview Dialogue Systems
| Title | Small Talk Improves User Impressions of Interview Dialogue Systems |
| Authors | Takahiro Kobori, Mikio Nakano, Tomoaki Nakamura |
| Abstract | |
| Tasks | Dialogue Management |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-3646/ |
| https://www.aclweb.org/anthology/W16-3646 | |
| PWC | https://paperswithcode.com/paper/small-talk-improves-user-impressions-of |
| Repo | |
| Framework | |
Creating a Large Benchmark for Open Information Extraction
| Title | Creating a Large Benchmark for Open Information Extraction |
| Authors | Gabriel Stanovsky, Ido Dagan |
| Abstract | |
| Tasks | Open Information Extraction |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1252/ |
| https://www.aclweb.org/anthology/D16-1252 | |
| PWC | https://paperswithcode.com/paper/creating-a-large-benchmark-for-open |
| Repo | |
| Framework | |
Understanding Negation in Positive Terms Using Syntactic Dependencies
| Title | Understanding Negation in Positive Terms Using Syntactic Dependencies |
| Authors | Zahra Sarabi, Eduardo Blanco |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1119/ |
| https://www.aclweb.org/anthology/D16-1119 | |
| PWC | https://paperswithcode.com/paper/understanding-negation-in-positive-terms |
| Repo | |
| Framework | |
The Challenges and Joys of Analysing Ongoing Language Change in Web-based Corpora: a Case Study
| Title | The Challenges and Joys of Analysing Ongoing Language Change in Web-based Corpora: a Case Study |
| Authors | Anne Krause |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2604/ |
| https://www.aclweb.org/anthology/W16-2604 | |
| PWC | https://paperswithcode.com/paper/the-challenges-and-joys-of-analysing-ongoing |
| Repo | |
| Framework | |
An Effect of Background Population Sample Size on the Performance of a Likelihood Ratio-based Forensic Text Comparison System: A Monte Carlo Simulation with Gaussian Mixture Model
| Title | An Effect of Background Population Sample Size on the Performance of a Likelihood Ratio-based Forensic Text Comparison System: A Monte Carlo Simulation with Gaussian Mixture Model |
| Authors | Shunichi Ishihara |
| Abstract | |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/U16-1012/ |
| https://www.aclweb.org/anthology/U16-1012 | |
| PWC | https://paperswithcode.com/paper/an-effect-of-background-population-sample |
| Repo | |
| Framework | |
