Paper Group NANR 34
SemEval-2018 Task 3: Irony Detection in English Tweets. Evaluating Domain Adaptation for Machine Translation Across Scenarios. Low-resource named entity recognition via multi-source projection: Not quite there yet?. Genre Separation Network with Adversarial Training for Cross-genre Relation Extraction. Towards a music-language mapping. Synthetic Da …
SemEval-2018 Task 3: Irony Detection in English Tweets
Title | SemEval-2018 Task 3: Irony Detection in English Tweets |
Authors | Cynthia Van Hee, Els Lefever, V{'e}ronique Hoste |
Abstract | This paper presents the first shared task on irony detection: given a tweet, automatic natural language processing systems should determine whether the tweet is ironic (Task A) and which type of irony (if any) is expressed (Task B). The ironic tweets were collected using irony-related hashtags (i.e. {#}irony, {#}sarcasm, {#}not) and were subsequently manually annotated to minimise the amount of noise in the corpus. Prior to distributing the data, hashtags that were used to collect the tweets were removed from the corpus. For both tasks, a training corpus of 3,834 tweets was provided, as well as a test set containing 784 tweets. Our shared tasks received submissions from 43 teams for the binary classification Task A and from 31 teams for the multiclass Task B. The highest classification scores obtained for both subtasks are respectively F1= 0.71 and F1= 0.51 and demonstrate that fine-grained irony classification is much more challenging than binary irony detection. |
Tasks | Sentiment Analysis |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1005/ |
https://www.aclweb.org/anthology/S18-1005 | |
PWC | https://paperswithcode.com/paper/semeval-2018-task-3-irony-detection-in |
Repo | |
Framework | |
Evaluating Domain Adaptation for Machine Translation Across Scenarios
Title | Evaluating Domain Adaptation for Machine Translation Across Scenarios |
Authors | Thierry Etchegoyhen, Anna Fern{'a}ndez Torn{'e}, Andoni Azpeitia, Eva Mart{'\i}nez Garcia, Anna Matamala |
Abstract | |
Tasks | Domain Adaptation, Machine Translation |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1002/ |
https://www.aclweb.org/anthology/L18-1002 | |
PWC | https://paperswithcode.com/paper/evaluating-domain-adaptation-for-machine |
Repo | |
Framework | |
Low-resource named entity recognition via multi-source projection: Not quite there yet?
Title | Low-resource named entity recognition via multi-source projection: Not quite there yet? |
Authors | Jan Vium Enghoff, S{\o}ren Harrison, {\v{Z}}eljko Agi{'c} |
Abstract | Projecting linguistic annotations through word alignments is one of the most prevalent approaches to cross-lingual transfer learning. Conventional wisdom suggests that annotation projection {``}just works{''} regardless of the task at hand. We carefully consider multi-source projection for named entity recognition. Our experiment with 17 languages shows that to detect named entities in true low-resource languages, annotation projection may not be the right way to move forward. On a more positive note, we also uncover the conditions that do favor named entity projection from multiple sources. We argue these are infeasible under noisy low-resource constraints. | |
Tasks | Cross-Lingual Transfer, Dependency Parsing, Named Entity Recognition, Part-Of-Speech Tagging, Transfer Learning |
Published | 2018-11-01 |
URL | https://www.aclweb.org/anthology/W18-6125/ |
https://www.aclweb.org/anthology/W18-6125 | |
PWC | https://paperswithcode.com/paper/low-resource-named-entity-recognition-via |
Repo | |
Framework | |
Genre Separation Network with Adversarial Training for Cross-genre Relation Extraction
Title | Genre Separation Network with Adversarial Training for Cross-genre Relation Extraction |
Authors | Ge Shi, Chong Feng, Lifu Huang, Boliang Zhang, Heng Ji, Lejian Liao, Heyan Huang |
Abstract | Relation Extraction suffers from dramatical performance decrease when training a model on one genre and directly applying it to a new genre, due to the distinct feature distributions. Previous studies address this problem by discovering a shared space across genres using manually crafted features, which requires great human effort. To effectively automate this process, we design a genre-separation network, which applies two encoders, one genre-independent and one genre-shared, to explicitly extract genre-specific and genre-agnostic features. Then we train a relation classifier using the genre-agnostic features on the source genre and directly apply to the target genre. Experiment results on three distinct genres of the ACE dataset show that our approach achieves up to 6.1{%} absolute F1-score gain compared to previous methods. By incorporating a set of external linguistic features, our approach outperforms the state-of-the-art by 1.7{%} absolute F1 gain. We make all programs of our model publicly available for research purpose |
Tasks | Feature Engineering, Relation Extraction, Word Embeddings |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1125/ |
https://www.aclweb.org/anthology/D18-1125 | |
PWC | https://paperswithcode.com/paper/genre-separation-network-with-adversarial |
Repo | |
Framework | |
Towards a music-language mapping
Title | Towards a music-language mapping |
Authors | Michele Berlingerio, Francesca Bonin |
Abstract | |
Tasks | Lexical Analysis, Sentiment Analysis, Text Generation |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1482/ |
https://www.aclweb.org/anthology/L18-1482 | |
PWC | https://paperswithcode.com/paper/towards-a-music-language-mapping |
Repo | |
Framework | |
Synthetic Data Made to Order: The Case of Parsing
Title | Synthetic Data Made to Order: The Case of Parsing |
Authors | Dingquan Wang, Jason Eisner |
Abstract | To approximately parse an unfamiliar language, it helps to have a treebank of a similar language. But what if the closest available treebank still has the wrong word order? We show how to (stochastically) permute the constituents of an existing dependency treebank so that its surface part-of-speech statistics approximately match those of the target language. The parameters of the permutation model can be evaluated for quality by dynamic programming and tuned by gradient descent (up to a local optimum). This optimization procedure yields trees for a new artificial language that resembles the target language. We show that delexicalized parsers for the target language can be successfully trained using such {``}made to order{''} artificial languages. | |
Tasks | Cross-Lingual Transfer, Dependency Parsing, Language Modelling, Word Embeddings |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1163/ |
https://www.aclweb.org/anthology/D18-1163 | |
PWC | https://paperswithcode.com/paper/synthetic-data-made-to-order-the-case-of |
Repo | |
Framework | |
FontLex: A Typographical Lexicon based on Affective Associations
Title | FontLex: A Typographical Lexicon based on Affective Associations |
Authors | Tugba Kulahcioglu, Gerard de Melo |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1010/ |
https://www.aclweb.org/anthology/L18-1010 | |
PWC | https://paperswithcode.com/paper/fontlex-a-typographical-lexicon-based-on |
Repo | |
Framework | |
IUCM at SemEval-2018 Task 11: Similar-Topic Texts as a Comprehension Knowledge Source
Title | IUCM at SemEval-2018 Task 11: Similar-Topic Texts as a Comprehension Knowledge Source |
Authors | Sofia Reznikova, Leon Derczynski |
Abstract | This paper describes the IUCM entry at SemEval-2018 Task 11, on machine comprehension using commonsense knowledge. First, clustering and topic modeling are used to divide given texts into topics. Then, during the answering phase, other texts of the same topic are retrieved and used as commonsense knowledge. Finally, the answer is selected. While clustering itself shows good results, finding an answer proves to be more challenging. This paper reports the results of system evaluation and suggests potential improvements. |
Tasks | Lemmatization, Question Answering, Reading Comprehension |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1179/ |
https://www.aclweb.org/anthology/S18-1179 | |
PWC | https://paperswithcode.com/paper/iucm-at-semeval-2018-task-11-similar-topic |
Repo | |
Framework | |
A Large Resource of Patterns for Verbal Paraphrases
Title | A Large Resource of Patterns for Verbal Paraphrases |
Authors | Octavian Popescu, Ngoc Phuoc An Vo, Vadim Sheinin |
Abstract | |
Tasks | Natural Language Inference, Semantic Textual Similarity |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1035/ |
https://www.aclweb.org/anthology/L18-1035 | |
PWC | https://paperswithcode.com/paper/a-large-resource-of-patterns-for-verbal |
Repo | |
Framework | |
Salience Guided Depth Calibration for Perceptually Optimized Compressive Light Field 3D Display
Title | Salience Guided Depth Calibration for Perceptually Optimized Compressive Light Field 3D Display |
Authors | Shizheng Wang, Wenjuan Liao, Phil Surman, Zhigang Tu, Yuanjin Zheng, Junsong Yuan |
Abstract | Multi-layer light field displays are a type of computational three-dimensional (3D) display which has recently gained increasing interest for its holographic-like effect and natural compatibility with 2D displays. However, the major shortcoming, depth limitation, still cannot be overcome in the traditional light field modeling and reconstruction based on multi-layer liquid crystal displays (LCDs). Considering this disadvantage, our paper incorporates a salience guided depth optimization over a limited display range to calibrate the displayed depth and present the maximum area of salience region for multi-layer light field display. Different from previously reported cascaded light field displays that use the fixed initialization plane as the depth center of display content, our method automatically calibrates the depth initialization based on the salience results derived from the proposed contrast enhanced salience detection method. Experiments demonstrate that the proposed method provides a promising advantage in visual perception for the compressive light field displays from both software simulation and prototype demonstration. |
Tasks | Calibration |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Salience_Guided_Depth_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Salience_Guided_Depth_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/salience-guided-depth-calibration-for |
Repo | |
Framework | |
The Reference Corpus of the Contemporary Romanian Language (CoRoLa)
Title | The Reference Corpus of the Contemporary Romanian Language (CoRoLa) |
Authors | Verginica Barbu Mititelu, Dan Tufi{\textcommabelow{s}}, Elena Irimia |
Abstract | |
Tasks | |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1189/ |
https://www.aclweb.org/anthology/L18-1189 | |
PWC | https://paperswithcode.com/paper/the-reference-corpus-of-the-contemporary |
Repo | |
Framework | |
Distributed non-parametric deep and wide networks
Title | Distributed non-parametric deep and wide networks |
Authors | Biswa Sengupta, Yu Qian |
Abstract | In recent work, it was shown that combining multi-kernel based support vector machines (SVMs) can lead to near state-of-the-art performance on an action recognition dataset (HMDB-51 dataset). In the present work, we show that combining distributed Gaussian Processes with multi-stream deep convolutional neural networks (CNN) alleviate the need to augment a neural network with hand-crafted features. In contrast to prior work, we treat each deep neural convolutional network as an expert wherein the individual predictions (and their respective uncertainties) are combined into a Product of Experts (PoE) framework. |
Tasks | Gaussian Processes, Temporal Action Localization |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=rkhCSO4T- |
https://openreview.net/pdf?id=rkhCSO4T- | |
PWC | https://paperswithcode.com/paper/distributed-non-parametric-deep-and-wide |
Repo | |
Framework | |
NEUROSENT-PDI at SemEval-2018 Task 1: Leveraging a Multi-Domain Sentiment Model for Inferring Polarity in Micro-blog Text
Title | NEUROSENT-PDI at SemEval-2018 Task 1: Leveraging a Multi-Domain Sentiment Model for Inferring Polarity in Micro-blog Text |
Authors | Mauro Dragoni |
Abstract | This paper describes the NeuroSent system that participated in SemEval 2018 Task 1. Our system takes a supervised approach that builds on neural networks and word embeddings. Word embeddings were built by starting from a repository of user generated reviews. Thus, they are specific for sentiment analysis tasks. Then, tweets are converted in the corresponding vector representation and given as input to the neural network with the aim of learning the different semantics contained in each emotion taken into account by the SemEval task. The output layer has been adapted based on the characteristics of each subtask. Preliminary results obtained on the provided training set are encouraging for pursuing the investigation into this direction. |
Tasks | Sentiment Analysis, Word Embeddings |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1013/ |
https://www.aclweb.org/anthology/S18-1013 | |
PWC | https://paperswithcode.com/paper/neurosent-pdi-at-semeval-2018-task-1 |
Repo | |
Framework | |
Unsupervised Learning of Entailment-Vector Word Embeddings
Title | Unsupervised Learning of Entailment-Vector Word Embeddings |
Authors | James Henderson |
Abstract | Entailment vectors are a principled way to encode in a vector what information is known and what is unknown. They are designed to model relations where one vector should include all the information in another vector, called entailment. This paper investigates the unsupervised learning of entailment vectors for the semantics of words. Using simple entailment-based models of the semantics of words in text (distributional semantics), we induce entailment-vector word embeddings which outperform the best previous results for predicting entailment between words, in unsupervised and semi-supervised experiments on hyponymy. |
Tasks | Word Embeddings |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=S1Q79heRW |
https://openreview.net/pdf?id=S1Q79heRW | |
PWC | https://paperswithcode.com/paper/unsupervised-learning-of-entailment-vector |
Repo | |
Framework | |
Obituary: Aravind K. Joshi
Title | Obituary: Aravind K. Joshi |
Authors | Bonnie Webber |
Abstract | |
Tasks | |
Published | 2018-09-01 |
URL | https://www.aclweb.org/anthology/J18-3001/ |
https://www.aclweb.org/anthology/J18-3001 | |
PWC | https://paperswithcode.com/paper/obituary-aravind-k-joshi |
Repo | |
Framework | |