Paper Group NANR 131
Target-side Word Segmentation Strategies for Neural Machine Translation. IMS at EmoInt-2017: Emotion Intensity Prediction with Affective Norms, Automatically Extended Resources and Deep Learning. Noise Reduction Methods for Distantly Supervised Biomedical Relation Extraction. Cross-lingual Flames Detection in News Discussions. IKM at SemEval-2017 T …
Target-side Word Segmentation Strategies for Neural Machine Translation
| Title | Target-side Word Segmentation Strategies for Neural Machine Translation |
| Authors | Matthias Huck, Simon Riess, Alex Fraser, er |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4706/ |
| https://www.aclweb.org/anthology/W17-4706 | |
| PWC | https://paperswithcode.com/paper/target-side-word-segmentation-strategies-for |
| Repo | |
| Framework | |
IMS at EmoInt-2017: Emotion Intensity Prediction with Affective Norms, Automatically Extended Resources and Deep Learning
| Title | IMS at EmoInt-2017: Emotion Intensity Prediction with Affective Norms, Automatically Extended Resources and Deep Learning |
| Authors | Maximilian K{"o}per, Evgeny Kim, Roman Klinger |
| Abstract | Our submission to the WASSA-2017 shared task on the prediction of emotion intensity in tweets is a supervised learning method with extended lexicons of affective norms. We combine three main information sources in a random forrest regressor, namely (1), manually created resources, (2) automatically extended lexicons, and (3) the output of a neural network (CNN-LSTM) for sentence regression. All three feature sets perform similarly well in isolation ({\mbox{$\approx$}} .67 macro average Pearson correlation). The combination achieves .72 on the official test set (ranked 2nd out of 22 participants). Our analysis reveals that performance is increased by providing cross-emotional intensity predictions. The automatic extension of lexicon features benefit from domain specific embeddings. Complementary ratings for affective norms increase the impact of lexicon features. Our resources (ratings for 1.6 million twitter specific words) and our implementation is publicly available at \url{http://www.ims.uni-stuttgart.de/data/ims_emoint}. |
| Tasks | Emotion Recognition, Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5206/ |
| https://www.aclweb.org/anthology/W17-5206 | |
| PWC | https://paperswithcode.com/paper/ims-at-emoint-2017-emotion-intensity |
| Repo | |
| Framework | |
Noise Reduction Methods for Distantly Supervised Biomedical Relation Extraction
| Title | Noise Reduction Methods for Distantly Supervised Biomedical Relation Extraction |
| Authors | Gang Li, Cathy Wu, K. Vijay-Shanker |
| Abstract | Distant supervision has been applied to automatically generate labeled data for biomedical relation extraction. Noise exists in both positively and negatively-labeled data and affects the performance of supervised machine learning methods. In this paper, we propose three novel heuristics based on the notion of proximity, trigger word and confidence of patterns to leverage lexical and syntactic information to reduce the level of noise in the distantly labeled data. Experiments on three different tasks, extraction of protein-protein-interaction, miRNA-gene regulation relation and protein-localization event, show that the proposed methods can improve the F-score over the baseline by 6, 10 and 14 points for the three tasks, respectively. We also show that when the models are configured to output high-confidence results, high precisions can be obtained using the proposed methods, making them promising for facilitating manual curation for databases. |
| Tasks | Relation Extraction |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2323/ |
| https://www.aclweb.org/anthology/W17-2323 | |
| PWC | https://paperswithcode.com/paper/noise-reduction-methods-for-distantly |
| Repo | |
| Framework | |
Cross-lingual Flames Detection in News Discussions
| Title | Cross-lingual Flames Detection in News Discussions |
| Authors | Josef Steinberger, Tom{'a}{\v{s}} Brychc{'\i}n, Tom{'a}{\v{s}} Hercig, Peter Krejzl |
| Abstract | We introduce Flames Detector, an online system for measuring flames, i.e. strong negative feelings or emotions, insults or other verbal offences, in news commentaries across five languages. It is designed to assist journalists, public institutions or discussion moderators to detect news topics which evoke wrangles. We propose a machine learning approach to flames detection and calculate an aggregated score for a set of comment threads. The demo application shows the most flaming topics of the current period in several language variants. The search functionality gives a possibility to measure flames in any topic specified by a query. The evaluation shows that the flame detection in discussions is a difficult task, however, the application can already reveal interesting information about the actual news discussions. |
| Tasks | Sarcasm Detection, Sentiment Analysis, Stance Detection |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1089/ |
| https://doi.org/10.26615/978-954-452-049-6_089 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-flames-detection-in-news |
| Repo | |
| Framework | |
IKM at SemEval-2017 Task 8: Convolutional Neural Networks for stance detection and rumor verification
| Title | IKM at SemEval-2017 Task 8: Convolutional Neural Networks for stance detection and rumor verification |
| Authors | Yi-Chin Chen, Zhao-Yang Liu, Hung-Yu Kao |
| Abstract | This paper describes our approach for SemEval-2017 Task 8. We aim at detecting the stance of tweets and determining the veracity of the given rumor. We utilize a convolutional neural network for short text categorization using multiple filter sizes. Our approach beats the baseline classifiers on different event data with good F1 scores. The best of our submitted runs achieves rank 1st among all scores on subtask B. |
| Tasks | Stance Detection, Text Categorization |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2081/ |
| https://www.aclweb.org/anthology/S17-2081 | |
| PWC | https://paperswithcode.com/paper/ikm-at-semeval-2017-task-8-convolutional |
| Repo | |
| Framework | |
Proceedings of Language, Ontology, Terminology and Knowledge Structures Workshop (LOTKS 2017)
| Title | Proceedings of Language, Ontology, Terminology and Knowledge Structures Workshop (LOTKS 2017) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-7000/ |
| https://www.aclweb.org/anthology/W17-7000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-language-ontology-terminology |
| Repo | |
| Framework | |
NRU-HSE at SemEval-2017 Task 4: Tweet Quantification Using Deep Learning Architecture
| Title | NRU-HSE at SemEval-2017 Task 4: Tweet Quantification Using Deep Learning Architecture |
| Authors | Nikolay Karpov |
| Abstract | In many areas, such as social science, politics or market research, people need to deal with dataset shifting over time. Distribution drift phenomenon usually appears in the field of sentiment analysis, when proportions of instances are changing over time. In this case, the task is to correctly estimate proportions of each sentiment expressed in the set of documents (quantification task). Basically, our study was aimed to analyze the effectiveness of a mixture of quantification technique with one of deep learning architecture. All the techniques are evaluated using the SemEval-2017 Task4 dataset and source code, mentioned in this paper and available online in the Python programming language. The results of an application of the quantification techniques are discussed. |
| Tasks | Opinion Mining, Sentiment Analysis, Text Classification, Word Sense Disambiguation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2113/ |
| https://www.aclweb.org/anthology/S17-2113 | |
| PWC | https://paperswithcode.com/paper/nru-hse-at-semeval-2017-task-4-tweet |
| Repo | |
| Framework | |
Attention-based Recurrent Convolutional Neural Network for Automatic Essay Scoring
| Title | Attention-based Recurrent Convolutional Neural Network for Automatic Essay Scoring |
| Authors | Fei Dong, Yue Zhang, Jie Yang |
| Abstract | Neural network models have recently been applied to the task of automatic essay scoring, giving promising results. Existing work used recurrent neural networks and convolutional neural networks to model input essays, giving grades based on a single vector representation of the essay. On the other hand, the relative advantages of RNNs and CNNs have not been compared. In addition, different parts of the essay can contribute differently for scoring, which is not captured by existing models. We address these issues by building a hierarchical sentence-document model to represent essays, using the attention mechanism to automatically decide the relative weights of words and sentences. Results show that our model outperforms the previous state-of-the-art methods, demonstrating the effectiveness of the attention mechanism. |
| Tasks | Feature Engineering, Machine Translation, Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-1017/ |
| https://www.aclweb.org/anthology/K17-1017 | |
| PWC | https://paperswithcode.com/paper/attention-based-recurrent-convolutional |
| Repo | |
| Framework | |
Stance Detection in Facebook Posts of a German Right-wing Party
| Title | Stance Detection in Facebook Posts of a German Right-wing Party |
| Authors | Manfred Klenner, Don Tuggener, Simon Clematide |
| Abstract | We argue that in order to detect stance, not only the explicit attitudes of the stance holder towards the targets are crucial. It is the whole narrative the writer drafts that counts, including the way he hypostasizes the discourse referents: as benefactors or villains, as victims or beneficiaries. We exemplify the ability of our system to identify targets and detect the writer{'}s stance towards them on the basis of about 100 000 Facebook posts of a German right-wing party. A reader and writer model on top of our verb-based attitude extraction directly reveal stance conflicts. |
| Tasks | Relation Extraction, Stance Detection |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0904/ |
| https://www.aclweb.org/anthology/W17-0904 | |
| PWC | https://paperswithcode.com/paper/stance-detection-in-facebook-posts-of-a |
| Repo | |
| Framework | |
Effective Domain Mixing for Neural Machine Translation
| Title | Effective Domain Mixing for Neural Machine Translation |
| Authors | Denny Britz, Quoc Le, Reid Pryzant |
| Abstract | |
| Tasks | Domain Adaptation, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4712/ |
| https://www.aclweb.org/anthology/W17-4712 | |
| PWC | https://paperswithcode.com/paper/effective-domain-mixing-for-neural-machine |
| Repo | |
| Framework | |
Copied Monolingual Data Improves Low-Resource Neural Machine Translation
| Title | Copied Monolingual Data Improves Low-Resource Neural Machine Translation |
| Authors | Anna Currey, Antonio Valerio Miceli Barone, Kenneth Heafield |
| Abstract | |
| Tasks | Low-Resource Neural Machine Translation, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4715/ |
| https://www.aclweb.org/anthology/W17-4715 | |
| PWC | https://paperswithcode.com/paper/copied-monolingual-data-improves-low-resource |
| Repo | |
| Framework | |
University of Rochester WMT 2017 NMT System Submission
| Title | University of Rochester WMT 2017 NMT System Submission |
| Authors | Chester Holtz, Chuyang Ke, Daniel Gildea |
| Abstract | |
| Tasks | Language Modelling, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4729/ |
| https://www.aclweb.org/anthology/W17-4729 | |
| PWC | https://paperswithcode.com/paper/university-of-rochester-wmt-2017-nmt-system |
| Repo | |
| Framework | |
Forewords
| Title | Forewords |
| Authors | Chi-Chun Jeremy Lee, Cheng-Zen Yang |
| Abstract | |
| Tasks | Emotion Recognition, Intent Classification, Question Answering, Speech Emotion Recognition |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/O17-3001/ |
| https://www.aclweb.org/anthology/O17-3001 | |
| PWC | https://paperswithcode.com/paper/forewords |
| Repo | |
| Framework | |
Classifying Languages by Dependency Structure. Typologies of Delexicalized Universal Dependency Treebanks
| Title | Classifying Languages by Dependency Structure. Typologies of Delexicalized Universal Dependency Treebanks |
| Authors | Xinying Chen, Kim Gerdes |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6508/ |
| https://www.aclweb.org/anthology/W17-6508 | |
| PWC | https://paperswithcode.com/paper/classifying-languages-by-dependency-structure |
| Repo | |
| Framework | |
Menzerath-Altmann Law in Syntactic Dependency Structure
| Title | Menzerath-Altmann Law in Syntactic Dependency Structure |
| Authors | J{'a}n Ma{\v{c}}utek, Radek {\v{C}}ech, Ji{\v{r}}{'\i} Mili{\v{c}}ka |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6513/ |
| https://www.aclweb.org/anthology/W17-6513 | |
| PWC | https://paperswithcode.com/paper/menzerath-altmann-law-in-syntactic-dependency |
| Repo | |
| Framework | |
