Paper Group NANR 255
The Role of Pragmatic and Discourse Context in Determining Argument Impact. KMI-Coling at SemEval-2019 Task 6: Exploring N-grams for Offensive Language detection. LTL-UDE at SemEval-2019 Task 6: BERT and Two-Vote Classification for Categorizing Offensiveness. Learning Words by Drawing Images. SphereRE: Distinguishing Lexical Relations with Hypersph …
The Role of Pragmatic and Discourse Context in Determining Argument Impact
| Title | The Role of Pragmatic and Discourse Context in Determining Argument Impact |
| Authors | Esin Durmus, Faisal Ladhak, Claire Cardie |
| Abstract | Research in the social sciences and psychology has shown that the persuasiveness of an argument depends not only the language employed, but also on attributes of the source/communicator, the audience, and the appropriateness and strength of the argument{'}s claims given the pragmatic and discourse context of the argument. Among these characteristics of persuasive arguments, prior work in NLP does not explicitly investigate the effect of the pragmatic and discourse context when determining argument quality. This paper presents a new dataset to initiate the study of this aspect of argumentation: it consists of a diverse collection of arguments covering 741 controversial topics and comprising over 47,000 claims. We further propose predictive models that incorporate the pragmatic and discourse context of argumentative claims and show that they outperform models that rely only on claim-specific linguistic features for predicting the perceived impact of individual claims within a particular line of argument. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1568/ |
| https://www.aclweb.org/anthology/D19-1568 | |
| PWC | https://paperswithcode.com/paper/the-role-of-pragmatic-and-discourse-context |
| Repo | |
| Framework | |
KMI-Coling at SemEval-2019 Task 6: Exploring N-grams for Offensive Language detection
| Title | KMI-Coling at SemEval-2019 Task 6: Exploring N-grams for Offensive Language detection |
| Authors | Priya Rani, Atul Kr. Ojha |
| Abstract | In this paper, we present the system description of Offensive language detection tool which is developed by the KMI{_}Coling under the OffensEval Shared task. The OffensEval Shared Task was conducted in SemEval 2019 workshop. To develop the system, we have explored n-grams up to 8-gram and trained three different namely A, B and C systems for three different subtasks within the OffensEval task which achieves 79.76{%}, 87.91{%} and 44.37{%} accuracy respectively. The task was completed using the dataset provided to us by the OffensEval organisers was the part of OLID dataset. It consists of 13,240 tweets extracted from twitter and were annotated at three levels using crowdsourcing. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2119/ |
| https://www.aclweb.org/anthology/S19-2119 | |
| PWC | https://paperswithcode.com/paper/kmi-coling-at-semeval-2019-task-6-exploring-n |
| Repo | |
| Framework | |
LTL-UDE at SemEval-2019 Task 6: BERT and Two-Vote Classification for Categorizing Offensiveness
| Title | LTL-UDE at SemEval-2019 Task 6: BERT and Two-Vote Classification for Categorizing Offensiveness |
| Authors | Piush Aggarwal, Tobias Horsmann, Michael Wojatzki, Torsten Zesch |
| Abstract | We present results for Subtask A and C of SemEval 2019 Shared Task 6. In Subtask A, we experiment with an embedding representation of postings and use BERT to categorize postings. Our best result reaches the 10th place (out of 103). In Subtask C, we applied a two-vote classification approach with minority fallback, which is placed on the 19th rank (out of 65). |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2121/ |
| https://www.aclweb.org/anthology/S19-2121 | |
| PWC | https://paperswithcode.com/paper/ltl-ude-at-semeval-2019-task-6-bert-and-two |
| Repo | |
| Framework | |
Learning Words by Drawing Images
| Title | Learning Words by Drawing Images |
| Authors | Didac Suris, Adria Recasens, David Bau, David Harwath, James Glass, Antonio Torralba |
| Abstract | We propose a framework for learning through drawing. Our goal is to learn the correspondence between spoken words and abstract visual attributes, from a dataset of spoken descriptions of images. Building upon recent findings that GAN representations can be manipulated to edit semantic concepts in the generated output, we propose a new method to use such GAN-generated images to train a model using a triplet loss. To apply the method, we develop Audio CLEVRGAN, a new dataset of audio descriptions of GAN-generated CLEVR images, and we describe a training procedure that creates a curriculum of GAN-generated images that focuses training on image pairs that differ in a specific, informative way. Training is done without additional supervision beyond the spoken captions and the GAN. We find that training that takes advantage of GAN-generated edited examples results in improvements in the model’s ability to learn attributes compared to previous results. Our proposed learning framework also results in models that can associate spoken words with some abstract visual concepts such as color and size. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Suris_Learning_Words_by_Drawing_Images_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Suris_Learning_Words_by_Drawing_Images_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-words-by-drawing-images |
| Repo | |
| Framework | |
SphereRE: Distinguishing Lexical Relations with Hyperspherical Relation Embeddings
| Title | SphereRE: Distinguishing Lexical Relations with Hyperspherical Relation Embeddings |
| Authors | Chengyu Wang, Xiaofeng He, Aoying Zhou |
| Abstract | Lexical relations describe how meanings of terms relate to each other. Typical examples include hypernymy, synonymy, meronymy, etc. Automatic distinction of lexical relations is vital for NLP applications, and also challenging due to the lack of contextual signals to discriminate between such relations. In this work, we present a neural representation learning model to distinguish lexical relations among term pairs based on Hyperspherical Relation Embeddings (SphereRE). Rather than learning embeddings for individual terms, the model learns representations of relation triples by mapping them to the hyperspherical embedding space, where relation triples of different lexical relations are well separated. Experiments over several benchmarks confirm SphereRE outperforms state-of-the-arts. |
| Tasks | Representation Learning |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1169/ |
| https://www.aclweb.org/anthology/P19-1169 | |
| PWC | https://paperswithcode.com/paper/spherere-distinguishing-lexical-relations |
| Repo | |
| Framework | |
NIT_Agartala_NLP_Team at SemEval-2019 Task 6: An Ensemble Approach to Identifying and Categorizing Offensive Language in Twitter Social Media Corpora
| Title | NIT_Agartala_NLP_Team at SemEval-2019 Task 6: An Ensemble Approach to Identifying and Categorizing Offensive Language in Twitter Social Media Corpora |
| Authors | Steve Durairaj Swamy, Anupam Jamatia, Bj{"o}rn Gamb{"a}ck, Amitava Das |
| Abstract | The paper describes the systems submitted to OffensEval (SemEval 2019, Task 6) on {}Identifying and Categorizing Offensive Language in Social Media{'} by the {}NIT{_}Agartala{_}NLP{_}Team{'}. A Twitter annotated dataset of 13,240 English tweets was provided by the task organizers to train the individual models, with the best results obtained using an ensemble model composed of six different classifiers. The ensemble model produced macro-averaged F1-scores of 0.7434, 0.7078 and 0.4853 on Subtasks A, B, and C, respectively. The paper highlights the overall low predictive nature of various linguistic features and surface level count features, as well as the limitations of a traditional machine learning approach when compared to a Deep Learning counterpart. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2124/ |
| https://www.aclweb.org/anthology/S19-2124 | |
| PWC | https://paperswithcode.com/paper/nit_agartala_nlp_team-at-semeval-2019-task-6 |
| Repo | |
| Framework | |
SINAI at SemEval-2019 Task 6: Incorporating lexicon knowledge into SVM learning to identify and categorize offensive language in social media
| Title | SINAI at SemEval-2019 Task 6: Incorporating lexicon knowledge into SVM learning to identify and categorize offensive language in social media |
| Authors | Flor Miriam Plaza-del-Arco, M. Dolores Molina-Gonz{'a}lez, Maite Martin, L. Alfonso Ure{~n}a-L{'o}pez |
| Abstract | Offensive language has an impact across society. The use of social media has aggravated this issue among online users, causing suicides in the worst cases. For this reason, it is important to develop systems capable of identifying and detecting offensive language in text automatically. In this paper, we developed a system to classify offensive tweets as part of our participation in SemEval-2019 Task 6: OffensEval. Our main contribution is the integration of lexical features in the classification using the SVM algorithm. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2129/ |
| https://www.aclweb.org/anthology/S19-2129 | |
| PWC | https://paperswithcode.com/paper/sinai-at-semeval-2019-task-6-incorporating |
| Repo | |
| Framework | |
Learning to Flip the Sentiment of Reviews from Non-Parallel Corpora
| Title | Learning to Flip the Sentiment of Reviews from Non-Parallel Corpora |
| Authors | Canasai Kruengkrai |
| Abstract | Flipping sentiment while preserving sentence meaning is challenging because parallel sentences with the same content but different sentiment polarities are not always available for model learning. We introduce a method for acquiring imperfectly aligned sentences from non-parallel corpora and propose a model that learns to minimize the sentiment and content losses in a fully end-to-end manner. Our model is simple and offers well-balanced results across two domains: Yelp restaurant and Amazon product reviews. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1659/ |
| https://www.aclweb.org/anthology/D19-1659 | |
| PWC | https://paperswithcode.com/paper/learning-to-flip-the-sentiment-of-reviews |
| Repo | |
| Framework | |
T"uKaSt at SemEval-2019 Task 6: Something Old, Something Neu(ral): Traditional and Neural Approaches to Offensive Text Classification
| Title | T"uKaSt at SemEval-2019 Task 6: Something Old, Something Neu(ral): Traditional and Neural Approaches to Offensive Text Classification |
| Authors | Madeeswaran Kannan, Lukas Stein |
| Abstract | We describe our system (T{"u}KaSt) submitted for Task 6: Offensive Language Classification, at SemEval 2019. We developed multiple SVM classifier models that used sentence-level dense vector representations of tweets enriched with sentiment information and term-weighting. Our best results achieved F1 scores of 0.734, 0.660 and 0.465 in the first, second and third sub-tasks respectively. We also describe a neural network model that was developed in parallel but not used during evaluation due to time constraints. |
| Tasks | Text Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2134/ |
| https://www.aclweb.org/anthology/S19-2134 | |
| PWC | https://paperswithcode.com/paper/tukast-at-semeval-2019-task-6-something-old |
| Repo | |
| Framework | |
Stop PropagHate at SemEval-2019 Tasks 5 and 6: Are abusive language classification results reproducible?
| Title | Stop PropagHate at SemEval-2019 Tasks 5 and 6: Are abusive language classification results reproducible? |
| Authors | Paula Fortuna, Juan Soler-Company, S{'e}rgio Nunes |
| Abstract | This paper summarizes the participation of Stop PropagHate team at SemEval 2019. Our approach is based on replicating one of the most relevant works on the literature, using word embeddings and LSTM. After circumventing some of the problems of the original code, we found poor results when applying it to the HatEval contest (F1=0.45). We think this is due mainly to inconsistencies in the data of this contest. Finally, for the OffensEval the classifier performed well (F1=0.74), proving to have a better performance for offense detection than for hate speech. |
| Tasks | Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2131/ |
| https://www.aclweb.org/anthology/S19-2131 | |
| PWC | https://paperswithcode.com/paper/stop-propaghate-at-semeval-2019-tasks-5-and-6 |
| Repo | |
| Framework | |
A Family of Robust Stochastic Operators for Reinforcement Learning
| Title | A Family of Robust Stochastic Operators for Reinforcement Learning |
| Authors | Yingdong Lu, Mark Squillante, Chai Wah Wu |
| Abstract | We consider a new family of stochastic operators for reinforcement learning with the goal of alleviating negative effects and becoming more robust to approximation or estimation errors. Various theoretical results are established, which include showing that our family of operators preserve optimality and increase the action gap in a stochastic sense. Our empirical results illustrate the strong benefits of our robust stochastic operators, significantly outperforming the classical Bellman operator and recently proposed operators. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9696-a-family-of-robust-stochastic-operators-for-reinforcement-learning |
| http://papers.nips.cc/paper/9696-a-family-of-robust-stochastic-operators-for-reinforcement-learning.pdf | |
| PWC | https://paperswithcode.com/paper/a-family-of-robust-stochastic-operators-for |
| Repo | |
| Framework | |
Word Sense Disambiguation based on Constrained Random Walks in Linked Semantic Networks
| Title | Word Sense Disambiguation based on Constrained Random Walks in Linked Semantic Networks |
| Authors | Arkadiusz Janz, Maciej Piasecki |
| Abstract | Word Sense Disambiguation remains a challenging NLP task. Due to the lack of annotated training data, especially for rare senses, the supervised approaches are usually designed for specific subdomains limited to a narrow subset of identified senses. Recent advances in this area have shown that knowledge-based approaches are more scalable and obtain more promising results in all-words WSD scenarios. In this work we present a faster WSD algorithm based on the Monte Carlo approximation of sense probabilities given a context using constrained random walks over linked semantic networks. We show that the local semantic relatedness is mostly sufficient to successfully identify correct senses when an extensive knowledge base and a proper weighting scheme are used. The proposed methods are evaluated on English (SenseEval, SemEval) and Polish (Sk{\l}adnica, KPWr) datasets. |
| Tasks | Word Sense Disambiguation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1061/ |
| https://www.aclweb.org/anthology/R19-1061 | |
| PWC | https://paperswithcode.com/paper/word-sense-disambiguation-based-on |
| Repo | |
| Framework | |
TUVD team at SemEval-2019 Task 6: Offense Target Identification
| Title | TUVD team at SemEval-2019 Task 6: Offense Target Identification |
| Authors | Elena Shushkevich, John Cardiff, Paolo Rosso |
| Abstract | This article presents our approach for detecting a target of offensive messages in Twitter, including Individual, Group and Others classes. The model we have created is an ensemble of simpler models, including Logistic Regression, Naive Bayes, Support Vector Machine and the interpolation between Logistic Regression and Naive Bayes with 0.25 coefficient of interpolation. The model allows us to achieve 0.547 macro F1-score. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2135/ |
| https://www.aclweb.org/anthology/S19-2135 | |
| PWC | https://paperswithcode.com/paper/tuvd-team-at-semeval-2019-task-6-offense |
| Repo | |
| Framework | |
Multi-Objective Value Iteration with Parameterized Threshold-Based Safety Constraints
| Title | Multi-Objective Value Iteration with Parameterized Threshold-Based Safety Constraints |
| Authors | Hussein Sibai, Sayan Mitra |
| Abstract | We consider an environment with multiple reward functions. One of them represents goal achievement and the others represent instantaneous safety conditions. We consider a scenario where the safety rewards should always be above some thresholds. The thresholds are parameters with values that differ between users. %The thresholds are not known at the time the policy is being designed. We efficiently compute a family of policies that cover all threshold-based constraints and maximize the goal achievement reward. We introduce a new parameterized threshold-based scalarization method of the reward vector that encodes our objective. We present novel data structures to store the value functions of the Bellman equation that allow their efficient computation using the value iteration algorithm. We present results for both discrete and continuous state spaces. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HyeS73ActX |
| https://openreview.net/pdf?id=HyeS73ActX | |
| PWC | https://paperswithcode.com/paper/multi-objective-value-iteration-with |
| Repo | |
| Framework | |
Exploiting machine algorithms in vocalic quantification of African English corpora
| Title | Exploiting machine algorithms in vocalic quantification of African English corpora |
| Authors | Lasisi Adeiza Isiaka |
| Abstract | Towards procedural fidelity in the processing of African English speech corpora, this work demonstrates how the adaptation of machine-assisted segmentation of phonemes and automatic extraction of acoustic values can significantly speed up the processing of naturalistic data and make the vocalic analysis of the varieties less impressionistic. Research in African English phonology has, till date, been least data-driven {–} much less the use of comparative corpora for cross-varietal assessments. Using over 30 hours of naturalistic data (from 28 speakers in 5 Nigerian cities), the procedures for segmenting audio files into phonemic units via the Munich Automatic Segmentation System (MAUS), and the extraction of their spectral values in Praat are explained. Evidence from the speech corpora supports a more complex vocalic inventory than attested in previous auditory/manual-based accounts {–} thus reinforcing the resourcefulness of the algorithms for the current data and cognate varieties. Keywords: machine algorithms; naturalistic data; African English phonology; vowel segmentation |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3647/ |
| https://www.aclweb.org/anthology/W19-3647 | |
| PWC | https://paperswithcode.com/paper/exploiting-machine-algorithms-in-vocalic |
| Repo | |
| Framework | |
