Paper Group NANR 124
Cross-Lingual Classification of Topics in Political Texts. Mining Social Science Publications for Survey Variables. Modelling Participation in Small Group Social Sequences with Markov Rewards Analysis. How Does Twitter User Behavior Vary Across Demographic Groups?. Latest News in Computational Argumentation: Surfing on the Deep Learning Wave, Scuba …
Cross-Lingual Classification of Topics in Political Texts
| Title | Cross-Lingual Classification of Topics in Political Texts |
| Authors | Goran Glava{\v{s}}, Federico Nanni, Simone Paolo Ponzetto |
| Abstract | In this paper, we propose an approach for cross-lingual topical coding of sentences from electoral manifestos of political parties in different languages. To this end, we exploit continuous semantic text representations and induce a joint multilingual semantic vector spaces to enable supervised learning using manually-coded sentences across different languages. Our experimental results show that classifiers trained on multilingual data yield performance boosts over monolingual topic classification. |
| Tasks | Text Classification, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2906/ |
| https://www.aclweb.org/anthology/W17-2906 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-classification-of-topics-in |
| Repo | |
| Framework | |
Mining Social Science Publications for Survey Variables
| Title | Mining Social Science Publications for Survey Variables |
| Authors | Andrea Zielinski, Peter Mutschke |
| Abstract | Research in Social Science is usually based on survey data where individual research questions relate to observable concepts (variables). However, due to a lack of standards for data citations a reliable identification of the variables used is often difficult. In this paper, we present a work-in-progress study that seeks to provide a solution to the variable detection task based on supervised machine learning algorithms, using a linguistic analysis pipeline to extract a rich feature set, including terminological concepts and similarity metric scores. Further, we present preliminary results on a small dataset that has been specifically designed for this task, yielding a significant increase in performance over the random baseline. |
| Tasks | Paraphrase Identification, Question Answering |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2907/ |
| https://www.aclweb.org/anthology/W17-2907 | |
| PWC | https://paperswithcode.com/paper/mining-social-science-publications-for-survey |
| Repo | |
| Framework | |
Modelling Participation in Small Group Social Sequences with Markov Rewards Analysis
| Title | Modelling Participation in Small Group Social Sequences with Markov Rewards Analysis |
| Authors | Gabriel Murray |
| Abstract | We explore a novel computational approach for analyzing member participation in small group social sequences. Using a complex state representation combining information about dialogue act types, sentiment expression, and participant roles, we explore which sequence states are associated with high levels of member participation. Using a Markov Rewards framework, we associate particular states with immediate positive and negative rewards, and employ a Value Iteration algorithm to calculate the expected value of all states. In our findings, we focus on discourse states belonging to team leaders and project managers which are either very likely or very unlikely to lead to participation from the rest of the group members. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2910/ |
| https://www.aclweb.org/anthology/W17-2910 | |
| PWC | https://paperswithcode.com/paper/modelling-participation-in-small-group-social |
| Repo | |
| Framework | |
How Does Twitter User Behavior Vary Across Demographic Groups?
| Title | How Does Twitter User Behavior Vary Across Demographic Groups? |
| Authors | Zach Wood-Doughty, Michael Smith, David Broniatowski, Mark Dredze |
| Abstract | Demographically-tagged social media messages are a common source of data for computational social science. While these messages can indicate differences in beliefs and behaviors between demographic groups, we do not have a clear understanding of how different demographic groups use platforms such as Twitter. This paper presents a preliminary analysis of how groups{'} differing behaviors may confound analyses of the groups themselves. We analyzed one million Twitter users by first inferring demographic attributes, and then measuring several indicators of Twitter behavior. We find differences in these indicators across demographic groups, suggesting that there may be underlying differences in how different demographic groups use Twitter. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2912/ |
| https://www.aclweb.org/anthology/W17-2912 | |
| PWC | https://paperswithcode.com/paper/how-does-twitter-user-behavior-vary-across |
| Repo | |
| Framework | |
Latest News in Computational Argumentation: Surfing on the Deep Learning Wave, Scuba Diving in the Abyss of Fundamental Questions
| Title | Latest News in Computational Argumentation: Surfing on the Deep Learning Wave, Scuba Diving in the Abyss of Fundamental Questions |
| Authors | Iryna Gurevych |
| Abstract | Mining arguments from natural language texts, parsing argumentative structures, and assessing argument quality are among the recent challeng-es tackled in computational argumentation. While advanced deep learning models provide state-of-the-art performance in many of these tasks, much attention is also paid to the underly-ing fundamental questions. How are arguments expressed in natural language across genres and domains? What is the essence of an argument{'}s claim? Can we reliably annotate convincingness of an argument? How can we approach logic and common-sense reasoning in argumentation? This talk highlights some recent advances in computa-tional argumentation and shows why researchers must be both {}surfers{''} and {}scuba divers{''}. |
| Tasks | Common Sense Reasoning |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5208/ |
| https://www.aclweb.org/anthology/W17-5208 | |
| PWC | https://paperswithcode.com/paper/latest-news-in-computational-argumentation |
| Repo | |
| Framework | |
Keyword Index
| Title | Keyword Index |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7626/ |
| https://www.aclweb.org/anthology/W17-7626 | |
| PWC | https://paperswithcode.com/paper/keyword-index |
| Repo | |
| Framework | |
Large-Scale Categorization of Japanese Product Titles Using Neural Attention Models
| Title | Large-Scale Categorization of Japanese Product Titles Using Neural Attention Models |
| Authors | Y Xia, i, Aaron Levine, Pradipto Das, Giuseppe Di Fabbrizio, Keiji Shinzato, Ankur Datta |
| Abstract | We propose a variant of Convolutional Neural Network (CNN) models, the Attention CNN (ACNN); for large-scale categorization of millions of Japanese items into thirty-five product categories. Compared to a state-of-the-art Gradient Boosted Tree (GBT) classifier, the proposed model reduces training time from three weeks to three days while maintaining more than 96{%} accuracy. Additionally, our proposed model characterizes products by imputing attentive focus on word tokens in a language agnostic way. The attention words have been observed to be semantically highly correlated with the predicted categories and give us a choice of automatic feature extraction for downstream processing. |
| Tasks | Feature Engineering, Product Categorization, Text Categorization |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2105/ |
| https://www.aclweb.org/anthology/E17-2105 | |
| PWC | https://paperswithcode.com/paper/large-scale-categorization-of-japanese |
| Repo | |
| Framework | |
Illegal is not a Noun: Linguistic Form for Detection of Pejorative Nominalizations
| Title | Illegal is not a Noun: Linguistic Form for Detection of Pejorative Nominalizations |
| Authors | Alexis Palmer, Melissa Robinson, Kristy K. Phillips |
| Abstract | This paper focuses on a particular type of abusive language, targeting expressions in which typically neutral adjectives take on pejorative meaning when used as nouns - compare {}gay people{'} to {}the gays{'}. We first collect and analyze a corpus of hand-curated, expert-annotated pejorative nominalizations for four target adjectives: female, gay, illegal, and poor. We then collect a second corpus of automatically-extracted and POS-tagged, crowd-annotated tweets. For both corpora, we find support for the hypothesis that some adjectives, when nominalized, take on negative meaning. The targeted constructions are non-standard yet widely-used, and part-of-speech taggers mistag some nominal forms as adjectives. We implement a tool called NomCatcher to correct these mistaggings, and find that the same tool is effective for identifying new adjectives subject to transformation via nominalization into abusive language. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-3014/ |
| https://www.aclweb.org/anthology/W17-3014 | |
| PWC | https://paperswithcode.com/paper/illegal-is-not-a-noun-linguistic-form-for |
| Repo | |
| Framework | |
Bootstrapping Unsupervised Bilingual Lexicon Induction
| Title | Bootstrapping Unsupervised Bilingual Lexicon Induction |
| Authors | Bradley Hauer, Garrett Nicolai, Grzegorz Kondrak |
| Abstract | The task of unsupervised lexicon induction is to find translation pairs across monolingual corpora. We develop a novel method that creates seed lexicons by identifying cognates in the vocabularies of related languages on the basis of their frequency and lexical similarity. We apply bidirectional bootstrapping to a method which learns a linear mapping between context-based vector spaces. Experimental results on three language pairs show consistent improvement over prior work. |
| Tasks | Semantic Textual Similarity |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2098/ |
| https://www.aclweb.org/anthology/E17-2098 | |
| PWC | https://paperswithcode.com/paper/bootstrapping-unsupervised-bilingual-lexicon |
| Repo | |
| Framework | |
Deep Dynamic Poisson Factorization Model
| Title | Deep Dynamic Poisson Factorization Model |
| Authors | Chengyue Gong, Win-Bin Huang |
| Abstract | A new model, named as deep dynamic poisson factorization model, is proposed in this paper for analyzing sequential count vectors. The model based on the Poisson Factor Analysis method captures dependence among time steps by neural networks, representing the implicit distributions. Local complicated relationship is obtained from local implicit distribution, and deep latent structure is exploited to get the long-time dependence. Variational inference on latent variables and gradient descent based on the loss functions derived from variational distribution is performed in our inference. Synthetic datasets and real-world datasets are applied to the proposed model and our results show good predicting and fitting performance with interpretable latent structure. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6764-deep-dynamic-poisson-factorization-model |
| http://papers.nips.cc/paper/6764-deep-dynamic-poisson-factorization-model.pdf | |
| PWC | https://paperswithcode.com/paper/deep-dynamic-poisson-factorization-model |
| Repo | |
| Framework | |
A vis-`a-vis evaluation of MT paradigms for linguistically distant languages
| Title | A vis-`a-vis evaluation of MT paradigms for linguistically distant languages |
| Authors | Ruchit Agrawal, Jahfar Ali, Dipti Misra Sharma |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7505/ |
| https://www.aclweb.org/anthology/W17-7505 | |
| PWC | https://paperswithcode.com/paper/a-vis-a-vis-evaluation-of-mt-paradigms-for |
| Repo | |
| Framework | |
A Modelagem Computacional do Dom'\inio dos Esportes na FrameNet Brasil (The Computational Modeling of the Sports Domain in FrameNet Brasil)[In Portuguese]
| Title | A Modelagem Computacional do Dom'\inio dos Esportes na FrameNet Brasil (The Computational Modeling of the Sports Domain in FrameNet Brasil)[In Portuguese] |
| Authors | Alex Costa, re Diniz, Tiago Timponi Torrent |
| Abstract | |
| Tasks | |
| Published | 2017-10-01 |
| URL | https://www.aclweb.org/anthology/W17-6623/ |
| https://www.aclweb.org/anthology/W17-6623 | |
| PWC | https://paperswithcode.com/paper/a-modelagem-computacional-do-domanio-dos |
| Repo | |
| Framework | |
Count-Invariance Including Exponentials
| Title | Count-Invariance Including Exponentials |
| Authors | Stepan Kuznetsov, Glyn Morrill, Oriol Valent{'\i}n |
| Abstract | |
| Tasks | Automated Theorem Proving |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/W17-3413/ |
| https://www.aclweb.org/anthology/W17-3413 | |
| PWC | https://paperswithcode.com/paper/count-invariance-including-exponentials |
| Repo | |
| Framework | |
Detecting Cross-Lingual Semantic Divergence for Neural Machine Translation
| Title | Detecting Cross-Lingual Semantic Divergence for Neural Machine Translation |
| Authors | Marine Carpuat, Yogarshi Vyas, Xing Niu |
| Abstract | Parallel corpora are often not as parallel as one might assume: non-literal translations and noisy translations abound, even in curated corpora routinely used for training and evaluation. We use a cross-lingual textual entailment system to distinguish sentence pairs that are parallel in meaning from those that are not, and show that filtering out divergent examples from training improves translation quality. |
| Tasks | Domain Adaptation, Machine Translation, Natural Language Inference |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-3209/ |
| https://www.aclweb.org/anthology/W17-3209 | |
| PWC | https://paperswithcode.com/paper/detecting-cross-lingual-semantic-divergence |
| Repo | |
| Framework | |
DialPort, Gone Live: An Update After A Year of Development
| Title | DialPort, Gone Live: An Update After A Year of Development |
| Authors | Kyusong Lee, Tiancheng Zhao, Yulun Du, Edward Cai, Allen Lu, Eli Pincus, David Traum, Stefan Ultes, Lina M. Rojas-Barahona, Milica Gasic, Steve Young, Maxine Eskenazi |
| Abstract | DialPort collects user data for connected spoken dialog systems. At present six systems are linked to a central portal that directs the user to the applicable system and suggests systems that the user may be interested in. User data has started to flow into the system. |
| Tasks | Chatbot |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-5521/ |
| https://www.aclweb.org/anthology/W17-5521 | |
| PWC | https://paperswithcode.com/paper/dialport-gone-live-an-update-after-a-year-of |
| Repo | |
| Framework | |
