Paper Group NANR 22
200K+ Crowdsourced Political Arguments for a New Chilean Constitution. Unsupervised AMR-Dependency Parse Alignment. Assessing the Verifiability of Attributions in News Text. SVNIT @ SemEval 2017 Task-6: Learning a Sense of Humor Using Supervised Approach. LIA at SemEval-2017 Task 4: An Ensemble of Neural Networks for Sentiment Classification. A Qua …
200K+ Crowdsourced Political Arguments for a New Chilean Constitution
| Title | 200K+ Crowdsourced Political Arguments for a New Chilean Constitution |
| Authors | Constanza Fierro, Claudio Fuentes, Jorge P{'e}rez, Mauricio Quezada |
| Abstract | In this paper we present the dataset of 200,000+ political arguments produced in the local phase of the 2016 Chilean constitutional process. We describe the human processing of this data by the government officials, and the manual tagging of arguments performed by members of our research group. Afterwards we focus on classification tasks that mimic the human processes, comparing linear methods with neural network architectures. The experiments show that some of the manual tasks are suitable for automatization. In particular, the best methods achieve a 90{%} top-5 accuracy in a multi-class classification of arguments, and 65{%} macro-averaged F1-score for tagging arguments according to a three-part argumentation model. |
| Tasks | Argument Mining |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5101/ |
| https://www.aclweb.org/anthology/W17-5101 | |
| PWC | https://paperswithcode.com/paper/200k-crowdsourced-political-arguments-for-a |
| Repo | |
| Framework | |
Unsupervised AMR-Dependency Parse Alignment
| Title | Unsupervised AMR-Dependency Parse Alignment |
| Authors | Wei-Te Chen, Martha Palmer |
| Abstract | In this paper, we introduce an Abstract Meaning Representation (AMR) to Dependency Parse aligner. Alignment is a preliminary step for AMR parsing, and our aligner improves current AMR parser performance. Our aligner involves several different features, including named entity tags and semantic role labels, and uses Expectation-Maximization training. Results show that our aligner reaches an 87.1{%} F-Score score with the experimental data, and enhances AMR parsing. |
| Tasks | Amr Parsing |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1053/ |
| https://www.aclweb.org/anthology/E17-1053 | |
| PWC | https://paperswithcode.com/paper/unsupervised-amr-dependency-parse-alignment |
| Repo | |
| Framework | |
Assessing the Verifiability of Attributions in News Text
| Title | Assessing the Verifiability of Attributions in News Text |
| Authors | Edward Newell, Ariane Schang, Drew Margolin, Derek Ruths |
| Abstract | When reporting the news, journalists rely on the statements of stakeholders, experts, and officials. The attribution of such a statement is verifiable if its fidelity to the source can be confirmed or denied. In this paper, we develop a new NLP task: determining the verifiability of an attribution based on linguistic cues. We operationalize the notion of verifiability as a score between 0 and 1 using human judgments in a comparison-based approach. Using crowdsourcing, we create a dataset of verifiability-scored attributions, and demonstrate a model that achieves an RMSE of 0.057 and Spearman{'}s rank correlation of 0.95 to human-generated scores. We discuss the application of this technique to the analysis of mass media. |
| Tasks | Question Answering |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1076/ |
| https://www.aclweb.org/anthology/I17-1076 | |
| PWC | https://paperswithcode.com/paper/assessing-the-verifiability-of-attributions |
| Repo | |
| Framework | |
SVNIT @ SemEval 2017 Task-6: Learning a Sense of Humor Using Supervised Approach
| Title | SVNIT @ SemEval 2017 Task-6: Learning a Sense of Humor Using Supervised Approach |
| Authors | Rutal Mahajan, Mukesh Zaveri |
| Abstract | This paper describes the system devel-oped for SemEval 2017 task 6: {#}HashTagWars -Learning a Sense of Hu-mor. Learning to recognize sense of hu-mor is the important task for language understanding applications. Different set of features based on frequency of words, structure of tweets and semantics are used in this system to identify the presence of humor in tweets. Supervised machine learning approaches, Multilayer percep-tron and Na{"\i}ve Bayes are used to classify the tweets in to three level of sense of humor. For given Hashtag, the system finds the funniest tweet and predicts the amount of funniness of all the other tweets. In official submitted runs, we have achieved 0.506 accuracy using mul-tilayer perceptron in subtask-A and 0.938 distance in subtask-B. Using Na{"\i}ve bayes in subtask-B, the system achieved 0.949 distance. Apart from official runs, this system have scored 0.751 accuracy in subtask-A using SVM. But still there is a wide room for improvement in system. |
| Tasks | Opinion Mining, Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2069/ |
| https://www.aclweb.org/anthology/S17-2069 | |
| PWC | https://paperswithcode.com/paper/svnit-semeval-2017-task-6-learning-a-sense-of |
| Repo | |
| Framework | |
LIA at SemEval-2017 Task 4: An Ensemble of Neural Networks for Sentiment Classification
| Title | LIA at SemEval-2017 Task 4: An Ensemble of Neural Networks for Sentiment Classification |
| Authors | Mickael Rouvier |
| Abstract | This paper describes the system developed at LIA for the SemEval-2017 evaluation campaign. The goal of Task 4.A was to identify sentiment polarity in tweets. The system is an ensemble of Deep Neural Network (DNN) models: Convolutional Neural Network (CNN) and Recurrent Neural Network Long Short-Term Memory (RNN-LSTM). We initialize the input representation of DNN with different sets of embeddings trained on large datasets. The ensemble of DNNs are combined using a score-level fusion approach. The system ranked 2nd at SemEval-2017 and obtained an average recall of 67.6{%}. |
| Tasks | Sentence Classification, Sentiment Analysis, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2128/ |
| https://www.aclweb.org/anthology/S17-2128 | |
| PWC | https://paperswithcode.com/paper/lia-at-semeval-2017-task-4-an-ensemble-of |
| Repo | |
| Framework | |
A Quantitative Study of Data in the NLP community
| Title | A Quantitative Study of Data in the NLP community |
| Authors | Margot Mieskes |
| Abstract | We present results on a quantitative analysis of publications in the NLP domain on collecting, publishing and availability of research data. We find that a wide range of publications rely on data crawled from the web, but few give details on how potentially sensitive data was treated. Additionally, we find that while links to repositories of data are given, they often do not work even a short time after publication. We put together several suggestions on how to improve this situation based on publications from the NLP domain, but also other research areas. |
| Tasks | Speech Recognition |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1603/ |
| https://www.aclweb.org/anthology/W17-1603 | |
| PWC | https://paperswithcode.com/paper/a-quantitative-study-of-data-in-the-nlp |
| Repo | |
| Framework | |
Inducing Event Types and Roles in Reverse: Using Function to Discover Theme
| Title | Inducing Event Types and Roles in Reverse: Using Function to Discover Theme |
| Authors | Natalie Ahn |
| Abstract | With growing interest in automated event extraction, there is an increasing need to overcome the labor costs of hand-written event templates, entity lists, and annotated corpora. In the last few years, more inductive approaches have emerged, seeking to discover unknown event types and roles in raw text. The main recent efforts use probabilistic generative models, as in topic modeling, which are formally concise but do not always yield stable or easily interpretable results. We argue that event schema induction can benefit from greater structure in the process and in linguistic features that distinguish words{'} functions and themes. To maximize our use of limited data, we reverse the typical schema induction steps and introduce new similarity measures, building an intuitive process for inducing the structure of unknown events. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2710/ |
| https://www.aclweb.org/anthology/W17-2710 | |
| PWC | https://paperswithcode.com/paper/inducing-event-types-and-roles-in-reverse |
| Repo | |
| Framework | |
Patterns of Argumentation Strategies across Topics
| Title | Patterns of Argumentation Strategies across Topics |
| Authors | Khalid Al-Khatib, Henning Wachsmuth, Matthias Hagen, Benno Stein |
| Abstract | This paper presents an analysis of argumentation strategies in news editorials within and across topics. Given nearly 29,000 argumentative editorials from the New York Times, we develop two machine learning models, one for determining an editorial{'}s topic, and one for identifying evidence types in the editorial. Based on the distribution and structure of the identified types, we analyze the usage patterns of argumentation strategies among 12 different topics. We detect several common patterns that provide insights into the manifestation of argumentation strategies. Also, our experiments reveal clear correlations between the topics and the detected patterns. |
| Tasks | Argument Mining |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1141/ |
| https://www.aclweb.org/anthology/D17-1141 | |
| PWC | https://paperswithcode.com/paper/patterns-of-argumentation-strategies-across |
| Repo | |
| Framework | |
Visualizing and Understanding Neural Machine Translation
| Title | Visualizing and Understanding Neural Machine Translation |
| Authors | Yanzhuo Ding, Yang Liu, Huanbo Luan, Maosong Sun |
| Abstract | While neural machine translation (NMT) has made remarkable progress in recent years, it is hard to interpret its internal workings due to the continuous representations and non-linearity of neural networks. In this work, we propose to use layer-wise relevance propagation (LRP) to compute the contribution of each contextual word to arbitrary hidden states in the attention-based encoder-decoder framework. We show that visualization with LRP helps to interpret the internal workings of NMT and analyze translation errors. |
| Tasks | Machine Translation |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1106/ |
| https://www.aclweb.org/anthology/P17-1106 | |
| PWC | https://paperswithcode.com/paper/visualizing-and-understanding-neural-machine |
| Repo | |
| Framework | |
Identification and Classification of the Most Important Moments in Students’ Collaborative Chats
| Title | Identification and Classification of the Most Important Moments in Students’ Collaborative Chats |
| Authors | Costin Chiru, Remus Decea |
| Abstract | In this paper, we present an application for the automatic identification of the important moments that might occur during students{'} collaborative chats. The moments are detected based on the input received from the user, who may choose to perform an analysis on the topics that interest him/her. Moreover, the application offers various types of suggestive and intuitive graphics that aid the user in identification of such moments. There are two main aspects that are considered when identifying important moments: the concepts{'} frequency and distribution throughout the conversation and the chat tempo, which is analyzed for identifying intensively debated concepts. By the tempo of the chat we understand the rate at which the ideas are input by the chat participants, expressed by the utterances{'} timestamps. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1024/ |
| https://doi.org/10.26615/978-954-452-049-6_024 | |
| PWC | https://paperswithcode.com/paper/identification-and-classification-of-the-most |
| Repo | |
| Framework | |
Explaining and Generalizing Skip-Gram through Exponential Family Principal Component Analysis
| Title | Explaining and Generalizing Skip-Gram through Exponential Family Principal Component Analysis |
| Authors | Ryan Cotterell, Adam Poliak, Benjamin Van Durme, Jason Eisner |
| Abstract | The popular skip-gram model induces word embeddings by exploiting the signal from word-context coocurrence. We offer a new interpretation of skip-gram based on exponential family PCA-a form of matrix factorization to generalize the skip-gram model to tensor factorization. In turn, this lets us train embeddings through richer higher-order coocurrences, e.g., triples that include positional information (to incorporate syntax) or morphological information (to share parameters across related words). We experiment on 40 languages and show our model improves upon skip-gram. |
| Tasks | Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2028/ |
| https://www.aclweb.org/anthology/E17-2028 | |
| PWC | https://paperswithcode.com/paper/explaining-and-generalizing-skip-gram-through |
| Repo | |
| Framework | |
Verb-Particle Constructions in Questions
| Title | Verb-Particle Constructions in Questions |
| Authors | Veronika Vincze |
| Abstract | In this paper, we investigate the behavior of verb-particle constructions in English questions. We present a small dataset that contains questions and verb-particle construction candidates. We demonstrate that there are significant differences in the distribution of WH-words, verbs and prepositions/particles in sentences that contain VPCs and sentences that contain only verb + prepositional phrase combinations both by statistical means and in machine learning experiments. Hence, VPCs and non-VPCs can be effectively separated from each other by using a rich feature set, containing several novel features. |
| Tasks | Chunking |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1721/ |
| https://www.aclweb.org/anthology/W17-1721 | |
| PWC | https://paperswithcode.com/paper/verb-particle-constructions-in-questions |
| Repo | |
| Framework | |
Guiding Interaction Behaviors for Multi-modal Grounded Language Learning
| Title | Guiding Interaction Behaviors for Multi-modal Grounded Language Learning |
| Authors | Jesse Thomason, Jivko Sinapov, Raymond Mooney |
| Abstract | Multi-modal grounded language learning connects language predicates to physical properties of objects in the world. Sensing with multiple modalities, such as audio, haptics, and visual colors and shapes while performing interaction behaviors like lifting, dropping, and looking on objects enables a robot to ground non-visual predicates like {}empty{''} as well as visual predicates like {}red{''}. Previous work has established that grounding in multi-modal space improves performance on object retrieval from human descriptions. In this work, we gather behavior annotations from humans and demonstrate that these improve language grounding performance by allowing a system to focus on relevant behaviors for words like {}white{''} or {}half-full{''} that can be understood by looking or lifting, respectively. We also explore adding modality annotations (whether to focus on audio or haptics when performing a behavior), which improves performance, and sharing information between linguistically related predicates (if {}green{''} is a color, {}white{''} is a color), which improves grounding recall but at the cost of precision. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2803/ |
| https://www.aclweb.org/anthology/W17-2803 | |
| PWC | https://paperswithcode.com/paper/guiding-interaction-behaviors-for-multi-modal |
| Repo | |
| Framework | |
POS Tagging For Resource Poor Languages Through Feature Projection
| Title | POS Tagging For Resource Poor Languages Through Feature Projection |
| Authors | Pruthwik Mishra, V Mujadia, an, Dipti Misra Sharma |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7507/ |
| https://www.aclweb.org/anthology/W17-7507 | |
| PWC | https://paperswithcode.com/paper/pos-tagging-for-resource-poor-languages |
| Repo | |
| Framework | |
Unsupervised Method for Improving Arabic Speech Recognition Systems
| Title | Unsupervised Method for Improving Arabic Speech Recognition Systems |
| Authors | Mohamed Labidi, Mohsen Maraoui, Mounir Zrigui |
| Abstract | |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1024/ |
| https://www.aclweb.org/anthology/Y17-1024 | |
| PWC | https://paperswithcode.com/paper/unsupervised-method-for-improving-arabic |
| Repo | |
| Framework | |
