Paper Group NANR 99
Topic Signatures in Political Campaign Speeches. Variational Inference via \chi Upper Bound Minimization. Exploring the Behavior of Classic REG Algorithms in the Description of Characters in 3D Images. QUB at SemEval-2017 Task 6: Cascaded Imbalanced Classification for Humor Analysis in Twitter. HumorHawk at SemEval-2017 Task 6: Mixing Meaning and S …
Topic Signatures in Political Campaign Speeches
| Title | Topic Signatures in Political Campaign Speeches |
| Authors | Cl{'e}ment Gautrais, Peggy Cellier, Ren{'e} Quiniou, Alex Termier, re |
| Abstract | Highlighting the recurrence of topics usage in candidates speeches is a key feature to identify the main ideas of each candidate during a political campaign. In this paper, we present a method combining standard topic modeling with signature mining for analyzing topic recurrence in speeches of Clinton and Trump during the 2016 American presidential campaign. The results show that the method extracts automatically the main ideas of each candidate and, in addition, provides information about the evolution of these topics during the campaign. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1249/ |
| https://www.aclweb.org/anthology/D17-1249 | |
| PWC | https://paperswithcode.com/paper/topic-signatures-in-political-campaign |
| Repo | |
| Framework | |
Variational Inference via \chi Upper Bound Minimization
| Title | Variational Inference via \chi Upper Bound Minimization |
| Authors | Adji Bousso Dieng, Dustin Tran, Rajesh Ranganath, John Paisley, David Blei |
| Abstract | Variational inference (VI) is widely used as an efficient alternative to Markov chain Monte Carlo. It posits a family of approximating distributions $q$ and finds the closest member to the exact posterior $p$. Closeness is usually measured via a divergence $D(q p)$ from $q$ to $p$. While successful, this approach also has problems. Notably, it typically leads to underestimation of the posterior variance. In this paper we propose CHIVI, a black-box variational inference algorithm that minimizes $D_{\chi}(p q)$, the $\chi$-divergence from $p$ to $q$. CHIVI minimizes an upper bound of the model evidence, which we term the $\chi$ upper bound (CUBO). Minimizing the CUBO leads to improved posterior uncertainty, and it can also be used with the classical VI lower bound (ELBO) to provide a sandwich estimate of the model evidence. We study CHIVI on three models: probit regression, Gaussian process classification, and a Cox process model of basketball plays. When compared to expectation propagation and classical VI, CHIVI produces better error rates and more accurate estimates of posterior variance. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6866-variational-inference-via-chi-upper-bound-minimization |
| http://papers.nips.cc/paper/6866-variational-inference-via-chi-upper-bound-minimization.pdf | |
| PWC | https://paperswithcode.com/paper/variational-inference-via-chi-upper-bound |
| Repo | |
| Framework | |
Exploring the Behavior of Classic REG Algorithms in the Description of Characters in 3D Images
| Title | Exploring the Behavior of Classic REG Algorithms in the Description of Characters in 3D Images |
| Authors | Gonzalo M{'e}ndez, Raquel Herv{'a}s, Susana Bautista, Adri{'a}n Rabad{'a}n, Teresa Rodr{'\i}guez |
| Abstract | Describing people and characters can be very useful in different contexts, such as computational narrative or image description for the visually impaired. However, a review of the existing literature shows that the automatic generation of people descriptions has not received much attention. Our work focuses on the description of people in snapshots from a 3D environment. First, we have conducted a survey to identify the way in which people describe other people under different conditions. We have used the information extracted from this survey to design several Referring Expression Generation algorithms which produce similar results. We have evaluated these algorithms with users in order to identify which ones generate the best description for specific characters in different situations. The evaluation has shown that, in order to generate good descriptions, a combination of different algorithms has to be used depending on the features and situation of the person to be described. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3507/ |
| https://www.aclweb.org/anthology/W17-3507 | |
| PWC | https://paperswithcode.com/paper/exploring-the-behavior-of-classic-reg |
| Repo | |
| Framework | |
QUB at SemEval-2017 Task 6: Cascaded Imbalanced Classification for Humor Analysis in Twitter
| Title | QUB at SemEval-2017 Task 6: Cascaded Imbalanced Classification for Humor Analysis in Twitter |
| Authors | Xiwu Han, Gregory Toner |
| Abstract | This paper presents our submission to SemEval-2017 Task 6: {#}HashtagWars: Learning a Sense of Humor. There are two subtasks: A. Pairwise Comparison, and B. Semi-Ranking. Our assumption is that the distribution of humorous and non-humorous texts in real life language is naturally imbalanced. Using Na{"\i}ve Bayes Multinomial with standard text-representation features, we approached Subtask B as a sequence of imbalanced classification problems, and optimized our system per the macro-average recall. Subtask A was then solved via the Semi-Ranking results. On the final test, our system was ranked 10th for Subtask A, and 3rd for Subtask B. |
| Tasks | Humor Detection |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2063/ |
| https://www.aclweb.org/anthology/S17-2063 | |
| PWC | https://paperswithcode.com/paper/qub-at-semeval-2017-task-6-cascaded |
| Repo | |
| Framework | |
HumorHawk at SemEval-2017 Task 6: Mixing Meaning and Sound for Humor Recognition
| Title | HumorHawk at SemEval-2017 Task 6: Mixing Meaning and Sound for Humor Recognition |
| Authors | David Donahue, Alexey Romanov, Anna Rumshisky |
| Abstract | This paper describes the winning system for SemEval-2017 Task 6: {#}HashtagWars: Learning a Sense of Humor. Humor detection has up until now been predominantly addressed using feature-based approaches. Our system utilizes recurrent deep learning methods with dense embeddings to predict humorous tweets from the @midnight show {#}HashtagWars. In order to include both meaning and sound in the analysis, GloVe embeddings are combined with a novel phonetic representation to serve as input to an LSTM component. The output is combined with a character-based CNN model, and an XGBoost component in an ensemble model which achieves 0.675 accuracy on the evaluation data. |
| Tasks | Humor Detection, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2010/ |
| https://www.aclweb.org/anthology/S17-2010 | |
| PWC | https://paperswithcode.com/paper/humorhawk-at-semeval-2017-task-6-mixing |
| Repo | |
| Framework | |
English Event Detection With Translated Language Features
| Title | English Event Detection With Translated Language Features |
| Authors | Sam Wei, Igor Korostil, Joel Nothman, Ben Hachey |
| Abstract | We propose novel radical features from automatic translation for event extraction. Event detection is a complex language processing task for which it is expensive to collect training data, making generalisation challenging. We derive meaningful subword features from automatic translations into target language. Results suggest this method is particularly useful when using languages with writing systems that facilitate easy decomposition into subword features, e.g., logograms and Cangjie. The best result combines logogram features from Chinese and Japanese with syllable features from Korean, providing an additional 3.0 points f-score when added to state-of-the-art generalisation features on the TAC KBP 2015 Event Nugget task. |
| Tasks | Named Entity Recognition, Sentiment Analysis, Word Sense Disambiguation |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2046/ |
| https://www.aclweb.org/anthology/P17-2046 | |
| PWC | https://paperswithcode.com/paper/english-event-detection-with-translated |
| Repo | |
| Framework | |
#WarTeam at SemEval-2017 Task 6: Using Neural Networks for Discovering Humorous Tweets
| Title | #WarTeam at SemEval-2017 Task 6: Using Neural Networks for Discovering Humorous Tweets |
| Authors | Iuliana Alex Fle{\textcommabelow{s}}can-Lovin-Arseni, ra, Ramona Andreea Turcu, Cristina S{^\i}rbu, Larisa Alexa, Amar, S ei, ra Maria, Nichita Herciu, Constantin Scutaru, Tr, Diana ab{\u{a}}{\textcommabelow{t}}, Adrian Iftene |
| Abstract | This paper presents the participation of {#}WarTeam in Task 6 of SemEval2017 with a system classifying humor by comparing and ranking tweets. The training data consists of annotated tweets from the @midnight TV show. {#}WarTeam{'}s system uses a neural network (TensorFlow) having inputs from a Na{"\i}ve Bayes humor classifier and a sentiment analyzer. |
| Tasks | Humor Detection |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2068/ |
| https://www.aclweb.org/anthology/S17-2068 | |
| PWC | https://paperswithcode.com/paper/warteam-at-semeval-2017-task-6-using-neural |
| Repo | |
| Framework | |
Foreign Influence and Sound Change: A Case Study of Cantonese Alveolar Affricates
| Title | Foreign Influence and Sound Change: A Case Study of Cantonese Alveolar Affricates |
| Authors | Yizhou Lan |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1023/ |
| https://www.aclweb.org/anthology/Y17-1023 | |
| PWC | https://paperswithcode.com/paper/foreign-influence-and-sound-change-a-case |
| Repo | |
| Framework | |
Topic-Based Agreement and Disagreement in US Electoral Manifestos
| Title | Topic-Based Agreement and Disagreement in US Electoral Manifestos |
| Authors | Stefano Menini, Federico Nanni, Simone Paolo Ponzetto, Sara Tonelli |
| Abstract | We present a topic-based analysis of agreement and disagreement in political manifestos, which relies on a new method for topic detection based on key concept clustering. Our approach outperforms both standard techniques like LDA and a state-of-the-art graph-based method, and provides promising initial results for this new task in computational social science. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1318/ |
| https://www.aclweb.org/anthology/D17-1318 | |
| PWC | https://paperswithcode.com/paper/topic-based-agreement-and-disagreement-in-us |
| Repo | |
| Framework | |
Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaos
| Title | Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaos |
| Authors | Gerasimos Palaiopanos, Ioannis Panageas, Georgios Piliouras |
| Abstract | The Multiplicative Weights Update (MWU) method is a ubiquitous meta-algorithm that works as follows: A distribution is maintained on a certain set, and at each step the probability assigned to action $\gamma$ is multiplied by $(1 -\epsilon C(\gamma))>0$ where $C(\gamma)$ is the ``cost” of action $\gamma$ and then rescaled to ensure that the new values form a distribution. We analyze MWU in congestion games where agents use \textit{arbitrary admissible constants} as learning rates $\epsilon$ and prove convergence to \textit{exact Nash equilibria}. Interestingly, this convergence result does not carry over to the nearly homologous MWU variant where at each step the probability assigned to action $\gamma$ is multiplied by $(1 -\epsilon)^{C(\gamma)}$ even for the simplest case of two-agent, two-strategy load balancing games, where such dynamics can provably lead to limit cycles or even chaotic behavior. | |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7169-multiplicative-weights-update-with-constant-step-size-in-congestion-games-convergence-limit-cycles-and-chaos |
| http://papers.nips.cc/paper/7169-multiplicative-weights-update-with-constant-step-size-in-congestion-games-convergence-limit-cycles-and-chaos.pdf | |
| PWC | https://paperswithcode.com/paper/multiplicative-weights-update-with-constant |
| Repo | |
| Framework | |
Prepositional Phrase Attachment over Word Embedding Products
| Title | Prepositional Phrase Attachment over Word Embedding Products |
| Authors | Pranava Swaroop Madhyastha, Xavier Carreras, Ariadna Quattoni |
| Abstract | We present a low-rank multi-linear model for the task of solving prepositional phrase attachment ambiguity (PP task). Our model exploits tensor products of word embeddings, capturing all possible conjunctions of latent embeddings. Our results on a wide range of datasets and task settings show that tensor products are the best compositional operation and that a relatively simple multi-linear model that uses only word embeddings of lexical features can outperform more complex non-linear architectures that exploit the same information. Our proposed model gives the current best reported performance on an out-of-domain evaluation and performs competively on out-of-domain dependency parsing datasets. |
| Tasks | Dependency Parsing, Prepositional Phrase Attachment, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6305/ |
| https://www.aclweb.org/anthology/W17-6305 | |
| PWC | https://paperswithcode.com/paper/prepositional-phrase-attachment-over-word |
| Repo | |
| Framework | |
Search-based Neural Structured Learning for Sequential Question Answering
| Title | Search-based Neural Structured Learning for Sequential Question Answering |
| Authors | Mohit Iyyer, Wen-tau Yih, Ming-Wei Chang |
| Abstract | Recent work in semantic parsing for question answering has focused on long and complicated questions, many of which would seem unnatural if asked in a normal conversation between two humans. In an effort to explore a conversational QA setting, we present a more realistic task: answering sequences of simple but inter-related questions. We collect a dataset of 6,066 question sequences that inquire about semi-structured tables from Wikipedia, with 17,553 question-answer pairs in total. To solve this sequential question answering task, we propose a novel dynamic neural semantic parsing framework trained using a weakly supervised reward-guided search. Our model effectively leverages the sequential context to outperform state-of-the-art QA systems that are designed to answer highly complex questions. |
| Tasks | Question Answering, Semantic Parsing |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1167/ |
| https://www.aclweb.org/anthology/P17-1167 | |
| PWC | https://paperswithcode.com/paper/search-based-neural-structured-learning-for |
| Repo | |
| Framework | |
Referential Success of Set Referring Expressions with Fuzzy Properties
| Title | Referential Success of Set Referring Expressions with Fuzzy Properties |
| Authors | Nicol{'a}s Mar{'\i}n, Gustavo Rivas-Gervilla, Daniel S{'a}nchez |
| Abstract | We introduce the properties to be satisfied by measures of referential success of set referring expressions with fuzzy properties. We define families of measures on the basis of n-cardinality measures and we illustrate some of them with a toy example. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3540/ |
| https://www.aclweb.org/anthology/W17-3540 | |
| PWC | https://paperswithcode.com/paper/referential-success-of-set-referring |
| Repo | |
| Framework | |
A demo of FORGe: the Pompeu Fabra Open Rule-based Generator
| Title | A demo of FORGe: the Pompeu Fabra Open Rule-based Generator |
| Authors | Simon Mille, Leo Wanner |
| Abstract | This demo paper presents the multilingual deep sentence generator developed by the TALN group at Universitat Pompeu Fabra, implemented as a series of rule-based graph-transducers for the syntacticization of the input graphs, the resolution of morphological agreements, and the linearization of the trees. |
| Tasks | Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3539/ |
| https://www.aclweb.org/anthology/W17-3539 | |
| PWC | https://paperswithcode.com/paper/a-demo-of-forge-the-pompeu-fabra-open-rule |
| Repo | |
| Framework | |
Template-Free Construction of Rhyming Poems with Thematic Cohesion
| Title | Template-Free Construction of Rhyming Poems with Thematic Cohesion |
| Authors | Pablo Gerv{'a}s |
| Abstract | |
| Tasks | Language Modelling, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3903/ |
| https://www.aclweb.org/anthology/W17-3903 | |
| PWC | https://paperswithcode.com/paper/template-free-construction-of-rhyming-poems |
| Repo | |
| Framework | |
