Paper Group NANR 32
M'alr'omur: A Manually Verified Corpus of Recorded Icelandic Speech. Learning attention for historical text normalization by learning to pronounce. UHH Submission to the WMT17 Metrics Shared Task. SemEval-2017 Task 6: #HashtagWars: Learning a Sense of Humor. Quantifying how much sensory information in a neural code is relevant for behavior. Idio …
M'alr'omur: A Manually Verified Corpus of Recorded Icelandic Speech
| Title | M'alr'omur: A Manually Verified Corpus of Recorded Icelandic Speech |
| Authors | Stein{\th}{'o}r Steingr{'\i}msson, J{'o}n Gu{\dh}nason, Sigr{'u}n Helgad{'o}ttir, Eir{'\i}kur R{"o}gnvaldsson |
| Abstract | |
| Tasks | Speech Recognition |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0229/ |
| https://www.aclweb.org/anthology/W17-0229 | |
| PWC | https://paperswithcode.com/paper/malra3mur-a-manually-verified-corpus-of |
| Repo | |
| Framework | |
Learning attention for historical text normalization by learning to pronounce
| Title | Learning attention for historical text normalization by learning to pronounce |
| Authors | Marcel Bollmann, Joachim Bingel, Anders S{\o}gaard |
| Abstract | Automated processing of historical texts often relies on pre-normalization to modern word forms. Training encoder-decoder architectures to solve such problems typically requires a lot of training data, which is not available for the named task. We address this problem by using several novel encoder-decoder architectures, including a multi-task learning (MTL) architecture using a grapheme-to-phoneme dictionary as auxiliary data, pushing the state-of-the-art by an absolute 2{%} increase in performance. We analyze the induced models across 44 different texts from Early New High German. Interestingly, we observe that, as previously conjectured, multi-task learning can learn to focus attention during decoding, in ways remarkably similar to recently proposed attention mechanisms. This, we believe, is an important step toward understanding how MTL works. |
| Tasks | Machine Translation, Multi-Task Learning |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1031/ |
| https://www.aclweb.org/anthology/P17-1031 | |
| PWC | https://paperswithcode.com/paper/learning-attention-for-historical-text |
| Repo | |
| Framework | |
UHH Submission to the WMT17 Metrics Shared Task
| Title | UHH Submission to the WMT17 Metrics Shared Task |
| Authors | Melania Duma, Wolfgang Menzel |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4766/ |
| https://www.aclweb.org/anthology/W17-4766 | |
| PWC | https://paperswithcode.com/paper/uhh-submission-to-the-wmt17-metrics-shared |
| Repo | |
| Framework | |
SemEval-2017 Task 6: #HashtagWars: Learning a Sense of Humor
| Title | SemEval-2017 Task 6: #HashtagWars: Learning a Sense of Humor |
| Authors | Peter Potash, Alexey Romanov, Anna Rumshisky |
| Abstract | This paper describes a new shared task for humor understanding that attempts to eschew the ubiquitous binary approach to humor detection and focus on comparative humor ranking instead. The task is based on a new dataset of funny tweets posted in response to shared hashtags, collected from the {`}Hashtag Wars{'} segment of the TV show @midnight. The results are evaluated in two subtasks that require the participants to generate either the correct pairwise comparisons of tweets (subtask A), or the correct ranking of the tweets (subtask B) in terms of how funny they are. 7 teams participated in subtask A, and 5 teams participated in subtask B. The best accuracy in subtask A was 0.675. The best (lowest) rank edit distance for subtask B was 0.872. | |
| Tasks | Humor Detection |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2004/ |
| https://www.aclweb.org/anthology/S17-2004 | |
| PWC | https://paperswithcode.com/paper/semeval-2017-task-6-hashtagwars-learning-a |
| Repo | |
| Framework | |
Quantifying how much sensory information in a neural code is relevant for behavior
| Title | Quantifying how much sensory information in a neural code is relevant for behavior |
| Authors | Giuseppe Pica, Eugenio Piasini, Houman Safaai, Caroline Runyan, Christopher Harvey, Mathew Diamond, Christoph Kayser, Tommaso Fellin, Stefano Panzeri |
| Abstract | Determining how much of the sensory information carried by a neural code contributes to behavioral performance is key to understand sensory function and neural information flow. However, there are as yet no analytical tools to compute this information that lies at the intersection between sensory coding and behavioral readout. Here we develop a novel measure, termed the information-theoretic intersection information $\III(S;R;C)$, that quantifies how much of the sensory information carried by a neural response $R$ is used for behavior during perceptual discrimination tasks. Building on the Partial Information Decomposition framework, we define $\III(S;R;C)$ as the part of the mutual information between the stimulus $S$ and the response $R$ that also informs the consequent behavioral choice $C$. We compute $\III(S;R;C)$ in the analysis of two experimental cortical datasets, to show how this measure can be used to compare quantitatively the contributions of spike timing and spike rates to task performance, and to identify brain areas or neural populations that specifically transform sensory information into choice. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6959-quantifying-how-much-sensory-information-in-a-neural-code-is-relevant-for-behavior |
| http://papers.nips.cc/paper/6959-quantifying-how-much-sensory-information-in-a-neural-code-is-relevant-for-behavior.pdf | |
| PWC | https://paperswithcode.com/paper/quantifying-how-much-sensory-information-in-a |
| Repo | |
| Framework | |
Idiom Savant at Semeval-2017 Task 7: Detection and Interpretation of English Puns
| Title | Idiom Savant at Semeval-2017 Task 7: Detection and Interpretation of English Puns |
| Authors | Samuel Doogan, Aniruddha Ghosh, Hanyang Chen, Tony Veale |
| Abstract | This paper describes our system, entitled Idiom Savant, for the 7th Task of the Semeval 2017 workshop, {``}Detection and interpretation of English Puns{''}. Our system consists of two probabilistic models for each type of puns using Google n-gram and Word2Vec. Our system achieved f-score of calculating, 0.663, and 0.07 in homographic puns and 0.8439, 0.6631, and 0.0806 in heterographic puns in task 1, task 2, and task 3 respectively. | |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2011/ |
| https://www.aclweb.org/anthology/S17-2011 | |
| PWC | https://paperswithcode.com/paper/idiom-savant-at-semeval-2017-task-7-detection |
| Repo | |
| Framework | |
Transforming Dependency Structures to LTAG Derivation Trees
| Title | Transforming Dependency Structures to LTAG Derivation Trees |
| Authors | Caio Corro, Joseph Le Roux |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6212/ |
| https://www.aclweb.org/anthology/W17-6212 | |
| PWC | https://paperswithcode.com/paper/transforming-dependency-structures-to-ltag |
| Repo | |
| Framework | |
Towards Confidence Estimation for Typed Protein-Protein Relation Extraction
| Title | Towards Confidence Estimation for Typed Protein-Protein Relation Extraction |
| Authors | Camilo Thorne, Roman Klinger |
| Abstract | Systems which build on top of information extraction are typically challenged to extract knowledge that, while correct, is not yet well-known. We hypothesize that a good confidence measure for relational information has the property that such interesting information is found between information extracted with very high confidence and very low confidence. We discuss confidence estimation for the domain of biomedical protein-protein relation discovery in biomedical literature. As facts reported in papers take some time to be validated and recorded in biomedical databases, such task gives rise to large quantities of unknown but potentially true candidate relations. It is thus important to rank them based on supporting evidence rather than discard them. In this paper, we discuss this task and propose different approaches for confidence estimation and a pipeline to evaluate such methods. We show that the most straight-forward approach, a combination of different confidence measures from pipeline modules seems not to work well. We discuss this negative result and pinpoint potential future research directions. |
| Tasks | Entity Linking, Named Entity Recognition, Relation Extraction |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-8008/ |
| https://doi.org/10.26615/978-954-452-044-1_008 | |
| PWC | https://paperswithcode.com/paper/towards-confidence-estimation-for-typed |
| Repo | |
| Framework | |
HCTI at SemEval-2017 Task 1: Use convolutional neural network to evaluate Semantic Textual Similarity
| Title | HCTI at SemEval-2017 Task 1: Use convolutional neural network to evaluate Semantic Textual Similarity |
| Authors | Yang Shao |
| Abstract | This paper describes our convolutional neural network (CNN) system for Semantic Textual Similarity (STS) task. We calculated semantic similarity score between two sentences by comparing their semantic vectors. We generated semantic vector of every sentence by max pooling every dimension of their word vectors. There are mainly two trick points in our system. One is that we trained a CNN to transfer GloVe word vectors to a more proper form for STS task before pooling. Another is that we trained a fully-connected neural network (FCNN) to transfer difference of two semantic vectors to probability of every similarity score. We decided all hyper parameters empirically. In spite of the simplicity of our neural network system, we achieved a good accuracy and ranked 3rd in primary track of SemEval 2017. |
| Tasks | Answer Selection, Machine Translation, Question Answering, Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2016/ |
| https://www.aclweb.org/anthology/S17-2016 | |
| PWC | https://paperswithcode.com/paper/hcti-at-semeval-2017-task-1-use-convolutional |
| Repo | |
| Framework | |
Bigger does not mean better! We prefer specificity
| Title | Bigger does not mean better! We prefer specificity |
| Authors | Emmanuelle Dusserre, Muntsa Padr{'o} |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6908/ |
| https://www.aclweb.org/anthology/W17-6908 | |
| PWC | https://paperswithcode.com/paper/bigger-does-not-mean-better-we-prefer |
| Repo | |
| Framework | |
Machine Learning Models of Universal Grammar Parameter Dependencies
| Title | Machine Learning Models of Universal Grammar Parameter Dependencies |
| Authors | Dimitar Kazakov, Guido Cordoni, Andrea Ceolin, Monica-Alex Irimia, rina, Shin-Sook Kim, Dimitris Michelioudakis, Nina Radkevich, Cristina Guardiano, Giuseppe Longobardi |
| Abstract | The use of parameters in the description of natural language syntax has to balance between the need to discriminate among (sometimes subtly different) languages, which can be seen as a cross-linguistic version of Chomsky{'}s (1964) descriptive adequacy, and the complexity of the acquisition task that a large number of parameters would imply, which is a problem for explanatory adequacy. Here we present a novel approach in which a machine learning algorithm is used to find dependencies in a table of parameters. The result is a dependency graph in which some of the parameters can be fully predicted from others. These empirical findings can be then subjected to linguistic analysis, which may either refute them by providing typological counter-examples of languages not included in the original dataset, dismiss them on theoretical grounds, or uphold them as tentative empirical laws worth of further study. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-7805/ |
| https://doi.org/10.26615/978-954-452-040-3_005 | |
| PWC | https://paperswithcode.com/paper/machine-learning-models-of-universal-grammar |
| Repo | |
| Framework | |
MITRE at SemEval-2017 Task 1: Simple Semantic Similarity
| Title | MITRE at SemEval-2017 Task 1: Simple Semantic Similarity |
| Authors | John Henderson, Elizabeth Merkhofer, Laura Strickhart, Guido Zarrella |
| Abstract | This paper describes MITRE{'}s participation in the Semantic Textual Similarity task (SemEval-2017 Task 1), which evaluated machine learning approaches to the identification of similar meaning among text snippets in English, Arabic, Spanish, and Turkish. We detail the techniques we explored ranging from simple bag-of-ngrams classifiers to neural architectures with varied attention and alignment mechanisms. Linear regression is used to tie the systems together into an ensemble submitted for evaluation. The resulting system is capable of matching human similarity ratings of image captions with correlations of 0.73 to 0.83 in monolingual settings and 0.68 to 0.78 in cross-lingual conditions, demonstrating the power of relatively simple approaches. |
| Tasks | Image Captioning, Machine Translation, Natural Language Inference, Semantic Similarity, Semantic Textual Similarity, Sentence Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2027/ |
| https://www.aclweb.org/anthology/S17-2027 | |
| PWC | https://paperswithcode.com/paper/mitre-at-semeval-2017-task-1-simple-semantic |
| Repo | |
| Framework | |
Detrended Partial Cross Correlation for Brain Connectivity Analysis
| Title | Detrended Partial Cross Correlation for Brain Connectivity Analysis |
| Authors | Jaime Ide, Fábio Cappabianco, Fabio Faria, Chiang-Shan R. Li |
| Abstract | Brain connectivity analysis is a critical component of ongoing human connectome projects to decipher the healthy and diseased brain. Recent work has highlighted the power-law (multi-time scale) properties of brain signals; however, there remains a lack of methods to specifically quantify short- vs. long- time range brain connections. In this paper, using detrended partial cross-correlation analysis (DPCCA), we propose a novel functional connectivity measure to delineate brain interactions at multiple time scales, while controlling for covariates. We use a rich simulated fMRI dataset to validate the proposed method, and apply it to a real fMRI dataset in a cocaine dependence prediction task. We show that, compared to extant methods, the DPCCA-based approach not only distinguishes short and long memory functional connectivity but also improves feature extraction and enhances classification accuracy. Together, this paper contributes broadly to new computational methodologies in understanding neural information processing. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6690-detrended-partial-cross-correlation-for-brain-connectivity-analysis |
| http://papers.nips.cc/paper/6690-detrended-partial-cross-correlation-for-brain-connectivity-analysis.pdf | |
| PWC | https://paperswithcode.com/paper/detrended-partial-cross-correlation-for-brain |
| Repo | |
| Framework | |
Using lexical level information in discourse structures for Basque sentiment analysis
| Title | Using lexical level information in discourse structures for Basque sentiment analysis |
| Authors | Jon Alkorta, Koldo Gojenola, Mikel Iruskieta, Maite Taboada |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3606/ |
| https://www.aclweb.org/anthology/W17-3606 | |
| PWC | https://paperswithcode.com/paper/using-lexical-level-information-in-discourse |
| Repo | |
| Framework | |
Bayesian Modeling of Lexical Resources for Low-Resource Settings
| Title | Bayesian Modeling of Lexical Resources for Low-Resource Settings |
| Authors | Nicholas Andrews, Mark Dredze, Benjamin Van Durme, Jason Eisner |
| Abstract | Lexical resources such as dictionaries and gazetteers are often used as auxiliary data for tasks such as part-of-speech induction and named-entity recognition. However, discriminative training with lexical features requires annotated data to reliably estimate the lexical feature weights and may result in overfitting the lexical features at the expense of features which generalize better. In this paper, we investigate a more robust approach: we stipulate that the lexicon is the result of an assumed generative process. Practically, this means that we may treat the lexical resources as observations under the proposed generative model. The lexical resources provide training data for the generative model without requiring separate data to estimate lexical feature weights. We evaluate the proposed approach in two settings: part-of-speech induction and low-resource named-entity recognition. |
| Tasks | Named Entity Recognition |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1095/ |
| https://www.aclweb.org/anthology/P17-1095 | |
| PWC | https://paperswithcode.com/paper/bayesian-modeling-of-lexical-resources-for |
| Repo | |
| Framework | |
