Paper Group NANR 83
CAMB at CWI Shared Task 2018: Complex Word Identification with Ensemble-Based Voting. Phrase-Level Metaphor Identification Using Distributed Representations of Word Meaning. Irony Detector at SemEval-2018 Task 3: Irony Detection in English Tweets using Word Graph. Vis-Eval Metric Viewer: A Visualisation Tool for Inspecting and Evaluating Metric Sco …
CAMB at CWI Shared Task 2018: Complex Word Identification with Ensemble-Based Voting
| Title | CAMB at CWI Shared Task 2018: Complex Word Identification with Ensemble-Based Voting |
| Authors | Sian Gooding, Ekaterina Kochmar |
| Abstract | This paper presents the winning systems we submitted to the Complex Word Identification Shared Task 2018. We describe our best performing systems{'} implementations and discuss our key findings from this research. Our best-performing systems achieve an F1 score of 0.8792 on the NEWS, 0.8430 on the WIKINEWS and 0.8115 on the WIKIPEDIA test sets in the monolingual English binary classification track, and a mean absolute error of 0.0558 on the NEWS, 0.0674 on the WIKINEWS and 0.0739 on the WIKIPEDIA test sets in the probabilistic track. |
| Tasks | Complex Word Identification, Lexical Simplification, Reading Comprehension, Text Simplification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0520/ |
| https://www.aclweb.org/anthology/W18-0520 | |
| PWC | https://paperswithcode.com/paper/camb-at-cwi-shared-task-2018-complex-word |
| Repo | |
| Framework | |
Phrase-Level Metaphor Identification Using Distributed Representations of Word Meaning
| Title | Phrase-Level Metaphor Identification Using Distributed Representations of Word Meaning |
| Authors | Omnia Zayed, John Philip McCrae, Paul Buitelaar |
| Abstract | Metaphor is an essential element of human cognition which is often used to express ideas and emotions that might be difficult to express using literal language. Processing metaphoric language is a challenging task for a wide range of applications ranging from text simplification to psychotherapy. Despite the variety of approaches that are trying to process metaphor, there is still a need for better models that mimic the human cognition while exploiting fewer resources. In this paper, we present an approach based on distributional semantics to identify metaphors on the phrase-level. We investigated the use of different word embeddings models to identify verb-noun pairs where the verb is used metaphorically. Several experiments are conducted to show the performance of the proposed approach on benchmark datasets. |
| Tasks | Machine Translation, Semantic Textual Similarity, Text Simplification, Text Summarization, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0910/ |
| https://www.aclweb.org/anthology/W18-0910 | |
| PWC | https://paperswithcode.com/paper/phrase-level-metaphor-identification-using |
| Repo | |
| Framework | |
Irony Detector at SemEval-2018 Task 3: Irony Detection in English Tweets using Word Graph
| Title | Irony Detector at SemEval-2018 Task 3: Irony Detection in English Tweets using Word Graph |
| Authors | Usman Ahmed, Lubna Zafar, Faiza Qayyum, Muhammad Arshad Islam |
| Abstract | This paper describes the Irony detection system that participates in SemEval-2018 Task 3: Irony detection in English tweets. The system participated in the subtasks A and B. This paper discusses the results of our system in the development, evaluation and post evaluation. Each class in the dataset is represented as directed unweighted graphs. Then, the comparison is carried out with each class graph which results in a vector. This vector is used as features by machine learning algorithm. The model is evaluated on a hold on strategy. The organizers randomly split 80{%} (3,833 instances) training set (provided to the participant in training their system) and testing set 20{%}(958 instances). The test set is reserved to evaluate the performance of participants systems. During the evaluation, our system ranked 23 in the Coda Lab result of the subtask A (binary class problem). The binary class system achieves accuracy 0.6135, precision 0.5091, recall 0.7170 and F measure 0.5955. The subtask B (multi-class problem) system is ranked 22 in Coda Lab results. The multiclass model achieves the accuracy 0.4158, precision 0.4055, recall 0.3526 and f measure 0.3101. |
| Tasks | Opinion Mining, Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1095/ |
| https://www.aclweb.org/anthology/S18-1095 | |
| PWC | https://paperswithcode.com/paper/irony-detector-at-semeval-2018-task-3-irony |
| Repo | |
| Framework | |
Vis-Eval Metric Viewer: A Visualisation Tool for Inspecting and Evaluating Metric Scores of Machine Translation Output
| Title | Vis-Eval Metric Viewer: A Visualisation Tool for Inspecting and Evaluating Metric Scores of Machine Translation Output |
| Authors | David Steele, Lucia Specia |
| Abstract | Machine Translation systems are usually evaluated and compared using automated evaluation metrics such as BLEU and METEOR to score the generated translations against human translations. However, the interaction with the output from the metrics is relatively limited and results are commonly a single score along with a few additional statistics. Whilst this may be enough for system comparison it does not provide much useful feedback or a means for inspecting translations and their respective scores. VisEval Metric Viewer VEMV is a tool designed to provide visualisation of multiple evaluation scores so they can be easily interpreted by a user. VEMV takes in the source, reference, and hypothesis files as parameters, and scores the hypotheses using several popular evaluation metrics simultaneously. Scores are produced at both the sentence and dataset level and results are written locally to a series of HTML files that can be viewed on a web browser. The individual scored sentences can easily be inspected using powerful search and selection functions and results can be visualised with graphical representations of the scores and distributions. |
| Tasks | Machine Translation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-5015/ |
| https://www.aclweb.org/anthology/N18-5015 | |
| PWC | https://paperswithcode.com/paper/vis-eval-metric-viewer-a-visualisation-tool |
| Repo | |
| Framework | |
PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup
| Title | PairedCycleGAN: Asymmetric Style Transfer for Applying and Removing Makeup |
| Authors | Huiwen Chang, Jingwan Lu, Fisher Yu, Adam Finkelstein |
| Abstract | This paper introduces an automatic method for editing a portrait photo so that the subject appears to be wearing makeup in the style of another person in a reference photo. Our unsupervised learning approach relies on a new framework of cycle-consistent generative adversarial networks. Different from the image domain transfer problem, our style transfer problem involves two asymmetric functions: a forward function encodes example-based style transfer, whereas a backward function removes the style. We construct two coupled networks to implement these functions – one that transfers makeup style and a second that can remove makeup – such that the output of their successive application to an input photo will match the input. The learned style network can then quickly apply an arbitrary makeup style to an arbitrary photo. We demonstrate the effectiveness on a broad range of portraits and styles. |
| Tasks | Style Transfer |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Chang_PairedCycleGAN_Asymmetric_Style_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Chang_PairedCycleGAN_Asymmetric_Style_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/pairedcyclegan-asymmetric-style-transfer-for |
| Repo | |
| Framework | |
EmojiGAN: learning emojis distributions with a generative model
| Title | EmojiGAN: learning emojis distributions with a generative model |
| Authors | Bogdan Mazoure, Thang Doan, Saibal Ray |
| Abstract | Generative models have recently experienced a surge in popularity due to the development of more efficient training algorithms and increasing computational power. Models such as adversarial generative networks (GANs) have been successfully used in various areas such as computer vision, medical imaging, style transfer and natural language generation. Adversarial nets were recently shown to yield results in the image-to-text task, where given a set of images, one has to provide their corresponding text description. In this paper, we take a similar approach and propose a image-to-emoji architecture, which is trained on data from social networks and can be used to score a given picture using ideograms. We show empirical results of our algorithm on data obtained from the most influential Instagram accounts. |
| Tasks | Image Captioning, Style Transfer, Text Generation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6240/ |
| https://www.aclweb.org/anthology/W18-6240 | |
| PWC | https://paperswithcode.com/paper/emojigan-learning-emojis-distributions-with-a |
| Repo | |
| Framework | |
Contractions: To Align or Not to Align, That Is the Question
| Title | Contractions: To Align or Not to Align, That Is the Question |
| Authors | Anabela Barreiro, Fern Batista, o |
| Abstract | This paper performs a detailed analysis on the alignment of Portuguese contractions, based on a previously aligned bilingual corpus. The alignment task was performed manually in a subset of the English-Portuguese CLUE4Translation Alignment Collection. The initial parallel corpus was pre-processed and, a decision was made as to whether the contraction should be maintained or decomposed in the alignment. Decomposition was required in the cases in which the two words that have been concatenated, i.e., the preposition and the determiner or pronoun, go in two separate translation alignment pairs (e.g., [no seio de] [a Uni{~a}o Europeia] [within] [the European Union]). Most contractions required decomposition in contexts where they are positioned at the end of a multiword unit. On the other hand, contractions tend to be maintained when they occur in the beginning or in the middle of the multiword unit, i.e., in the frozen part of the multiword (e.g., [no que diz respeito a] [with regard to] or [al{'e}m disso] [in addition]. A correct alignment of multiwords and phrasal units containing contractions is instrumental for machine translation, paraphrasing, and variety adaptation. |
| Tasks | Machine Translation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3816/ |
| https://www.aclweb.org/anthology/W18-3816 | |
| PWC | https://paperswithcode.com/paper/contractions-to-align-or-not-to-align-that-is |
| Repo | |
| Framework | |
Learning a latent manifold of odor representations from neural responses in piriform cortex
| Title | Learning a latent manifold of odor representations from neural responses in piriform cortex |
| Authors | Anqi Wu, Stan Pashkovski, Sandeep R. Datta, Jonathan W. Pillow |
| Abstract | A major difficulty in studying the neural mechanisms underlying olfactory perception is the lack of obvious structure in the relationship between odorants and the neural activity patterns they elicit. Here we use odor-evoked responses in piriform cortex to identify a latent manifold specifying latent distance relationships between olfactory stimuli. Our approach is based on the Gaussian process latent variable model, and seeks to map odorants to points in a low-dimensional embedding space, where distances between points in the embedding space relate to the similarity of population responses they elicit. The model is specified by an explicit continuous mapping from a latent embedding space to the space of high-dimensional neural population firing rates via nonlinear tuning curves, each parametrized by a Gaussian process. Population responses are then generated by the addition of correlated, odor-dependent Gaussian noise. We fit this model to large-scale calcium fluorescence imaging measurements of population activity in layers 2 and 3 of mouse piriform cortex following the presentation of a diverse set of odorants. The model identifies a low-dimensional embedding of each odor, and a smooth tuning curve over the latent embedding space that accurately captures each neuron’s response to different odorants. The model captures both signal and noise correlations across more than 500 neurons. We validate the model using a cross-validation analysis known as co-smoothing to show that the model can accurately predict the responses of a population of held-out neurons to test odorants. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7783-learning-a-latent-manifold-of-odor-representations-from-neural-responses-in-piriform-cortex |
| http://papers.nips.cc/paper/7783-learning-a-latent-manifold-of-odor-representations-from-neural-responses-in-piriform-cortex.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-latent-manifold-of-odor |
| Repo | |
| Framework | |
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
| Title | Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1000/ |
| https://www.aclweb.org/anthology/P18-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-56th-annual-meeting-of-the |
| Repo | |
| Framework | |
Person Re-Identification With Cascaded Pairwise Convolutions
| Title | Person Re-Identification With Cascaded Pairwise Convolutions |
| Authors | Yicheng Wang, Zhenzhong Chen, Feng Wu, Gang Wang |
| Abstract | In this paper, a novel deep architecture named BraidNet is proposed for person re-identification. BraidNet has a specially designed WConv layer, and the cascaded WConv structure learns to extract the comparison features of two images, which are robust to misalignments and color differences across cameras. Furthermore, a Channel Scaling layer is designed to optimize the scaling factor of each input channel, which helps mitigate the zero gradient problem in the training phase. To solve the problem of imbalanced volume of negative and positive training samples, a Sample Rate Learning strategy is proposed to adaptively update the ratio between positive and negative samples in each batch. Experiments conducted on CUHK03-Detected, CUHK03-Labeled, CUHK01, Market-1501 and DukeMTMC-reID datasets demonstrate that our method achieves competitive performance when compared to state-of-the-art methods. |
| Tasks | Person Re-Identification |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Wang_Person_Re-Identification_With_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Wang_Person_Re-Identification_With_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/person-re-identification-with-cascaded |
| Repo | |
| Framework | |
Approximation algorithms for stochastic clustering
| Title | Approximation algorithms for stochastic clustering |
| Authors | David Harris, Shi Li, Aravind Srinivasan, Khoa Trinh, Thomas Pensyl |
| Abstract | We consider stochastic settings for clustering, and develop provably-good (approximation) algorithms for a number of these notions. These algorithms allow one to obtain better approximation ratios compared to the usual deterministic clustering setting. Additionally, they offer a number of advantages including providing fairer clustering and clustering which has better long-term behavior for each user. In particular, they ensure that every user is guaranteed to get good service (on average). We also complement some of these with impossibility results. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7843-approximation-algorithms-for-stochastic-clustering |
| http://papers.nips.cc/paper/7843-approximation-algorithms-for-stochastic-clustering.pdf | |
| PWC | https://paperswithcode.com/paper/approximation-algorithms-for-stochastic |
| Repo | |
| Framework | |
UDPipe 2.0 Prototype at CoNLL 2018 UD Shared Task
| Title | UDPipe 2.0 Prototype at CoNLL 2018 UD Shared Task |
| Authors | Milan Straka |
| Abstract | UDPipe is a trainable pipeline which performs sentence segmentation, tokenization, POS tagging, lemmatization and dependency parsing. We present a prototype for UDPipe 2.0 and evaluate it in the CoNLL 2018 UD Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, which employs three metrics for submission ranking. Out of 26 participants, the prototype placed first in the MLAS ranking, third in the LAS ranking and third in the BLEX ranking. In extrinsic parser evaluation EPE 2018, the system ranked first in the overall score. |
| Tasks | Dependency Parsing, Lemmatization, Tokenization, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-2020/ |
| https://www.aclweb.org/anthology/K18-2020 | |
| PWC | https://paperswithcode.com/paper/udpipe-20-prototype-at-conll-2018-ud-shared |
| Repo | |
| Framework | |
Learning to Play With Intrinsically-Motivated, Self-Aware Agents
| Title | Learning to Play With Intrinsically-Motivated, Self-Aware Agents |
| Authors | Nick Haber, Damian Mrowca, Stephanie Wang, Li F. Fei-Fei, Daniel L. Yamins |
| Abstract | Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network that implements curiosity-driven intrinsic motivation. Using a simple but ecologically naturalistic simulated environment in which an agent can move and interact with objects it sees, we propose a “world-model” network that learns to predict the dynamic consequences of the agent’s actions. Simultaneously, we train a separate explicit “self-model” that allows the agent to track the error map of its world-model. It then uses the self-model to adversarially challenge the developing world-model. We demonstrate that this policy causes the agent to explore novel and informative interactions with its environment, leading to the generation of a spectrum of complex behaviors, including ego-motion prediction, object attention, and object gathering. Moreover, the world-model that the agent learns supports improved performance on object dynamics prediction, detection, localization and recognition tasks. Taken together, our results are initial steps toward creating flexible autonomous agents that self-supervise in realistic physical environments. |
| Tasks | motion prediction |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8059-learning-to-play-with-intrinsically-motivated-self-aware-agents |
| http://papers.nips.cc/paper/8059-learning-to-play-with-intrinsically-motivated-self-aware-agents.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-play-with-intrinsically-motivated-1 |
| Repo | |
| Framework | |
CRF-LSTM Text Mining Method Unveiling the Pharmacological Mechanism of Off-target Side Effect of Anti-Multiple Myeloma Drugs
| Title | CRF-LSTM Text Mining Method Unveiling the Pharmacological Mechanism of Off-target Side Effect of Anti-Multiple Myeloma Drugs |
| Authors | Kaiyin Zhou, Sheng Zhang, Xiangyu Meng, Qi Luo, Yuxing Wang, Ke Ding, Yukun Feng, Mo Chen, Kevin Cohen, Jingbo Xia |
| Abstract | Sequence labeling of biomedical entities, e.g., side effects or phenotypes, was a long-term task in BioNLP and MedNLP communities. Thanks to effects made among these communities, adverse reaction NER has developed dramatically in recent years. As an illuminative application, to achieve knowledge discovery via the combination of the text mining result and bioinformatics idea shed lights on the pharmacological mechanism research. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2321/ |
| https://www.aclweb.org/anthology/W18-2321 | |
| PWC | https://paperswithcode.com/paper/crf-lstm-text-mining-method-unveiling-the |
| Repo | |
| Framework | |
A Neural Method for Goal-Oriented Dialog Systems to interact with Named Entities
| Title | A Neural Method for Goal-Oriented Dialog Systems to interact with Named Entities |
| Authors | Janarthanan Rajendran, Jatin Ganhotra, Xiaoxiao Guo, Mo Yu, Satinder Singh |
| Abstract | Many goal-oriented dialog tasks, especially ones in which the dialog system has to interact with external knowledge sources such as databases, have to handle a large number of Named Entities (NEs). There are at least two challenges in handling NEs using neural methods in such settings: individual NEs may occur only rarely making it hard to learn good representations of them, and many of the Out Of Vocabulary words that occur during test time may be NEs. Thus, the need to interact well with these NEs has emerged as a serious challenge to building neural methods for goal-oriented dialog tasks. In this paper, we propose a new neural method for this problem, and present empirical evaluations on a structured Question answering task and three related goal-oriented dialog tasks that show that our proposed method can be effective in interacting with NEs in these settings. |
| Tasks | Goal-Oriented Dialog, Question Answering |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ByhthReRb |
| https://openreview.net/pdf?id=ByhthReRb | |
| PWC | https://paperswithcode.com/paper/a-neural-method-for-goal-oriented-dialog |
| Repo | |
| Framework | |
