Paper Group NANR 69
Word-Embedding based Content Features for Automated Oral Proficiency Scoring. Submodular Field Grammars: Representation, Inference, and Application to Image Parsing. Bridging CNNs, RNNs, and Weighted Finite-State Machines. Retrofitting Word Representations for Unsupervised Sense Aware Word Similarities. Investigating the Role of Argumentation in th …
Word-Embedding based Content Features for Automated Oral Proficiency Scoring
| Title | Word-Embedding based Content Features for Automated Oral Proficiency Scoring |
| Authors | Su-Youn Yoon, Anastassia Loukina, Chong Min Lee, Matthew Mulholland, Xinhao Wang, Ikkyu Choi |
| Abstract | |
| Tasks | Speech Recognition, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W18-4002/w18-4002 |
| https://www.aclweb.org/anthology/W18-4002 | |
| PWC | https://paperswithcode.com/paper/word-embedding-based-content-features-for |
| Repo | |
| Framework | |
Submodular Field Grammars: Representation, Inference, and Application to Image Parsing
| Title | Submodular Field Grammars: Representation, Inference, and Application to Image Parsing |
| Authors | Abram L. Friesen, Pedro M. Domingos |
| Abstract | Natural scenes contain many layers of part-subpart structure, and distributions over them are thus naturally represented by stochastic image grammars, with one production per decomposition of a part. Unfortunately, in contrast to language grammars, where the number of possible split points for a production $A \rightarrow BC$ is linear in the length of $A$, in an image there are an exponential number of ways to split a region into subregions. This makes parsing intractable and requires image grammars to be severely restricted in practice, for example by allowing only rectangular regions. In this paper, we address this problem by associating with each production a submodular Markov random field whose labels are the subparts and whose labeling segments the current object into these subparts. We call the result a submodular field grammar (SFG). Finding the MAP split of a region into subregions is now tractable, and by exploiting this we develop an efficient approximate algorithm for MAP parsing of images with SFGs. Empirically, we present promising improvements in accuracy when using SFGs for scene understanding, and show exponential improvements in inference time compared to traditional methods, while returning comparable minima. |
| Tasks | Scene Understanding |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7684-submodular-field-grammars-representation-inference-and-application-to-image-parsing |
| http://papers.nips.cc/paper/7684-submodular-field-grammars-representation-inference-and-application-to-image-parsing.pdf | |
| PWC | https://paperswithcode.com/paper/submodular-field-grammars-representation |
| Repo | |
| Framework | |
Bridging CNNs, RNNs, and Weighted Finite-State Machines
| Title | Bridging CNNs, RNNs, and Weighted Finite-State Machines |
| Authors | Roy Schwartz, Sam Thomson, Noah A. Smith |
| Abstract | Recurrent and convolutional neural networks comprise two distinct families of models that have proven to be useful for encoding natural language utterances. In this paper we present SoPa, a new model that aims to bridge these two approaches. SoPa combines neural representation learning with weighted finite-state automata (WFSAs) to learn a soft version of traditional surface patterns. We show that SoPa is an extension of a one-layer CNN, and that such CNNs are equivalent to a restricted version of SoPa, and accordingly, to a restricted form of WFSA. Empirically, on three text classification tasks, SoPa is comparable or better than both a BiLSTM (RNN) baseline and a CNN baseline, and is particularly useful in small data settings. |
| Tasks | Representation Learning, Text Classification |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1028/ |
| https://www.aclweb.org/anthology/P18-1028 | |
| PWC | https://paperswithcode.com/paper/bridging-cnns-rnns-and-weighted-finite-state |
| Repo | |
| Framework | |
Retrofitting Word Representations for Unsupervised Sense Aware Word Similarities
| Title | Retrofitting Word Representations for Unsupervised Sense Aware Word Similarities |
| Authors | Steffen Remus, Chris Biemann |
| Abstract | |
| Tasks | Named Entity Recognition, Question Answering, Semantic Textual Similarity, Sentiment Analysis, Topic Models, Word Embeddings, Word Sense Induction |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1167/ |
| https://www.aclweb.org/anthology/L18-1167 | |
| PWC | https://paperswithcode.com/paper/retrofitting-word-representations-for |
| Repo | |
| Framework | |
Investigating the Role of Argumentation in the Rhetorical Analysis of Scientific Publications with Neural Multi-Task Learning Models
| Title | Investigating the Role of Argumentation in the Rhetorical Analysis of Scientific Publications with Neural Multi-Task Learning Models |
| Authors | Anne Lauscher, Goran Glava{\v{s}}, Simone Paolo Ponzetto, Kai Eckert |
| Abstract | Exponential growth in the number of scientific publications yields the need for effective automatic analysis of rhetorical aspects of scientific writing. Acknowledging the argumentative nature of scientific text, in this work we investigate the link between the argumentative structure of scientific publications and rhetorical aspects such as discourse categories or citation contexts. To this end, we (1) augment a corpus of scientific publications annotated with four layers of rhetoric annotations with argumentation annotations and (2) investigate neural multi-task learning architectures combining argument extraction with a set of rhetorical classification tasks. By coupling rhetorical classifiers with the extraction of argumentative components in a joint multi-task learning setting, we obtain significant performance gains for different rhetorical analysis tasks. |
| Tasks | Multi-Task Learning |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1370/ |
| https://www.aclweb.org/anthology/D18-1370 | |
| PWC | https://paperswithcode.com/paper/investigating-the-role-of-argumentation-in |
| Repo | |
| Framework | |
Constraint-Aware Deep Neural Network Compression
| Title | Constraint-Aware Deep Neural Network Compression |
| Authors | Changan Chen, Frederick Tung, Naveen Vedula, Greg Mori |
| Abstract | Deep neural network compression has the potential to bring modern resource-hungry deep networks to resource-limited devices. However, in many of the most compelling deployment scenarios of compressed deep networks, the operational constraints matter: for example, a pedestrian detection network on a self-driving car may have to satisfy a latency constraint for safe operation. We propose the first principled treatment of deep network compression under operational constraints. We formulate the compression learning problem from the perspective of constrained Bayesian optimization, and introduce a cooling (annealing) strategy to guide the network compression towards the target constraints. Experiments on ImageNet demonstrate the value of modelling constraints directly in network compression. |
| Tasks | Neural Network Compression, Pedestrian Detection |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Changan_Chen_Constraints_Matter_in_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Changan_Chen_Constraints_Matter_in_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/constraint-aware-deep-neural-network |
| Repo | |
| Framework | |
Recognizing Behavioral Factors while Driving: A Real-World Multimodal Corpus to Monitor the Driver’s Affective State
| Title | Recognizing Behavioral Factors while Driving: A Real-World Multimodal Corpus to Monitor the Driver’s Affective State |
| Authors | Alicia Lotz, Klas Ihme, Audrey Charnoz, Pantelis Maroudis, Ivan Dmitriev, Andreas Wendemuth |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1251/ |
| https://www.aclweb.org/anthology/L18-1251 | |
| PWC | https://paperswithcode.com/paper/recognizing-behavioral-factors-while-driving |
| Repo | |
| Framework | |
EmotionX-SmartDubai_NLP: Detecting User Emotions In Social Media Text
| Title | EmotionX-SmartDubai_NLP: Detecting User Emotions In Social Media Text |
| Authors | Hessa AlBalooshi, Shahram Rahmanian, Rahul Venkatesh Kumar |
| Abstract | This paper describes the working note on {``}EmotionX{''} shared task. It is hosted by SocialNLP 2018. The objective of this task is to detect the emotions, based on each speaker{'}s utterances that are in English. Taking this as multiclass text classification problem, we have experimented to develop a model to classify the target class. The primary challenge in this task is to detect the emotions in short messages, communicated through social media. This paper describes the participation of SmartDubai{_}NLP team in EmotionX shared task and our investigation to detect the emotions from utterance using Neural networks and Natural language understanding. | |
| Tasks | Feature Engineering, Text Classification, Word Sense Disambiguation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3508/ |
| https://www.aclweb.org/anthology/W18-3508 | |
| PWC | https://paperswithcode.com/paper/emotionx-smartdubai_nlp-detecting-user |
| Repo | |
| Framework | |
Detecting Heavy Rain Disaster from Social and Physical Sensor
| Title | Detecting Heavy Rain Disaster from Social and Physical Sensor |
| Authors | Tomoya Iwakura, Seiji Okajima, Nobuyuki Igata, Kunihiro Takeda, Yuzuru Yamakage, Naoshi Morita |
| Abstract | We present our system that assists to detect heavy rain disaster, which is being used in real world in Japan. Our system selects tweets about heavy rain disaster with a document classifier. Then, the locations mentioned in the selected tweets are estimated by a location estimator. Finally, combined the selected tweets with amount of rainfall given by physical sensors and a statistical analysis, our system provides users with visualized results for detecting heavy rain disaster. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-2014/ |
| https://www.aclweb.org/anthology/C18-2014 | |
| PWC | https://paperswithcode.com/paper/detecting-heavy-rain-disaster-from-social-and |
| Repo | |
| Framework | |
Fluency Boost Learning and Inference for Neural Grammatical Error Correction
| Title | Fluency Boost Learning and Inference for Neural Grammatical Error Correction |
| Authors | Tao Ge, Furu Wei, Ming Zhou |
| Abstract | Most of the neural sequence-to-sequence (seq2seq) models for grammatical error correction (GEC) have two limitations: (1) a seq2seq model may not be well generalized with only limited error-corrected data; (2) a seq2seq model may fail to completely correct a sentence with multiple errors through normal seq2seq inference. We attempt to address these limitations by proposing a fluency boost learning and inference mechanism. Fluency boosting learning generates fluency-boost sentence pairs during training, enabling the error correction model to learn how to improve a sentence{'}s fluency from more instances, while fluency boosting inference allows the model to correct a sentence incrementally with multiple inference steps until the sentence{'}s fluency stops increasing. Experiments show our approaches improve the performance of seq2seq models for GEC, achieving state-of-the-art results on both CoNLL-2014 and JFLEG benchmark datasets. |
| Tasks | Grammatical Error Correction |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1097/ |
| https://www.aclweb.org/anthology/P18-1097 | |
| PWC | https://paperswithcode.com/paper/fluency-boost-learning-and-inference-for |
| Repo | |
| Framework | |
IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis
| Title | IARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis |
| Authors | Navonil Majumder, Soujanya Poria, Alex Gelbukh, er, Md. Shad Akhtar, Erik Cambria, Asif Ekbal |
| Abstract | Sentiment analysis has immense implications in e-commerce through user feedback mining. Aspect-based sentiment analysis takes this one step further by enabling businesses to extract aspect specific sentimental information. In this paper, we present a novel approach of incorporating the neighboring aspects related information into the sentiment classification of the target aspect using memory networks. We show that our method outperforms the state of the art by 1.6{%} on average in two distinct domains: restaurant and laptop. |
| Tasks | Aspect-Based Sentiment Analysis, Extract Aspect, Sentiment Analysis |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1377/ |
| https://www.aclweb.org/anthology/D18-1377 | |
| PWC | https://paperswithcode.com/paper/iarm-inter-aspect-relation-modeling-with |
| Repo | |
| Framework | |
LDR at SemEval-2018 Task 3: A Low Dimensional Text Representation for Irony Detection
| Title | LDR at SemEval-2018 Task 3: A Low Dimensional Text Representation for Irony Detection |
| Authors | Bilal Ghanem, Francisco Rangel, Paolo Rosso |
| Abstract | In this paper we describe our participation in the SemEval-2018 task 3 Shared Task on Irony Detection. We have approached the task with our low dimensionality representation method (LDR), which exploits low dimensional features extracted from text on the basis of the occurrence probability of the words depending on each class. Our intuition is that words in ironic texts have different probability of occurrence than in non-ironic ones. Our approach obtained acceptable results in both subtasks A and B. We have performed an error analysis that shows the difference on correct and incorrect classified tweets. |
| Tasks | Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1086/ |
| https://www.aclweb.org/anthology/S18-1086 | |
| PWC | https://paperswithcode.com/paper/ldr-at-semeval-2018-task-3-a-low-dimensional |
| Repo | |
| Framework | |
When science journalism meets artificial intelligence : An interactive demonstration
| Title | When science journalism meets artificial intelligence : An interactive demonstration |
| Authors | Raghuram Vadapalli, Bakhtiyar Syed, Nishant Prabhu, Balaji Vasan Srinivasan, Vasudeva Varma |
| Abstract | We present an online interactive tool that generates titles of blog titles and thus take the first step toward automating science journalism. Science journalism aims to transform jargon-laden scientific articles into a form that the common reader can comprehend while ensuring that the underlying meaning of the article is retained. In this work, we present a tool, which, given the title and abstract of a research paper will generate a blog title by mimicking a human science journalist. The tool makes use of a model trained on a corpus of 87,328 pairs of research papers and their corresponding blogs, built from two science news aggregators. The architecture of the model is a two-stage mechanism which generates blog titles. Evaluation using standard metrics indicate the viability of the proposed system. |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/D18-2028/ |
| https://www.aclweb.org/anthology/D18-2028 | |
| PWC | https://paperswithcode.com/paper/when-science-journalism-meets-artificial |
| Repo | |
| Framework | |
Multi-grained Attention Network for Aspect-Level Sentiment Classification
| Title | Multi-grained Attention Network for Aspect-Level Sentiment Classification |
| Authors | Feifan Fan, Yansong Feng, Dongyan Zhao |
| Abstract | We propose a novel multi-grained attention network (MGAN) model for aspect level sentiment classification. Existing approaches mostly adopt coarse-grained attention mechanism, which may bring information loss if the aspect has multiple words or larger context. We propose a fine-grained attention mechanism, which can capture the word-level interaction between aspect and context. And then we leverage the fine-grained and coarse-grained attention mechanisms to compose the MGAN framework. Moreover, unlike previous works which train each aspect with its context separately, we design an aspect alignment loss to depict the aspect-level interactions among the aspects that have the same context. We evaluate the proposed approach on three datasets: laptop and restaurant are from SemEval 2014, and the last one is a twitter dataset. Experimental results show that the multi-grained attention network consistently outperforms the state-of-the-art methods on all three datasets. We also conduct experiments to evaluate the effectiveness of aspect alignment loss, which indicates the aspect-level interactions can bring extra useful information and further improve the performance. |
| Tasks | Aspect-Based Sentiment Analysis, Sentiment Analysis |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1380/ |
| https://www.aclweb.org/anthology/D18-1380 | |
| PWC | https://paperswithcode.com/paper/multi-grained-attention-network-for-aspect |
| Repo | |
| Framework | |
Contextual Inter-modal Attention for Multi-modal Sentiment Analysis
| Title | Contextual Inter-modal Attention for Multi-modal Sentiment Analysis |
| Authors | Deepanway Ghosal, Md Shad Akhtar, Dushyant Chauhan, Soujanya Poria, Asif Ekbal, Pushpak Bhattacharyya |
| Abstract | Multi-modal sentiment analysis offers various challenges, one being the effective combination of different input modalities, namely text, visual and acoustic. In this paper, we propose a recurrent neural network based multi-modal attention framework that leverages the contextual information for utterance-level sentiment prediction. The proposed approach applies attention on multi-modal multi-utterance representations and tries to learn the contributing features amongst them. We evaluate our proposed approach on two multi-modal sentiment analysis benchmark datasets, viz. CMU Multi-modal Opinion-level Sentiment Intensity (CMU-MOSI) corpus and the recently released CMU Multi-modal Opinion Sentiment and Emotion Intensity (CMU-MOSEI) corpus. Evaluation results show the effectiveness of our proposed approach with the accuracies of 82.31{%} and 79.80{%} for the MOSI and MOSEI datasets, respectively. These are approximately 2 and 1 points performance improvement over the state-of-the-art models for the datasets. |
| Tasks | Multimodal Sentiment Analysis, Sentiment Analysis |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1382/ |
| https://www.aclweb.org/anthology/D18-1382 | |
| PWC | https://paperswithcode.com/paper/contextual-inter-modal-attention-for-multi |
| Repo | |
| Framework | |
