Paper Group NANR 150
Extract and Aggregate: A Novel Domain-Independent Approach to Factual Data Verification. Interactive Evidence Detection: train state-of-the-art model out-of-domain or simple model interactively?. A deep-learning framework to detect sarcasm targets. Finding Hierarchical Structure in Neural Stacks Using Unsupervised Parsing. Word Embedding-Based Auto …
Extract and Aggregate: A Novel Domain-Independent Approach to Factual Data Verification
| Title | Extract and Aggregate: A Novel Domain-Independent Approach to Factual Data Verification |
| Authors | Anton Chernyavskiy, Dmitry Ilvovsky |
| Abstract | Triggered by Internet development, a large amount of information is published in online sources. However, it is a well-known fact that publications are inundated with inaccurate data. That is why fact-checking has become a significant topic in the last 5 years. It is widely accepted that factual data verification is a challenge even for the experts. This paper presents a domain-independent fact checking system. It can solve the fact verification problem entirely or at the individual stages. The proposed model combines various advanced methods of text data analysis, such as BERT and Infersent. The theoretical and empirical study of the system features is carried out. Based on FEVER and Fact Checking Challenge test-collections, experimental results demonstrate that our model can achieve the score on a par with state-of-the-art models designed by the specificity of particular datasets. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6612/ |
| https://www.aclweb.org/anthology/D19-6612 | |
| PWC | https://paperswithcode.com/paper/extract-and-aggregate-a-novel-domain |
| Repo | |
| Framework | |
Interactive Evidence Detection: train state-of-the-art model out-of-domain or simple model interactively?
| Title | Interactive Evidence Detection: train state-of-the-art model out-of-domain or simple model interactively? |
| Authors | Chris Stahlhut |
| Abstract | Finding evidence is of vital importance in research as well as fact checking and an evidence detection method would be useful in speeding up this process. However, when addressing a new topic there is no training data and there are two approaches to get started. One could use large amounts of out-of-domain data to train a state-of-the-art method, or to use the small data that a person creates while working on the topic. In this paper, we address this problem in two steps. First, by simulating users who read source documents and label sentences they can use as evidence, thereby creating small amounts of training data for an interactively trained evidence detection model; and second, by comparing such an interactively trained model against a pre-trained model that has been trained on large out-of-domain data. We found that an interactively trained model not only often out-performs a state-of-the-art model but also requires significantly lower amounts of computational resources. Therefore, especially when computational resources are scarce, e.g. no GPU available, training a smaller model on the fly is preferable to training a well generalising but resource hungry out-of-domain model. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6613/ |
| https://www.aclweb.org/anthology/D19-6613 | |
| PWC | https://paperswithcode.com/paper/interactive-evidence-detection-train-state-of |
| Repo | |
| Framework | |
A deep-learning framework to detect sarcasm targets
| Title | A deep-learning framework to detect sarcasm targets |
| Authors | Jasabanta Patro, Srijan Bansal, Animesh Mukherjee |
| Abstract | In this paper we propose a deep learning framework for sarcasm target detection in predefined sarcastic texts. Identification of sarcasm targets can help in many core natural language processing tasks such as aspect based sentiment analysis, opinion mining etc. To begin with, we perform an empirical study of the socio-linguistic features and identify those that are statistically significant in indicating sarcasm targets (p-values in the range(0.05,0.001)). Finally, we present a deep-learning framework augmented with socio-linguistic features to detect sarcasm targets in sarcastic book-snippets and tweets.We achieve a huge improvement in the performance in terms of exact match and dice scores compared to the current state-of-the-art baseline. |
| Tasks | Aspect-Based Sentiment Analysis, Opinion Mining, Sentiment Analysis |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1663/ |
| https://www.aclweb.org/anthology/D19-1663 | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-framework-to-detect-sarcasm |
| Repo | |
| Framework | |
Finding Hierarchical Structure in Neural Stacks Using Unsupervised Parsing
| Title | Finding Hierarchical Structure in Neural Stacks Using Unsupervised Parsing |
| Authors | William Merrill, Lenny Khazan, Noah Amsel, Yiding Hao, Simon Mendelsohn, Robert Frank |
| Abstract | Neural network architectures have been augmented with differentiable stacks in order to introduce a bias toward learning hierarchy-sensitive regularities. It has, however, proven difficult to assess the degree to which such a bias is effective, as the operation of the differentiable stack is not always interpretable. In this paper, we attempt to detect the presence of latent representations of hierarchical structure through an exploration of the unsupervised learning of constituency structure. Using a technique due to Shen et al. (2018a,b), we extract syntactic trees from the pushing behavior of stack RNNs trained on language modeling and classification objectives. We find that our models produce parses that reflect natural language syntactic constituencies, demonstrating that stack RNNs do indeed infer linguistically relevant hierarchical structure. |
| Tasks | Language Modelling |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4823/ |
| https://www.aclweb.org/anthology/W19-4823 | |
| PWC | https://paperswithcode.com/paper/finding-hierarchical-structure-in-neural |
| Repo | |
| Framework | |
Word Embedding-Based Automatic MT Evaluation Metric using Word Position Information
| Title | Word Embedding-Based Automatic MT Evaluation Metric using Word Position Information |
| Authors | Hiroshi Echizen{'}ya, Kenji Araki, Eduard Hovy |
| Abstract | We propose a new automatic evaluation metric for machine translation. Our proposed metric is obtained by adjusting the Earth Mover{'}s Distance (EMD) to the evaluation task. The EMD measure is used to obtain the distance between two probability distributions consisting of some signatures having a feature and a weight. We use word embeddings, sentence-level tf-idf, and cosine similarity between two word embeddings, respectively, as the features, weight, and the distance between two features. Results show that our proposed metric can evaluate machine translation based on word meaning. Moreover, for distance, cosine similarity and word position information are used to address word-order differences. We designate this metric as Word Embedding-Based automatic MT evaluation using Word Position Information (WE{_}WPI). A meta-evaluation using WMT16 metrics shared task set indicates that our WE{_}WPI achieves the highest correlation with human judgment among several representative metrics. |
| Tasks | Machine Translation, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1186/ |
| https://www.aclweb.org/anthology/N19-1186 | |
| PWC | https://paperswithcode.com/paper/word-embedding-based-automatic-mt-evaluation |
| Repo | |
| Framework | |
An Attention-Enhanced Recurrent Graph Convolutional Network for Skeleton-Based Action Recognition
| Title | An Attention-Enhanced Recurrent Graph Convolutional Network for Skeleton-Based Action Recognition |
| Authors | Xiaolu Ding, Kai Yang, Wai Chen |
| Abstract | Dynamic movements of human skeleton have attracted more and more attention as a robust modality for action recognition. As not all temporal stages and skeleton joints are informative for action recognition, and the irrelevant information often brings noise which can degrade the detection performance, extracting discriminative temporal and spatial features becomes an important task. In this paper, we propose a novel end-to-end attention-enhanced recurrent graph convolutional network (AR-GCN) for skeleton-based action recognition. An attention-enhanced mechanism is employed in AR-GCN to pay different levels of attention to different temporal stages and spatial joints. This approach overcomes the information loss caused by only using keyframes and key joints. In particular, AR-GCN combines the graph convolutional network (GCN) with the bidirectional recurrent neural network (BRNN), which retains the irregular joints expressive power of the original GCN, while promoting its sequential modeling ability by introducing a recurrent network. Experimental results demonstrate the effectiveness of our proposed model on the widely used NTU and Kinetics |
| Tasks | Skeleton Based Action Recognition |
| Published | 2019-11-27 |
| URL | https://doi.org/10.1145/3372806.3372814 |
| https://dl.acm.org/doi/pdf/10.1145/3372806.3372814 | |
| PWC | https://paperswithcode.com/paper/an-attention-enhanced-recurrent-graph |
| Repo | |
| Framework | |
TUPA at MRP 2019: A Multi-Task Baseline System
| Title | TUPA at MRP 2019: A Multi-Task Baseline System |
| Authors | Daniel Hershcovich, Ofir Arviv |
| Abstract | This paper describes the TUPA system submission to the shared task on Cross-Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL). Because it was prepared by one of the task co-organizers, TUPA provides a baseline point of comparison and is not considered in the official ranking of participating systems. While originally developed for UCCA only, TUPA has been generalized to support all MRP frameworks included in the task, and trained using multi-task learning to parse them all with a shared model. It is a transition-based parser with a BiLSTM encoder, augmented with BERT contextualized embeddings. |
| Tasks | Multi-Task Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-2002/ |
| https://www.aclweb.org/anthology/K19-2002 | |
| PWC | https://paperswithcode.com/paper/tupa-at-mrp-2019-a-multi-task-baseline-system |
| Repo | |
| Framework | |
Investigating Terminology Translation in Statistical and Neural Machine Translation: A Case Study on English-to-Hindi and Hindi-to-English
| Title | Investigating Terminology Translation in Statistical and Neural Machine Translation: A Case Study on English-to-Hindi and Hindi-to-English |
| Authors | Rejwanul Haque, Md Hasanuzzaman, Andy Way |
| Abstract | Terminology translation plays a critical role in domain-specific machine translation (MT). In this paper, we conduct a comparative qualitative evaluation on terminology translation in phrase-based statistical MT (PB-SMT) and neural MT (NMT) in two translation directions: English-to-Hindi and Hindi-to-English. For this, we select a test set from a legal domain corpus and create a gold standard for evaluating terminology translation in MT. We also propose an error typology taking the terminology translation errors into consideration. We evaluate the MT systems{'} performance on terminology translation, and demonstrate our findings, unraveling strengths, weaknesses, and similarities of PB-SMT and NMT in the area of term translation. |
| Tasks | Machine Translation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1052/ |
| https://www.aclweb.org/anthology/R19-1052 | |
| PWC | https://paperswithcode.com/paper/investigating-terminology-translation-in |
| Repo | |
| Framework | |
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
| Title | Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1000/ |
| https://www.aclweb.org/anthology/N19-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2019-conference-of-the |
| Repo | |
| Framework | |
Proceedings of the First Workshop on Gender Bias in Natural Language Processing
| Title | Proceedings of the First Workshop on Gender Bias in Natural Language Processing |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3800/ |
| https://www.aclweb.org/anthology/W19-3800 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-workshop-on-gender |
| Repo | |
| Framework | |
System Description: The Submission of FOKUS to the WMT 19 Robustness Task
| Title | System Description: The Submission of FOKUS to the WMT 19 Robustness Task |
| Authors | Cristian Grozea |
| Abstract | This paper describes the systems of Fraunhofer FOKUS for the WMT 2019 machine translation robustness task. We have made submissions to the EN-FR, FR-EN, and JA-EN language pairs. The first two were made with a baseline translator, trained on clean data for the WMT 2019 biomedical translation task. These baselines improved over the baselines from the MTNT paper by 2 to 4 BLEU points, but where not trained on the same data. The last one used the same model class and training procedure, with induced typos in the training data to increase the model robustness. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5363/ |
| https://www.aclweb.org/anthology/W19-5363 | |
| PWC | https://paperswithcode.com/paper/system-description-the-submission-of-fokus-to |
| Repo | |
| Framework | |
Computational Linguistics Applications for Multimedia Services
| Title | Computational Linguistics Applications for Multimedia Services |
| Authors | Kyeongmin Rim, Kelley Lynch, James Pustejovsky |
| Abstract | We present Computational Linguistics Applications for Multimedia Services (CLAMS), a platform that provides access to computational content analysis tools for archival multimedia material that appear in different media, such as text, audio, image, and video. The primary goal of CLAMS is: (1) to develop an interchange format between multimodal metadata generation tools to ensure interoperability between tools; (2) to provide users with a portable, user-friendly workflow engine to chain selected tools to extract meaningful analyses; and (3) to create a public software development kit (SDK) for developers that eases deployment of analysis tools within the CLAMS platform. CLAMS is designed to help archives and libraries enrich the metadata associated with their mass-digitized multimedia collections, that would otherwise be largely unsearchable. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2512/ |
| https://www.aclweb.org/anthology/W19-2512 | |
| PWC | https://paperswithcode.com/paper/computational-linguistics-applications-for |
| Repo | |
| Framework | |
POS Tagging for Improving Code-Switching Identification in Arabic
| Title | POS Tagging for Improving Code-Switching Identification in Arabic |
| Authors | Mohammed Attia, Younes Samih, Ali Elkahky, Hamdy Mubarak, Ahmed Abdelali, Kareem Darwish |
| Abstract | When speakers code-switch between their native language and a second language or language variant, they follow a syntactic pattern where words and phrases from the embedded language are inserted into the matrix language. This paper explores the possibility of utilizing this pattern in improving code-switching identification between Modern Standard Arabic (MSA) and Egyptian Arabic (EA). We try to answer the question of how strong is the POS signal in word-level code-switching identification. We build a deep learning model enriched with linguistic features (including POS tags) that outperforms the state-of-the-art results by 1.9{%} on the development set and 1.0{%} on the test set. We also show that in intra-sentential code-switching, the selection of lexical items is constrained by POS categories, where function words tend to come more often from the dialectal language while the majority of content words come from the standard language. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4603/ |
| https://www.aclweb.org/anthology/W19-4603 | |
| PWC | https://paperswithcode.com/paper/pos-tagging-for-improving-code-switching |
| Repo | |
| Framework | |
Deep Multiple-Attribute-Perceived Network for Real-World Texture Recognition
| Title | Deep Multiple-Attribute-Perceived Network for Real-World Texture Recognition |
| Authors | Wei Zhai, Yang Cao, Jing Zhang, Zheng-Jun Zha |
| Abstract | Texture recognition is a challenging visual task as multiple perceptual attributes may be perceived from the same texture image when combined with different spatial context. Some recent works building upon Convolutional Neural Network (CNN) incorporate feature encoding with orderless aggregating to provide invariance to spatial layouts. However, these existing methods ignore visual texture attributes, which are important cues for describing the real-world texture images, resulting in incomplete description and inaccurate recognition. To address this problem, we propose a novel deep Multiple-Attribute-Perceived Network (MAP-Net) by progressively learning visual texture attributes in a mutually reinforced manner. Specifically, a multi-branch network architecture is devised, in which cascaded global contexts are learned by introducing similarity constraint at each branch, and leveraged as guidance of spatial feature encoding at next branch through an attribute transfer scheme. To enhance the modeling capability of spatial transformation, a deformable pooling strategy is introduced to augment the spatial sampling with adaptive offsets to the global context, leading to perceive new visual attributes. An attribute fusion module is then introduced to jointly utilize the perceived visual attributes and the abstracted semantic concepts at each branch. Experimental results on the five most challenging texture recognition datasets have demonstrated the superiority of the proposed model against the state-of-the-arts. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zhai_Deep_Multiple-Attribute-Perceived_Network_for_Real-World_Texture_Recognition_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhai_Deep_Multiple-Attribute-Perceived_Network_for_Real-World_Texture_Recognition_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-multiple-attribute-perceived-network-for |
| Repo | |
| Framework | |
Extending Neural Question Answering with Linguistic Input Features
| Title | Extending Neural Question Answering with Linguistic Input Features |
| Authors | Fabian Hommel, Philipp Cimiano, Matthias Orlikowski, Matthias Hartung |
| Abstract | |
| Tasks | Question Answering |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5806/ |
| https://www.aclweb.org/anthology/W19-5806 | |
| PWC | https://paperswithcode.com/paper/extending-neural-question-answering-with |
| Repo | |
| Framework | |
