Paper Group NANR 269
bhanodaig at SemEval-2019 Task 6: Categorizing Offensive Language in social media. Exploiting Frame-Semantics and Frame-Semantic Parsing for Automatic Extraction of Typological Information from Descriptive Grammars of Natural Languages. Turning silver into gold: error-focused corpus reannotation with active learning. A Benchmark Corpus of English M …
bhanodaig at SemEval-2019 Task 6: Categorizing Offensive Language in social media
| Title | bhanodaig at SemEval-2019 Task 6: Categorizing Offensive Language in social media |
| Authors | Ritesh Kumar, Guggilla Bhanodai, Rajendra Pamula, Maheswara Reddy Chennuru |
| Abstract | This paper describes the work that our team bhanodaig did at Indian Institute of Technology (ISM) towards OffensEval i.e. identifying and categorizing offensive language in social media. Out of three sub-tasks, we have participated in sub-task B: automatic categorization of offensive types. We perform the task of categorizing offensive language, whether the tweet is targeted insult or untargeted. We use Linear Support Vector Machine for classification. The official ranking metric is macro-averaged F1. Our system gets the score 0.5282 with accuracy 0.8792. However, as new entrant to the field, our scores are encouraging enough to work for better results in future. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2098/ |
| https://www.aclweb.org/anthology/S19-2098 | |
| PWC | https://paperswithcode.com/paper/bhanodaig-at-semeval-2019-task-6-categorizing |
| Repo | |
| Framework | |
Exploiting Frame-Semantics and Frame-Semantic Parsing for Automatic Extraction of Typological Information from Descriptive Grammars of Natural Languages
| Title | Exploiting Frame-Semantics and Frame-Semantic Parsing for Automatic Extraction of Typological Information from Descriptive Grammars of Natural Languages |
| Authors | Shafqat Mumtaz Virk, Azam Sheikh Muhammad, Lars Borin, Muhammad Irfan Aslam, Saania Iqbal, Nazia Khurram |
| Abstract | We describe a novel system for automatic extraction of typological linguistic information from descriptive grammars of natural languages, applying the theory of frame semantics in the form of frame-semantic parsing. The current proof-of-concept system covers a few selected linguistic features, but the methodology is general and can be extended not only to other typological features but also to descriptive grammars written in languages other than English. Such a system is expected to be a useful assistance for automatic curation of typological databases which otherwise are built manually, a very labor and time consuming as well as cognitively taxing enterprise. |
| Tasks | Semantic Parsing |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1143/ |
| https://www.aclweb.org/anthology/R19-1143 | |
| PWC | https://paperswithcode.com/paper/exploiting-frame-semantics-and-frame-semantic |
| Repo | |
| Framework | |
Turning silver into gold: error-focused corpus reannotation with active learning
| Title | Turning silver into gold: error-focused corpus reannotation with active learning |
| Authors | Pierre Andr{'e} M{'e}nard, Antoine Mougeot |
| Abstract | While high quality gold standard annotated corpora are crucial for most tasks in natural language processing, many annotated corpora published in recent years, created by annotators or tools, contains noisy annotations. These corpora can be viewed as more silver than gold standards, even if they are used in evaluation campaigns or to compare systems{'} performances. As upgrading a silver corpus to gold level is still a challenge, we explore the application of active learning techniques to detect errors using four datasets designed for document classification and part-of-speech tagging. Our results show that the proposed method for the seeding step improves the chance of finding incorrect annotations by a factor of 2.73 when compared to random selection, a 14.71{%} increase from the baseline methods. Our query method provides an increase in the error detection precision on average by a factor of 1.78 against random selection, an increase of 61.82{%} compared to other query approaches. |
| Tasks | Active Learning, Document Classification, Part-Of-Speech Tagging |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1088/ |
| https://www.aclweb.org/anthology/R19-1088 | |
| PWC | https://paperswithcode.com/paper/turning-silver-into-gold-error-focused-corpus |
| Repo | |
| Framework | |
A Benchmark Corpus of English Misspellings and a Minimally-supervised Model for Spelling Correction
| Title | A Benchmark Corpus of English Misspellings and a Minimally-supervised Model for Spelling Correction |
| Authors | Michael Flor, Michael Fried, Alla Rozovskaya |
| Abstract | Spelling correction has attracted a lot of attention in the NLP community. However, models have been usually evaluated on artificiallycreated or proprietary corpora. A publiclyavailable corpus of authentic misspellings, annotated in context, is still lacking. To address this, we present and release an annotated data set of 6,121 spelling errors in context, based on a corpus of essays written by English language learners. We also develop a minimallysupervised context-aware approach to spelling correction. It achieves strong results on our data: 88.12{%} accuracy. This approach can also train with a minimal amount of annotated data (performance reduced by less than 1{%}). Furthermore, this approach allows easy portability to new domains. We evaluate our model on data from a medical domain and demonstrate that it rivals the performance of a model trained and tuned on in-domain data. |
| Tasks | Spelling Correction |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4407/ |
| https://www.aclweb.org/anthology/W19-4407 | |
| PWC | https://paperswithcode.com/paper/a-benchmark-corpus-of-english-misspellings |
| Repo | |
| Framework | |
A Dataset of Crowdsourced Word Sequences: Collections and Answer Aggregation for Ground Truth Creation
| Title | A Dataset of Crowdsourced Word Sequences: Collections and Answer Aggregation for Ground Truth Creation |
| Authors | Jiyi Li, Fumiyo Fukumoto |
| Abstract | The target outputs of many NLP tasks are word sequences. To collect the data for training and evaluating models, the crowd is a cheaper and easier to access than the oracle. To ensure the quality of the crowdsourced data, people can assign multiple workers to one question and then aggregate the multiple answers with diverse quality into a golden one. How to aggregate multiple crowdsourced word sequences with diverse quality is a curious and challenging problem. People need a dataset for addressing this problem. We thus create a dataset (CrowdWSA2019) which contains the translated sentences generated from multiple workers. We provide three approaches as the baselines on the task of extractive word sequence aggregation. Specially, one of them is an original one we propose which models the reliability of workers. We also discuss some issues on ground truth creation of word sequences which can be addressed based on this dataset. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5904/ |
| https://www.aclweb.org/anthology/D19-5904 | |
| PWC | https://paperswithcode.com/paper/a-dataset-of-crowdsourced-word-sequences |
| Repo | |
| Framework | |
Question Answering Systems Approaches and Challenges
| Title | Question Answering Systems Approaches and Challenges |
| Authors | Reem Alqifari |
| Abstract | Question answering (QA) systems permit the user to ask a question using natural language, and the system provides a concise and correct answer. QA systems can be implemented for different types of datasets, structured or unstructured. In this paper, some of the recent studies will be reviewed and the limitations will be discussed. Consequently, the current issues are analyzed with the proposed solutions. |
| Tasks | Question Answering |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-2011/ |
| https://www.aclweb.org/anthology/R19-2011 | |
| PWC | https://paperswithcode.com/paper/question-answering-systems-approaches-and |
| Repo | |
| Framework | |
Dual Variational Generation for Low Shot Heterogeneous Face Recognition
| Title | Dual Variational Generation for Low Shot Heterogeneous Face Recognition |
| Authors | Chaoyou Fu, Xiang Wu, Yibo Hu, Huaibo Huang, Ran He |
| Abstract | Heterogeneous Face Recognition (HFR) is a challenging issue because of the large domain discrepancy and a lack of heterogeneous data. This paper considers HFR as a dual generation problem, and proposes a novel Dual Variational Generation (DVG) framework. It generates large-scale new paired heterogeneous images with the same identity from noise, for the sake of reducing the domain gap of HFR. Specifically, we first introduce a dual variational autoencoder to represent a joint distribution of paired heterogeneous images. Then, in order to ensure the identity consistency of the generated paired heterogeneous images, we impose a distribution alignment in the latent space and a pairwise identity preserving in the image space. Moreover, the HFR network reduces the domain discrepancy by constraining the pairwise feature distances between the generated paired heterogeneous images. Extensive experiments on four HFR databases show that our method can significantly improve state-of-the-art results. When using the generated paired images for training, our method gains more than 18% True Positive Rate improvements over the baseline model when False Positive Rate is at $10^{-5}$. |
| Tasks | Face Recognition, Heterogeneous Face Recognition |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8535-dual-variational-generation-for-low-shot-heterogeneous-face-recognition |
| http://papers.nips.cc/paper/8535-dual-variational-generation-for-low-shot-heterogeneous-face-recognition.pdf | |
| PWC | https://paperswithcode.com/paper/dual-variational-generation-for-low-shot-1 |
| Repo | |
| Framework | |
Joint Multiple Intent Detection and Slot Labeling for Goal-Oriented Dialog
| Title | Joint Multiple Intent Detection and Slot Labeling for Goal-Oriented Dialog |
| Authors | Rashmi Gangadharaiah, Balakrishnan Narayanaswamy |
| Abstract | Neural network models have recently gained traction for sentence-level intent classification and token-based slot-label identification. In many real-world scenarios, users have multiple intents in the same utterance, and a token-level slot label can belong to more than one intent. We investigate an attention-based neural network model that performs multi-label classification for identifying multiple intents and produces labels for both intents and slot-labels at the token-level. We show state-of-the-art performance for both intent detection and slot-label identification by comparing against strong, recently proposed models. Our model provides a small but statistically significant improvement of 0.2{%} on the predominantly single-intent ATIS public data set, and 55{%} intent accuracy improvement on an internal multi-intent dataset. |
| Tasks | Goal-Oriented Dialog, Intent Classification, Intent Detection, Multi-Label Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1055/ |
| https://www.aclweb.org/anthology/N19-1055 | |
| PWC | https://paperswithcode.com/paper/joint-multiple-intent-detection-and-slot |
| Repo | |
| Framework | |
Geotagging a Diachronic Corpus of Alpine Texts: Comparing Distinct Approaches to Toponym Recognition
| Title | Geotagging a Diachronic Corpus of Alpine Texts: Comparing Distinct Approaches to Toponym Recognition |
| Authors | Tannon Kew, Anastassia Shaitarova, Isabel Meraner, Janis Goldzycher, Simon Clematide, Martin Volk |
| Abstract | Geotagging historic and cultural texts provides valuable access to heritage data, enabling location-based searching and new geographically related discoveries. In this paper, we describe two distinct approaches to geotagging a variety of fine-grained toponyms in a diachronic corpus of alpine texts. By applying a traditional gazetteer-based approach, aided by a few simple heuristics, we attain strong high-precision annotations. Using the output of this earlier system, we adopt a state-of-the-art neural approach in order to facilitate the detection of new toponyms on the basis of context. Additionally, we present the results of preliminary experiments on integrating a small amount of crowdsourced annotations to improve overall performance of toponym recognition in our heritage corpus. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-9003/ |
| https://www.aclweb.org/anthology/W19-9003 | |
| PWC | https://paperswithcode.com/paper/geotagging-a-diachronic-corpus-of-alpine |
| Repo | |
| Framework | |
Attention Neural Model for Temporal Relation Extraction
| Title | Attention Neural Model for Temporal Relation Extraction |
| Authors | Sijia Liu, Liwei Wang, Vipin Chaudhary, Hongfang Liu |
| Abstract | Neural network models have shown promise in the temporal relation extraction task. In this paper, we present the attention based neural network model to extract the containment relations within sentences from clinical narratives. The attention mechanism used on top of GRU model outperforms the existing state-of-the-art neural network models on THYME corpus in intra-sentence temporal relation extraction. |
| Tasks | Relation Extraction |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1917/ |
| https://www.aclweb.org/anthology/W19-1917 | |
| PWC | https://paperswithcode.com/paper/attention-neural-model-for-temporal-relation |
| Repo | |
| Framework | |
Learning to Detect Human-Object Interactions With Knowledge
| Title | Learning to Detect Human-Object Interactions With Knowledge |
| Authors | Bingjie Xu, Yongkang Wong, Junnan Li, Qi Zhao, Mohan S. Kankanhalli |
| Abstract | The recent advances in instance-level detection tasks lay a strong foundation for automated visual scenes understanding. However, the ability to fully comprehend a social scene still eludes us. In this work, we focus on detecting human-object interactions (HOIs) in images, an essential step towards deeper scene understanding. HOI detection aims to localize human and objects, as well as to identify the complex interactions between them. Innate in practical problems with large label space, HOI categories exhibit a long-tail distribution, i.e., there exist some rare categories with very few training samples. Given the key observation that HOIs contain intrinsic semantic regularities despite they are visually diverse, we tackle the challenge of long-tail HOI categories by modeling the underlying regularities among verbs and objects in HOIs as well as general relationships. In particular, we construct a knowledge graph based on the ground-truth annotations of training dataset and external source. In contrast to direct knowledge incorporation, we address the necessity of dynamic image-specific knowledge retrieval by multi-modal learning, which leads to an enhanced semantic embedding space for HOI comprehension. The proposed method shows improved performance on V-COCO and HICO-DET benchmarks, especially when predicting the rare HOI categories. |
| Tasks | Human-Object Interaction Detection, Scene Understanding |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Xu_Learning_to_Detect_Human-Object_Interactions_With_Knowledge_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Xu_Learning_to_Detect_Human-Object_Interactions_With_Knowledge_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-detect-human-object-interactions-1 |
| Repo | |
| Framework | |
A Deep Reinforced Sequence-to-Set Model for Multi-Label Classification
| Title | A Deep Reinforced Sequence-to-Set Model for Multi-Label Classification |
| Authors | Pengcheng Yang, Fuli Luo, Shuming Ma, Junyang Lin, Xu Sun |
| Abstract | Multi-label classification (MLC) aims to predict a set of labels for a given instance. Based on a pre-defined label order, the sequence-to-sequence (Seq2Seq) model trained via maximum likelihood estimation method has been successfully applied to the MLC task and shows powerful ability to capture high-order correlations between labels. However, the output labels are essentially an unordered set rather than an ordered sequence. This inconsistency tends to result in some intractable problems, e.g., sensitivity to the label order. To remedy this, we propose a simple but effective sequence-to-set model. The proposed model is trained via reinforcement learning, where reward feedback is designed to be independent of the label order. In this way, we can reduce the dependence of the model on the label order, as well as capture high-order correlations between labels. Extensive experiments show that our approach can substantially outperform competitive baselines, as well as effectively reduce the sensitivity to the label order. |
| Tasks | Multi-Label Classification |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1518/ |
| https://www.aclweb.org/anthology/P19-1518 | |
| PWC | https://paperswithcode.com/paper/a-deep-reinforced-sequence-to-set-model-for-1 |
| Repo | |
| Framework | |
SEQ^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression
| Title | SEQ^3: Differentiable Sequence-to-Sequence-to-Sequence Autoencoder for Unsupervised Abstractive Sentence Compression |
| Authors | Christos Baziotis, Ion Androutsopoulos, Ioannis Konstas, Alex Potamianos, ros |
| Abstract | Neural sequence-to-sequence models are currently the dominant approach in several natural language processing tasks, but require large parallel corpora. We present a sequence-to-sequence-to-sequence autoencoder (SEQ{^{}}3), consisting of two chained encoder-decoder pairs, with words used as a sequence of discrete latent variables. We apply the proposed model to unsupervised abstractive sentence compression, where the first and last sequences are the input and reconstructed sentences, respectively, while the middle sequence is the compressed sentence. Constraining the length of the latent word sequences forces the model to distill important information from the input. A pretrained language model, acting as a prior over the latent sequences, encourages the compressed sentences to be human-readable. Continuous relaxations enable us to sample from categorical distributions, allowing gradient-based optimization, unlike alternatives that rely on reinforcement learning. The proposed model does not require parallel text-summary pairs, achieving promising results in unsupervised sentence compression on benchmark datasets. |
| Tasks | Language Modelling, Sentence Compression, Unsupervised Sentence Compression |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1071/ |
| https://www.aclweb.org/anthology/N19-1071 | |
| PWC | https://paperswithcode.com/paper/seq3-differentiable-sequence-to-sequence-to-1 |
| Repo | |
| Framework | |
Opinion Mining with Deep Contextualized Embeddings
| Title | Opinion Mining with Deep Contextualized Embeddings |
| Authors | Wen-Bin Han, K, Noriko o |
| Abstract | Detecting opinion expression is a potential and essential task in opinion mining that can be extended to advanced tasks. In this paper, we considered opinion expression detection as a sequence labeling task and exploited different deep contextualized embedders into the state-of-the-art architecture, composed of bidirectional long short-term memory (BiLSTM) and conditional random field (CRF). Our experimental results show that using different word embeddings can cause contrasting results, and the model can achieve remarkable scores with deep contextualized embeddings. Especially, using BERT embedder can significantly exceed using ELMo embedder. |
| Tasks | Opinion Mining, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-3006/ |
| https://www.aclweb.org/anthology/N19-3006 | |
| PWC | https://paperswithcode.com/paper/opinion-mining-with-deep-contextualized |
| Repo | |
| Framework | |
Discourse Relation Prediction: Revisiting Word Pairs with Convolutional Networks
| Title | Discourse Relation Prediction: Revisiting Word Pairs with Convolutional Networks |
| Authors | Siddharth Varia, Christopher Hidey, Tuhin Chakrabarty |
| Abstract | Word pairs across argument spans have been shown to be effective for predicting the discourse relation between them. We propose an approach to distill knowledge from word pairs for discourse relation classification with convolutional neural networks by incorporating joint learning of implicit and explicit relations. Our novel approach of representing the input as word pairs achieves state-of-the-art results on four-way classification of both implicit and explicit relations as well as one of the binary classification tasks. For explicit relation prediction, we achieve around 20{%} error reduction on the four-way task. At the same time, compared to a two-layered Bi-LSTM-CRF model, our model is able to achieve these results with half the number of learnable parameters and approximately half the amount of training time. |
| Tasks | Relation Classification |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5951/ |
| https://www.aclweb.org/anthology/W19-5951 | |
| PWC | https://paperswithcode.com/paper/discourse-relation-prediction-revisiting-word |
| Repo | |
| Framework | |
