Paper Group NANR 139
Toponym Detection in the Bio-Medical Domain: A Hybrid Approach with Deep Learning. Dimensionality reduction: theoretical perspective on practical measures. Unsupervised dialogue intent detection via hierarchical topic model. Policy Preference Detection in Parliamentary Debate Motions. The MADAR Shared Task on Arabic Fine-Grained Dialect Identificat …
Toponym Detection in the Bio-Medical Domain: A Hybrid Approach with Deep Learning
| Title | Toponym Detection in the Bio-Medical Domain: A Hybrid Approach with Deep Learning |
| Authors | Alistair Plum, Tharindu Ranasinghe, Constantin Orasan |
| Abstract | This paper compares how different machine learning classifiers can be used together with simple string matching and named entity recognition to detect locations in texts. We compare five different state-of-the-art machine learning classifiers in order to predict whether a sentence contains a location or not. Following this classification task, we use a string matching algorithm with a gazetteer to identify the exact index of a toponym within the sentence. We evaluate different approaches in terms of machine learning classifiers, text pre-processing and location extraction on the SemEval-2019 Task 12 dataset, compiled for toponym resolution in the bio-medical domain. Finally, we compare the results with our system that was previously submitted to the SemEval-2019 task evaluation. |
| Tasks | Named Entity Recognition |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1106/ |
| https://www.aclweb.org/anthology/R19-1106 | |
| PWC | https://paperswithcode.com/paper/toponym-detection-in-the-bio-medical-domain-a |
| Repo | |
| Framework | |
Dimensionality reduction: theoretical perspective on practical measures
| Title | Dimensionality reduction: theoretical perspective on practical measures |
| Authors | Yair Bartal, Nova Fandina, Ofer Neiman |
| Abstract | Dimensionality reduction plays a central role in real-world applications for Machine Learning, among many fields. In particular, metric dimensionality reduction where data from a general metric is mapped into low dimensional space, is often used as a first step before applying machine learning algorithms. In almost all these applications the quality of the embedding is measured by various average case criteria. Metric dimensionality reduction has also been studied in Math and TCS, within the extremely fruitful and influential field of metric embedding. Yet, the vast majority of theoretical research has been devoted to analyzing the worst case behavior of embeddings and therefore has little relevance to practical settings. The goal of this paper is to bridge the gap between theory and practice view-points of metric dimensionality reduction, laying the foundation for a theoretical study of more practically oriented analysis. This paper can be viewed as providing a comprehensive theoretical framework addressing a line of research initiated by VL [NeuroIPS’ 18] who have set the goal of analyzing different distortion measurement criteria, with the lens of Machine Learning applicability, from both theoretical and practical perspectives. We complement their work by considering some important and vastly used average case criteria, some of which originated within the well-known Multi-Dimensional Scaling framework. While often studied in practice, no theoretical studies have thus far attempted at providing rigorous analysis of these criteria. In this paper we provide the first analysis of these, as well as the new distortion measure developed by [VL18] designed to possess Machine Learning desired properties. Moreover, we show that all measures considered can be adapted to possess similar qualities. The main consequences of our work are nearly tight bounds on the absolute values of all distortion criteria, as well as first approximation algorithms with provable guarantees. |
| Tasks | Dimensionality Reduction |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9243-dimensionality-reduction-theoretical-perspective-on-practical-measures |
| http://papers.nips.cc/paper/9243-dimensionality-reduction-theoretical-perspective-on-practical-measures.pdf | |
| PWC | https://paperswithcode.com/paper/dimensionality-reduction-theoretical |
| Repo | |
| Framework | |
Unsupervised dialogue intent detection via hierarchical topic model
| Title | Unsupervised dialogue intent detection via hierarchical topic model |
| Authors | Artem Popov, Victor Bulatov, Darya Polyudova, Eugenia Veselova |
| Abstract | One of the challenges during a task-oriented chatbot development is the scarce availability of the labeled training data. The best way of getting one is to ask the assessors to tag each dialogue according to its intent. Unfortunately, performing labeling without any provisional collection structure is difficult since the very notion of the intent is ill-defined. In this paper, we propose a hierarchical multimodal regularized topic model to obtain a first approximation of the intent set. Our rationale for hierarchical models usage is their ability to take into account several degrees of the dialogues relevancy. We attempt to build a model that can distinguish between subject-based (e.g. medicine and transport topics) and action-based (e.g. filing of an application and tracking application status) similarities. In order to achieve this, we divide set of all features into several groups according to part-of-speech analysis. Various feature groups are treated differently on different hierarchy levels. |
| Tasks | Chatbot, Intent Detection |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1108/ |
| https://www.aclweb.org/anthology/R19-1108 | |
| PWC | https://paperswithcode.com/paper/unsupervised-dialogue-intent-detection-via |
| Repo | |
| Framework | |
Policy Preference Detection in Parliamentary Debate Motions
| Title | Policy Preference Detection in Parliamentary Debate Motions |
| Authors | Gavin Abercrombie, Federico Nanni, Riza Batista-Navarro, Simone Paolo Ponzetto |
| Abstract | Debate motions (proposals) tabled in the UK Parliament contain information about the stated policy preferences of the Members of Parliament who propose them, and are key to the analysis of all subsequent speeches given in response to them. We attempt to automatically label debate motions with codes from a pre-existing coding scheme developed by political scientists for the annotation and analysis of political parties{'} manifestos. We develop annotation guidelines for the task of applying these codes to debate motions at two levels of granularity and produce a dataset of manually labelled examples. We evaluate the annotation process and the reliability and utility of the labelling scheme, finding that inter-annotator agreement is comparable with that of other studies conducted on manifesto data. Moreover, we test a variety of ways of automatically labelling motions with the codes, ranging from similarity matching to neural classification methods, and evaluate them against the gold standard labels. From these experiments, we note that established supervised baselines are not always able to improve over simple lexical heuristics. At the same time, we detect a clear and evident benefit when employing BERT, a state-of-the-art deep language representation model, even in classification scenarios with over 30 different labels and limited amounts of training data. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1024/ |
| https://www.aclweb.org/anthology/K19-1024 | |
| PWC | https://paperswithcode.com/paper/policy-preference-detection-in-parliamentary |
| Repo | |
| Framework | |
The MADAR Shared Task on Arabic Fine-Grained Dialect Identification
| Title | The MADAR Shared Task on Arabic Fine-Grained Dialect Identification |
| Authors | Houda Bouamor, Sabit Hassan, Nizar Habash |
| Abstract | In this paper, we present the results and findings of the MADAR Shared Task on Arabic Fine-Grained Dialect Identification. This shared task was organized as part of The Fourth Arabic Natural Language Processing Workshop, collocated with ACL 2019. The shared task includes two subtasks: the MADAR Travel Domain Dialect Identification subtask (Subtask 1) and the MADAR Twitter User Dialect Identification subtask (Subtask 2). This shared task is the first to target a large set of dialect labels at the city and country levels. The data for the shared task was created or collected under the Multi-Arabic Dialect Applications and Resources (MADAR) project. A total of 21 teams from 15 countries participated in the shared task. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4622/ |
| https://www.aclweb.org/anthology/W19-4622 | |
| PWC | https://paperswithcode.com/paper/the-madar-shared-task-on-arabic-fine-grained |
| Repo | |
| Framework | |
Ground-to-Aerial Image Geo-Localization With a Hard Exemplar Reweighting Triplet Loss
| Title | Ground-to-Aerial Image Geo-Localization With a Hard Exemplar Reweighting Triplet Loss |
| Authors | Sudong Cai, Yulan Guo, Salman Khan, Jiwei Hu, Gongjian Wen |
| Abstract | The task of ground-to-aerial image geo-localization can be achieved by matching a ground view query image to a reference database of aerial/satellite images. It is highly challenging due to the dramatic viewpoint changes and unknown orientations. In this paper, we propose a novel in-batch reweighting triplet loss to emphasize the positive effect of hard exemplars during end-to-end training. We also integrate an attention mechanism into our model using feature-level contextual information. To analyze the difficulty level of each triplet, we first enforce a modified logistic regression to triplets with a distance rectifying factor. Then, the reference negative distances for corresponding anchors are set, and the relative weights of triplets are computed by comparing their difficulty to the corresponding references. To reduce the influence of extreme hard data and less useful simple exemplars, the final weights are pruned using upper and lower bound constraints. Experiments on two benchmark datasets show that the proposed approach significantly outperforms the state-of-the-art methods. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Cai_Ground-to-Aerial_Image_Geo-Localization_With_a_Hard_Exemplar_Reweighting_Triplet_Loss_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Cai_Ground-to-Aerial_Image_Geo-Localization_With_a_Hard_Exemplar_Reweighting_Triplet_Loss_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/ground-to-aerial-image-geo-localization-with |
| Repo | |
| Framework | |
Generating Formality-Tuned Summaries Using Input-Dependent Rewards
| Title | Generating Formality-Tuned Summaries Using Input-Dependent Rewards |
| Authors | Kushal Chawla, Balaji Vasan Srinivasan, Niyati Chhaya |
| Abstract | Abstractive text summarization aims at generating human-like summaries by understanding and paraphrasing the given input content. Recent efforts based on sequence-to-sequence networks only allow the generation of a single summary. However, it is often desirable to accommodate the psycho-linguistic preferences of the intended audience while generating the summaries. In this work, we present a reinforcement learning based approach to generate formality-tailored summaries for an input article. Our novel input-dependent reward function aids in training the model with stylistic feedback on sampled and ground-truth summaries together. Once trained, the same model can generate formal and informal summary variants. Our automated and qualitative evaluations show the viability of the proposed framework. |
| Tasks | Abstractive Text Summarization, Text Summarization |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1078/ |
| https://www.aclweb.org/anthology/K19-1078 | |
| PWC | https://paperswithcode.com/paper/generating-formality-tuned-summaries-using |
| Repo | |
| Framework | |
Classification of Micro-Texts Using Sub-Word Embeddings
| Title | Classification of Micro-Texts Using Sub-Word Embeddings |
| Authors | Mihir Joshi, Nur Zincir-Heywood |
| Abstract | Extracting features and writing styles from short text messages is always a challenge. Short messages, like tweets, do not have enough data to perform statistical authorship attribution. Besides, the vocabulary used in these texts is sometimes improvised or misspelled. Therefore, in this paper, we propose combining four feature extraction techniques namely character n-grams, word n-grams, Flexible Patterns and a new sub-word embedding using the skip-gram model. Our system uses a Multi-Layer Perceptron to utilize these features from tweets to analyze short text messages. This proposed system achieves 85{%} accuracy, which is a considerable improvement over previous systems. |
| Tasks | Word Embeddings |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1062/ |
| https://www.aclweb.org/anthology/R19-1062 | |
| PWC | https://paperswithcode.com/paper/classification-of-micro-texts-using-sub-word |
| Repo | |
| Framework | |
Graph Embeddings for Frame Identification
| Title | Graph Embeddings for Frame Identification |
| Authors | Alex Popov, er, Jennifer Sikos |
| Abstract | Lexical resources such as WordNet (Miller, 1995) and FrameNet (Baker et al., 1998) are organized as graphs, where relationships between words are made explicit via the structure of the resource. This work explores how structural information from these lexical resources can lead to gains in a downstream task, namely frame identification. While much of the current work in frame identification uses various neural architectures to predict frames, those neural architectures only use representations of frames based on annotated corpus data. We demonstrate how incorporating knowledge directly from the FrameNet graph structure improves the performance of a neural network-based frame identification system. Specifically, we construct a bidirectional LSTM with a loss function that incorporates various graph- and corpus-based frame embeddings for learning and ultimately achieves strong performance gains with the graph-based embeddings over corpus-based embeddings alone. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1109/ |
| https://www.aclweb.org/anthology/R19-1109 | |
| PWC | https://paperswithcode.com/paper/graph-embeddings-for-frame-identification |
| Repo | |
| Framework | |
On Committee Representations of Adversarial Learning Models for Question-Answer Ranking
| Title | On Committee Representations of Adversarial Learning Models for Question-Answer Ranking |
| Authors | Sparsh Gupta, Vitor Carvalho |
| Abstract | Adversarial training is a process in Machine Learning that explicitly trains models on adversarial inputs (inputs designed to deceive or trick the learning process) in order to make it more robust or accurate. In this paper we investigate how representing adversarial training models as committees can be used to effectively improve the performance of Question-Answer (QA) Ranking. We start by empirically probing the effects of adversarial training over multiple QA ranking algorithms, including the state-of-the-art Multihop Attention Network model. We evaluate these algorithms on several benchmark datasets and observe that, while adversarial training is beneficial to most baseline algorithms, there are cases where it may lead to overfitting and performance degradation. We investigate the causes of such degradation, and then propose a new representation procedure for this adversarial learning problem, based on committee learning, that not only is capable of consistently improving all baseline algorithms, but also outperforms the previous state-of-the-art algorithm by as much as 6{%} in NDCG. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4325/ |
| https://www.aclweb.org/anthology/W19-4325 | |
| PWC | https://paperswithcode.com/paper/on-committee-representations-of-adversarial |
| Repo | |
| Framework | |
From Strings to Things: Knowledge-Enabled VQA Model That Can Read and Reason
| Title | From Strings to Things: Knowledge-Enabled VQA Model That Can Read and Reason |
| Authors | Ajeet Kumar Singh, Anand Mishra, Shashank Shekhar, Anirban Chakraborty |
| Abstract | Text present in images are not merely strings, they provide useful cues about the image. Despite their utility in better image understanding, scene texts are not used in traditional visual question answering (VQA) models. In this work, we present a VQA model which can read scene texts and perform reasoning on a knowledge graph to arrive at an accurate answer. Our proposed model has three mutually interacting modules: i. proposal module to get word and visual content proposals from the image, ii. fusion module to fuse these proposals, question and knowledge base to mine relevant facts, and represent these facts as multi-relational graph, iii. reasoning module to perform a novel gated graph neural network based reasoning on this graph. The performance of our knowledge-enabled VQA model is evaluated on our newly introduced dataset, viz. text-KVQA. To the best of our knowledge, this is the first dataset which identifies the need for bridging text recognition with knowledge graph based reasoning. Through extensive experiments, we show that our proposed method outperforms traditional VQA as well as question-answering over knowledge base-based methods on text-KVQA. |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Singh_From_Strings_to_Things_Knowledge-Enabled_VQA_Model_That_Can_Read_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Singh_From_Strings_to_Things_Knowledge-Enabled_VQA_Model_That_Can_Read_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/from-strings-to-things-knowledge-enabled-vqa |
| Repo | |
| Framework | |
A Framework for Relation Extraction Across Multiple Datasets in Multiple Domains
| Title | A Framework for Relation Extraction Across Multiple Datasets in Multiple Domains |
| Authors | Geeticka Chauhan, Matthew McDermott, Peter Szolovits |
| Abstract | In this work, we aim to build a unifying framework for relation extraction (RE), applying this on 3 highly used datasets with the ability to be extendable to new datasets. At the moment, the domain suffers from lack of reproducibility as well as a lack of consensus on generalizable techniques. Our framework will be open-sourced and will aid in performing systematic exploration on the effect of different modeling techniques, pre-processing, training methodologies and evaluation metrics on the 3 datasets to help establish a consensus. |
| Tasks | Relation Extraction |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3608/ |
| https://www.aclweb.org/anthology/W19-3608 | |
| PWC | https://paperswithcode.com/paper/a-framework-for-relation-extraction-across |
| Repo | |
| Framework | |
Quantum-based subgraph convolutional neural networks
| Title | Quantum-based subgraph convolutional neural networks |
| Authors | Zhihong Zhang, Dongdong Chen, Jianjia Wang, Lu Bai, Edwin R.Hancock |
| Abstract | This paper proposes a new graph convolutional neural network architecture based on a depth-based representation of graph structure deriving from quantum walks, which we refer to as the quantum-based subgraph convolutional neural network (QS-CNNs). This new architecture captures both the global topological structure and the local connectivity structure within a graph. Specifically, we commence by establishing a family of K-layer expansion subgraphs for each vertex of a graph by quantum walks, which captures the global topological arrangement information for substructures contained within a graph. We then design a set of fixed-size convolution filters over the subgraphs, which helps to characterise multi-scale patterns residing in the data. The idea is to apply convolution filters sliding over the entire set of subgraphs rooted at a vertex to extract the local features analogous to the standard convolution operation on grid data. Experiments on eight graph-structured datasets demonstrate that QS-CNNs architecture is capable of outperforming fourteen state-of-the-art methods for the tasks of node classification and graph classification. |
| Tasks | Graph Classification, Node Classification |
| Published | 2019-04-01 |
| URL | https://doi.org/10.1016/j.patcog.2018.11.002 |
| http://eprints.whiterose.ac.uk/139142/ | |
| PWC | https://paperswithcode.com/paper/quantum-based-subgraph-convolutional-neural |
| Repo | |
| Framework | |
BNU-HKBU UIC NLP Team 2 at SemEval-2019 Task 6: Detecting Offensive Language Using BERT model
| Title | BNU-HKBU UIC NLP Team 2 at SemEval-2019 Task 6: Detecting Offensive Language Using BERT model |
| Authors | Zhenghao Wu, Hao Zheng, Jianming Wang, Weifeng Su, Jefferson Fong |
| Abstract | In this study we deal with the problem of identifying and categorizing offensive language in social media. Our group, BNU-HKBU UIC NLP Team2, use supervised classification along with multiple version of data generated by different ways of pre-processing the data. We then use the state-of-the-art model Bidirectional Encoder Representations from Transformers, or BERT (Devlin et al, 2018), to capture linguistic, syntactic and semantic features. Long range dependencies between each part of a sentence can be captured by BERT{'}s bidirectional encoder representations. Our results show 85.12{%} accuracy and 80.57{%} F1 scores in Subtask A (offensive language identification), 87.92{%} accuracy and 50{%} F1 scores in Subtask B (categorization of offense types), and 69.95{%} accuracy and 50.47{%} F1 score in Subtask C (offense target identification). Analysis of the results shows that distinguishing between targeted and untargeted offensive language is not a simple task. More work needs to be done on the unbalance data problem in Subtasks B and C. Some future work is also discussed. |
| Tasks | Language Identification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2099/ |
| https://www.aclweb.org/anthology/S19-2099 | |
| PWC | https://paperswithcode.com/paper/bnu-hkbu-uic-nlp-team-2-at-semeval-2019-task |
| Repo | |
| Framework | |
The Universitat d’Alacant Submissions to the English-to-Kazakh News Translation Task at WMT 2019
| Title | The Universitat d’Alacant Submissions to the English-to-Kazakh News Translation Task at WMT 2019 |
| Authors | V{'\i}ctor M. S{'a}nchez-Cartagena, Juan Antonio P{'e}rez-Ortiz, Felipe S{'a}nchez-Mart{'\i}nez |
| Abstract | This paper describes the two submissions of Universitat d{'}Alacant to the English-to-Kazakh news translation task at WMT 2019. Our submissions take advantage of monolingual data and parallel data from other language pairs by means of iterative backtranslation, pivot backtranslation and transfer learning. They also use linguistic information in two ways: morphological segmentation of Kazakh text, and integration of the output of a rule-based machine translation system. Our systems were ranked second in terms of chrF++ despite being built from an ensemble of only 2 independent training runs. |
| Tasks | Machine Translation, Transfer Learning |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5339/ |
| https://www.aclweb.org/anthology/W19-5339 | |
| PWC | https://paperswithcode.com/paper/the-universitat-dalacant-submissions-to-the |
| Repo | |
| Framework | |
