Paper Group NANR 106
The FinSBD-2019 Shared Task: Sentence Boundary Detection in PDF Noisy Text in the Financial Domain. An Arabic Multi-Domain Spoken Language Understanding System. Improving Domain Adaptation for Machine Translation withTranslation Pieces. Raising the TM Threshold in Neural MT Post-Editing: a Case Study onTwo Datasets. A Continuous Improvement Framewo …
The FinSBD-2019 Shared Task: Sentence Boundary Detection in PDF Noisy Text in the Financial Domain
| Title | The FinSBD-2019 Shared Task: Sentence Boundary Detection in PDF Noisy Text in the Financial Domain |
| Authors | Abderrahim Ait Azzi, Houda Bouamor, Sira Ferradans |
| Abstract | |
| Tasks | Boundary Detection |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5512/ |
| https://www.aclweb.org/anthology/W19-5512 | |
| PWC | https://paperswithcode.com/paper/the-finsbd-2019-shared-task-sentence-boundary |
| Repo | |
| Framework | |
An Arabic Multi-Domain Spoken Language Understanding System
| Title | An Arabic Multi-Domain Spoken Language Understanding System |
| Authors | Mohamed Lichouri, Mourad Abbas, Rachida Djeradi, Amar Djeradi |
| Abstract | |
| Tasks | Spoken Language Understanding |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-7407/ |
| https://www.aclweb.org/anthology/W19-7407 | |
| PWC | https://paperswithcode.com/paper/an-arabic-multi-domain-spoken-language |
| Repo | |
| Framework | |
Improving Domain Adaptation for Machine Translation withTranslation Pieces
| Title | Improving Domain Adaptation for Machine Translation withTranslation Pieces |
| Authors | Catarina Silva |
| Abstract | |
| Tasks | Domain Adaptation, Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6735/ |
| https://www.aclweb.org/anthology/W19-6735 | |
| PWC | https://paperswithcode.com/paper/improving-domain-adaptation-for-machine |
| Repo | |
| Framework | |
Raising the TM Threshold in Neural MT Post-Editing: a Case Study onTwo Datasets
| Title | Raising the TM Threshold in Neural MT Post-Editing: a Case Study onTwo Datasets |
| Authors | Anna Zaretskaya |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6736/ |
| https://www.aclweb.org/anthology/W19-6736 | |
| PWC | https://paperswithcode.com/paper/raising-the-tm-threshold-in-neural-mt-post |
| Repo | |
| Framework | |
A Continuous Improvement Framework of Machine Translation for Shipibo-Konibo
| Title | A Continuous Improvement Framework of Machine Translation for Shipibo-Konibo |
| Authors | H{'e}ctor Erasmo G{'o}mez Montoya, Kervy Dante Rivas Rojas, Arturo Oncevay |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6804/ |
| https://www.aclweb.org/anthology/W19-6804 | |
| PWC | https://paperswithcode.com/paper/a-continuous-improvement-framework-of-machine |
| Repo | |
| Framework | |
Developing a Neural Machine Translation system for Irish
| Title | Developing a Neural Machine Translation system for Irish |
| Authors | Arne Defauw, Sara Szoc, Tom Vanallemeersch, Anna Bardadym, Joris Brabers, Frederic Everaert, Kim Scholte, Koen Van Winckel, Joachim Van den Bogaert |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6806/ |
| https://www.aclweb.org/anthology/W19-6806 | |
| PWC | https://paperswithcode.com/paper/developing-a-neural-machine-translation-1 |
| Repo | |
| Framework | |
Universal dependencies for Scottish Gaelic: syntax
| Title | Universal dependencies for Scottish Gaelic: syntax |
| Authors | Colin Batchelor |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6902/ |
| https://www.aclweb.org/anthology/W19-6902 | |
| PWC | https://paperswithcode.com/paper/universal-dependencies-for-scottish-gaelic |
| Repo | |
| Framework | |
Free indirect discourse: an insurmountable challenge for literary MT systems?
| Title | Free indirect discourse: an insurmountable challenge for literary MT systems? |
| Authors | Kristiina Taivalkoski-Shilov |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7305/ |
| https://www.aclweb.org/anthology/W19-7305 | |
| PWC | https://paperswithcode.com/paper/free-indirect-discourse-an-insurmountable |
| Repo | |
| Framework | |
Do You Know That Florence Is Packed with Visitors? Evaluating State-of-the-art Models of Speaker Commitment
| Title | Do You Know That Florence Is Packed with Visitors? Evaluating State-of-the-art Models of Speaker Commitment |
| Authors | Nanjiang Jiang, Marie-Catherine de Marneffe |
| Abstract | When a speaker, Mary, asks {}Do you know that Florence is packed with visitors?{''}, we take her to believe that Florence is packed with visitors, but not if she asks {}Do you think that Florence is packed with visitors?{''}. Inferring speaker commitment (aka event factuality) is crucial for information extraction and question answering. Here, we explore the hypothesis that linguistic deficits drive the error patterns of existing speaker commitment models by analyzing the linguistic correlates of model error on a challenging naturalistic dataset. We evaluate two state-of-the-art speaker commitment models on the CommitmentBank, an English dataset of naturally occurring discourses. The CommitmentBank is annotated with speaker commitment towards the content of the complement ({}Florence is packed with visitors{''} in our example) of clause-embedding verbs ({}know{''}, {``}think{''}) under four entailment-canceling environments (negation, modal, question, conditional). A breakdown of items by linguistic features reveals asymmetrical error patterns: while the models achieve good performance on some classes (e.g., negation), they fail to generalize to the diverse linguistic constructions (e.g., conditionals) in natural language, highlighting directions for improvement. | |
| Tasks | Question Answering |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1412/ |
| https://www.aclweb.org/anthology/P19-1412 | |
| PWC | https://paperswithcode.com/paper/do-you-know-that-florence-is-packed-with |
| Repo | |
| Framework | |
IIT-KGP at MEDIQA 2019: Recognizing Question Entailment using Sci-BERT stacked with a Gradient Boosting Classifier
| Title | IIT-KGP at MEDIQA 2019: Recognizing Question Entailment using Sci-BERT stacked with a Gradient Boosting Classifier |
| Authors | Prakhar Sharma, Sumegh Roychowdhury |
| Abstract | Official System Description paper of Team IIT-KGP ranked 1st in the Development phase and 3rd in Testing Phase in MEDIQA 2019 - Recognizing Question Entailment (RQE) Shared Task of BioNLP workshop - ACL 2019. The number of people turning to the Internet to search for a diverse range of health-related subjects continues to grow and with this multitude of information available, duplicate questions are becoming more frequent and finding the most appropriate answers becomes problematic. This issue is important for question answering platforms as it complicates the retrieval of all information relevant to the same topic, particularly when questions similar in essence are expressed differently, and answering a given medical question by retrieving similar questions that are already answered by human experts seems to be a promising solution. In this paper, we present our novel approach to detect question entailment by determining the type of question asked rather than focusing on the type of the ailment given. This unique methodology makes the approach robust towards examples which have different ailment names but are synonyms of each other. Also, it enables us to check entailment at a much more fine-grained level. QSpider is a staged system consisting of state-of-the-art model Sci-BERT used as a multi-class classifier aimed at capturing both question types and semantic relations stacked with a Gradient Boosting Classifier which checks for entailment. QSpider achieves an accuracy score of 68.4{%} on the Test set which outperforms the baseline model (54.1{%}) by an accuracy score of 14.3{%}. |
| Tasks | Question Answering |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5050/ |
| https://www.aclweb.org/anthology/W19-5050 | |
| PWC | https://paperswithcode.com/paper/iit-kgp-at-mediqa-2019-recognizing-question |
| Repo | |
| Framework | |
Aligning the IndoWordNet with the Princeton WordNet
| Title | Aligning the IndoWordNet with the Princeton WordNet |
| Authors | N Nair, u Ch, ran, Rajendran Sankara Velayuthan, Khuyagbaatar Batsuren |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-7402/ |
| https://www.aclweb.org/anthology/W19-7402 | |
| PWC | https://paperswithcode.com/paper/aligning-the-indowordnet-with-the-princeton |
| Repo | |
| Framework | |
SumSAT: Hybrid Arabic Text Summarization based on symbolic and numerical Approaches
| Title | SumSAT: Hybrid Arabic Text Summarization based on symbolic and numerical Approaches |
| Authors | Mohamed Amine Cheragui, Said Moulay Lakhdar |
| Abstract | |
| Tasks | Text Summarization |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-7417/ |
| https://www.aclweb.org/anthology/W19-7417 | |
| PWC | https://paperswithcode.com/paper/sumsat-hybrid-arabic-text-summarization-based |
| Repo | |
| Framework | |
A Deep Step Pattern Representation for Multimodal Retinal Image Registration
| Title | A Deep Step Pattern Representation for Multimodal Retinal Image Registration |
| Authors | Jimmy Addison Lee, Peng Liu, Jun Cheng, Huazhu Fu |
| Abstract | This paper presents a novel feature-based method that is built upon a convolutional neural network (CNN) to learn the deep representation for multimodal retinal image registration. We coined the algorithm deep step patterns, in short DeepSPa. Most existing deep learning based methods require a set of manually labeled training data with known corresponding spatial transformations, which limits the size of training datasets. By contrast, our method is fully automatic and scale well to different image modalities with no human intervention. We generate feature classes from simple step patterns within patches of connecting edges formed by vascular junctions in multiple retinal imaging modalities. We leverage CNN to learn and optimize the input patches to be used for image registration. Spatial transformations are estimated based on the output possibility of the fully connected layer of CNN for a pair of images. One of the key advantages of the proposed algorithm is its robustness to non-linear intensity changes, which widely exist on retinal images due to the difference of acquisition modalities. We validate our algorithm on extensive challenging datasets comprising poor quality multimodal retinal images which are adversely affected by pathologies (diseases), speckle noise and low resolutions. The experimental results demonstrate the robustness and accuracy over state-of-the-art multimodal image registration algorithms. |
| Tasks | Image Registration |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Lee_A_Deep_Step_Pattern_Representation_for_Multimodal_Retinal_Image_Registration_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Lee_A_Deep_Step_Pattern_Representation_for_Multimodal_Retinal_Image_Registration_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-deep-step-pattern-representation-for |
| Repo | |
| Framework | |
Deep Graphical Feature Learning for the Feature Matching Problem
| Title | Deep Graphical Feature Learning for the Feature Matching Problem |
| Authors | Zhen Zhang, Wee Sun Lee |
| Abstract | The feature matching problem is a fundamental problem in various areas of computer vision including image registration, tracking and motion analysis. Rich local representation is a key part of efficient feature matching methods. However, when the local features are limited to the coordinate of key points, it becomes challenging to extract rich local representations. Traditional approaches use pairwise or higher order handcrafted geometric features to get robust matching; this requires solving NP-hard assignment problems. In this paper, we address this problem by proposing a graph neural network model to transform coordinates of feature points into local features. With our local features, the traditional NP-hard assignment problems are replaced with a simple assignment problem which can be solved efficiently. Promising results on both synthetic and real datasets demonstrate the effectiveness of the proposed method. |
| Tasks | Image Registration |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zhang_Deep_Graphical_Feature_Learning_for_the_Feature_Matching_Problem_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_Deep_Graphical_Feature_Learning_for_the_Feature_Matching_Problem_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-graphical-feature-learning-for-the |
| Repo | |
| Framework | |
Open-Domain Why-Question Answering with Adversarial Learning to Encode Answer Texts
| Title | Open-Domain Why-Question Answering with Adversarial Learning to Encode Answer Texts |
| Authors | Jong-Hoon Oh, Kazuma Kadowaki, Julien Kloetzer, Ryu Iida, Kentaro Torisawa |
| Abstract | In this paper, we propose a method for why-question answering (why-QA) that uses an adversarial learning framework. Existing why-QA methods retrieve {}answer passages{''} that usually consist of several sentences. These multi-sentence passages contain not only the reason sought by a why-question and its connection to the why-question, but also redundant and/or unrelated parts. We use our proposed {}Adversarial networks for Generating compact-answer Representation{''} (AGR) to generate from a passage a vector representation of the non-redundant reason sought by a why-question and exploit the representation for judging whether the passage actually answers the why-question. Through a series of experiments using Japanese why-QA datasets, we show that these representations improve the performance of our why-QA neural model as well as that of a BERT-based why-QA model. We show that they also improve a state-of-the-art distantly supervised open-domain QA (DS-QA) method on publicly available English datasets, even though the target task is not a why-QA. |
| Tasks | Question Answering |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1414/ |
| https://www.aclweb.org/anthology/P19-1414 | |
| PWC | https://paperswithcode.com/paper/open-domain-why-question-answering-with |
| Repo | |
| Framework | |
