Paper Group NANR 47
The FinTOC-2019 Shared Task: Financial Document Structure Extraction. Proceedings of the Second Financial Narrative Processing Workshop (FNP 2019). Surface Realization Shared Task 2019 (MSR19): The Team 6 Approach. Can a simple approach identify complex nurse care activity?. Learning a Meta-Solver for Syntax-Guided Program Synthesis. Proceedings of …
The FinTOC-2019 Shared Task: Financial Document Structure Extraction
| Title | The FinTOC-2019 Shared Task: Financial Document Structure Extraction |
| Authors | Remi Juge, Imane Bentabet, Sira Ferradans |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6407/ |
| https://www.aclweb.org/anthology/W19-6407 | |
| PWC | https://paperswithcode.com/paper/the-fintoc-2019-shared-task-financial |
| Repo | |
| Framework | |
Proceedings of the Second Financial Narrative Processing Workshop (FNP 2019)
| Title | Proceedings of the Second Financial Narrative Processing Workshop (FNP 2019) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6400/ |
| https://www.aclweb.org/anthology/W19-6400 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-second-financial-narrative |
| Repo | |
| Framework | |
Surface Realization Shared Task 2019 (MSR19): The Team 6 Approach
| Title | Surface Realization Shared Task 2019 (MSR19): The Team 6 Approach |
| Authors | Thiago Castro Ferreira, Emiel Krahmer |
| Abstract | This study describes the approach developed by the Tilburg University team to the shallow track of the Multilingual Surface Realization Shared Task 2019 (SR{'}19) (Mille et al., 2019). Based on Ferreira et al. (2017) and on our 2018 submission Ferreira et al. (2018), the approach generates texts by first preprocessing an input dependency tree into an ordered linearized string, which is then realized using a rule-based and a statistical machine translation (SMT) model. This year our submission is able to realize texts in the 11 languages proposed for the task, different from our last year submission, which covered only 6 Indo-European languages. The model is publicly available. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6307/ |
| https://www.aclweb.org/anthology/D19-6307 | |
| PWC | https://paperswithcode.com/paper/surface-realization-shared-task-2019-msr19 |
| Repo | |
| Framework | |
Can a simple approach identify complex nurse care activity?
| Title | Can a simple approach identify complex nurse care activity? |
| Authors | Md. Eusha Kadir, Pritom Saha Akash, Sadia Sharmin, Amin Ahsan Ali, Mohammad Shoyaib |
| Abstract | For the last two decades, more and more complex methods have been developed to identify human activities using various types of sensors, e.g., data from motion capture, accelerometer, and gyroscopes sensors. To date, most of the researches mainly focus on identifying simple human activities, e.g., walking, eating, and running. However, many of our daily life activities are usually more complex than those. To instigate research in complex activity recognition, the “Nurse Care Activity Recognition Challenge” [1] is initiated where six nurse activities are to be identified based on location, air pressure, motion capture, and accelerometer data. Our team, “IITDU”, investigates the use of simple methods for this purpose. We first extract features from the sensor data and use one of the simplest classifiers, namely K-Nearest Neighbors (KNN). Experiment using an ensemble of KNN classifiers demonstrates that it is possible to achieve approximately 87% accuracy on 10-fold cross-validation and 66% accuracy on leave-one-subject-out cross-validation. |
| Tasks | Activity Recognition, Motion Capture, Multimodal Activity Recognition |
| Published | 2019-09-09 |
| URL | https://doi.org/10.1145/3341162.3344859 |
| http://delivery.acm.org/10.1145/3350000/3344859/p736-kadir.pdf | |
| PWC | https://paperswithcode.com/paper/can-a-simple-approach-identify-complex-nurse |
| Repo | |
| Framework | |
Learning a Meta-Solver for Syntax-Guided Program Synthesis
| Title | Learning a Meta-Solver for Syntax-Guided Program Synthesis |
| Authors | Xujie Si, Yuan Yang, Hanjun Dai, Mayur Naik, Le Song |
| Abstract | We study a general formulation of program synthesis called syntax-guided synthesis(SyGuS) that concerns synthesizing a program that follows a given grammar and satisfies a given logical specification. Both the logical specification and the grammar have complex structures and can vary from task to task, posing significant challenges for learning across different tasks. Furthermore, training data is often unavailable for domain specific synthesis tasks. To address these challenges, we propose a meta-learning framework that learns a transferable policy from only weak supervision. Our framework consists of three components: 1) an encoder, which embeds both the logical specification and grammar at the same time using a graph neural network; 2) a grammar adaptive policy network which enables learning a transferable policy; and 3) a reinforcement learning algorithm that jointly trains the specification and grammar embedding and adaptive policy. We evaluate the framework on 214 cryptographic circuit synthesis tasks. It solves 141 of them in the out-of-box solver setting, significantly outperforming a similar search-based approach but without learning, which solves only 31. The result is comparable to two state-of-the-art classical synthesis engines, which solve 129 and 153 respectively. In the meta-solver setting, the framework can efficiently adapt to unseen tasks and achieves speedup ranging from 2x up to 100x. |
| Tasks | Meta-Learning, Program Synthesis |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Syl8Sn0cK7 |
| https://openreview.net/pdf?id=Syl8Sn0cK7 | |
| PWC | https://paperswithcode.com/paper/learning-a-meta-solver-for-syntax-guided |
| Repo | |
| Framework | |
Proceedings of the 2nd Workshop on Technologies for MT of Low Resource Languages
| Title | Proceedings of the 2nd Workshop on Technologies for MT of Low Resource Languages |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6800/ |
| https://www.aclweb.org/anthology/W19-6800 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2nd-workshop-on-4 |
| Repo | |
| Framework | |
Edit distances do not describe editing, but they can be useful for translation process research
| Title | Edit distances do not describe editing, but they can be useful for translation process research |
| Authors | F{'e}lix do Carmo |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7001/ |
| https://www.aclweb.org/anthology/W19-7001 | |
| PWC | https://paperswithcode.com/paper/edit-distances-do-not-describe-editing-but |
| Repo | |
| Framework | |
A Green Approach for an Irish App (Refactor, reuse and keeping it real)
| Title | A Green Approach for an Irish App (Refactor, reuse and keeping it real) |
| Authors | Monica Ward, Maxim Mozgovoy, Marina Purgina |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6911/ |
| https://www.aclweb.org/anthology/W19-6911 | |
| PWC | https://paperswithcode.com/paper/a-green-approach-for-an-irish-app-refactor |
| Repo | |
| Framework | |
Annotating formulaic sequences in spoken Slovenian: structure, function and relevance
| Title | Annotating formulaic sequences in spoken Slovenian: structure, function and relevance |
| Authors | Kaja Dobrovoljc |
| Abstract | This paper presents the identification of formulaic sequences in the reference corpus of spoken Slovenian and their annotation in terms of syntactic structure, pragmatic function and lexicographic relevance. The annotation campaign, specific in terms of setting, subjectivity and the multifunctionality of items under investigation, resulted in a preliminary lexicon of formulaic sequences in spoken Slovenian with immediate potential for future explorations in formulaic language research. This is especially relevant for the notable number of identified multi-word expressions with discourse-structuring and stance-marking functions, which have often been overlooked by traditional phraseology research. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4013/ |
| https://www.aclweb.org/anthology/W19-4013 | |
| PWC | https://paperswithcode.com/paper/annotating-formulaic-sequences-in-spoken |
| Repo | |
| Framework | |
C-Command Dependencies as TSL String Constraints
| Title | C-Command Dependencies as TSL String Constraints |
| Authors | Thomas Graf, Nazila Shafiei |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0121/ |
| https://www.aclweb.org/anthology/W19-0121 | |
| PWC | https://paperswithcode.com/paper/c-command-dependencies-as-tsl-string |
| Repo | |
| Framework | |
Analyzing Incorporation of Emotion in Emoji Prediction
| Title | Analyzing Incorporation of Emotion in Emoji Prediction |
| Authors | Shirley Anugrah Hayati, Aldrian Obaja Muis |
| Abstract | In this work, we investigate the impact of incorporating emotion classes on the task of predicting emojis from Twitter texts. More specifically, we first show that there is a correlation between the emotion expressed in the text and the emoji choice of Twitter users. Based on this insight we propose a few simple methods to incorporate emotion information in traditional classifiers. Through automatic metrics, human evaluation, and error analysis, we show that the improvement obtained by incorporating emotion is significant and correlate better with human preferences compared to the baseline models. Through the human ratings that we obtained, we also argue for preference metric to better evaluate the usefulness of an emoji prediction system. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1311/ |
| https://www.aclweb.org/anthology/W19-1311 | |
| PWC | https://paperswithcode.com/paper/analyzing-incorporation-of-emotion-in-emoji |
| Repo | |
| Framework | |
Execution-Guided Neural Program Synthesis
| Title | Execution-Guided Neural Program Synthesis |
| Authors | Xinyun Chen, Chang Liu, Dawn Song |
| Abstract | Neural program synthesis from input-output examples has attracted an increasing interest from both the machine learning and the programming language community. Most existing neural program synthesis approaches employ an encoder-decoder architecture, which uses an encoder to compute the embedding of the given input-output examples, as well as a decoder to generate the program from the embedding following a given syntax. Although such approaches achieve a reasonable performance on simple tasks such as FlashFill, on more complex tasks such as Karel, the state-of-the-art approach can only achieve an accuracy of around 77%. We observe that the main drawback of existing approaches is that the semantic information is greatly under-utilized. In this work, we propose two simple yet principled techniques to better leverage the semantic information, which are execution-guided synthesis and synthesizer ensemble. These techniques are general enough to be combined with any existing encoder-decoder-style neural program synthesizer. Applying our techniques to the Karel dataset, we can boost the accuracy from around 77% to more than 90%. |
| Tasks | Program Synthesis |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1gfOiAqYm |
| https://openreview.net/pdf?id=H1gfOiAqYm | |
| PWC | https://paperswithcode.com/paper/execution-guided-neural-program-synthesis |
| Repo | |
| Framework | |
On the role of discourse relations in persuasive texts
| Title | On the role of discourse relations in persuasive texts |
| Authors | Ines Rehbein |
| Abstract | This paper investigates the use of explicitly signalled discourse relations in persuasive texts. We present a corpus study where we control for speaker and topic and show that the distribution of different discourse connectives varies considerably across different discourse settings. While this variation can be explained by genre differences, we also observe variation regarding the distribution of discourse relations across different settings. This variation, however, cannot be easily explained by genre differences. We argue that the differences regarding the use of discourse relations reflects different strategies of persuasion and that these might be due to audience design. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4017/ |
| https://www.aclweb.org/anthology/W19-4017 | |
| PWC | https://paperswithcode.com/paper/on-the-role-of-discourse-relations-in |
| Repo | |
| Framework | |
Automatic Data-Driven Approaches for Evaluating the Phonemic Verbal Fluency Task with Healthy Adults
| Title | Automatic Data-Driven Approaches for Evaluating the Phonemic Verbal Fluency Task with Healthy Adults |
| Authors | Hali Lindsay, Nicklas Linz, Johannes Troeger, Alex, Jan ersson |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-7403/ |
| https://www.aclweb.org/anthology/W19-7403 | |
| PWC | https://paperswithcode.com/paper/automatic-data-driven-approaches-for |
| Repo | |
| Framework | |
Automatic Diacritization as Prerequisite Towards the Automatic Generation of Arabic Lexical Recognition Tests
| Title | Automatic Diacritization as Prerequisite Towards the Automatic Generation of Arabic Lexical Recognition Tests |
| Authors | Osama Hamed |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-7414/ |
| https://www.aclweb.org/anthology/W19-7414 | |
| PWC | https://paperswithcode.com/paper/automatic-diacritization-as-prerequisite |
| Repo | |
| Framework | |
