Paper Group NANR 105
Tone Analysis in Spanish Financial Reporting Narratives. NICT’s participation to WAT 2019: Multilingualism and Multi-step Fine-Tuning for Low Resource NMT. Proceedings of Machine Translation Summit XVII Volume 1: Research Track. Agreement is overrated: A plea for correlation to assess human evaluation reliability. An Exploration of Placeholding in …
Tone Analysis in Spanish Financial Reporting Narratives
| Title | Tone Analysis in Spanish Financial Reporting Narratives |
| Authors | Moreno-S, Antonio oval, Pablo Alfonso Haya Ana Gisbert, Marta Guerrero, Helena Montoro |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6406/ |
| https://www.aclweb.org/anthology/W19-6406 | |
| PWC | https://paperswithcode.com/paper/tone-analysis-in-spanish-financial-reporting |
| Repo | |
| Framework | |
NICT’s participation to WAT 2019: Multilingualism and Multi-step Fine-Tuning for Low Resource NMT
| Title | NICT’s participation to WAT 2019: Multilingualism and Multi-step Fine-Tuning for Low Resource NMT |
| Authors | Raj Dabre, Eiichiro Sumita |
| Abstract | In this paper we describe our submissions to WAT 2019 for the following tasks: English{–}Tamil translation and Russian{–}Japanese translation. Our team,{``}NICT-5{''}, focused on multilingual domain adaptation and back-translation for Russian{–}Japanese translation and on simple fine-tuning for English{–}Tamil translation . We noted that multi-stage fine tuning is essential in leveraging the power of multilingualism for an extremely low-resource language like Russian{–}Japanese. Furthermore, we can improve the performance of such a low-resource language pair by exploiting a small but in-domain monolingual corpus via back-translation. We managed to obtain second rank in both tasks for all translation directions. | |
| Tasks | Domain Adaptation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5207/ |
| https://www.aclweb.org/anthology/D19-5207 | |
| PWC | https://paperswithcode.com/paper/nicts-participation-to-wat-2019 |
| Repo | |
| Framework | |
Proceedings of Machine Translation Summit XVII Volume 1: Research Track
| Title | Proceedings of Machine Translation Summit XVII Volume 1: Research Track |
| Authors | |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6600/ |
| https://www.aclweb.org/anthology/W19-6600 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-machine-translation-summit |
| Repo | |
| Framework | |
Agreement is overrated: A plea for correlation to assess human evaluation reliability
| Title | Agreement is overrated: A plea for correlation to assess human evaluation reliability |
| Authors | Jacopo Amidei, Paul Piwek, Alistair Willis |
| Abstract | Inter-Annotator Agreement (IAA) is used as a means of assessing the quality of NLG evaluation data, in particular, its reliability. According to existing scales of IAA interpretation {–} see, for example, Lommel et al. (2014), Liu et al. (2016), Sedoc et al. (2018) and Amidei et al. (2018a) {–} most data collected for NLG evaluation fail the reliability test. We confirmed this trend by analysing papers published over the last 10 years in NLG-specific conferences (in total 135 papers that included some sort of human evaluation study). Following Sampson and Babarczy (2008), Lommel et al. (2014), Joshi et al. (2016) and Amidei et al. (2018b), such phenomena can be explained in terms of irreducible human language variability. Using three case studies, we show the limits of considering IAA as the only criterion for checking evaluation reliability. Given human language variability, we propose that for human evaluation of NLG, correlation coefficients and agreement coefficients should be used together to obtain a better assessment of the evaluation data reliability. This is illustrated using the three case studies. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8642/ |
| https://www.aclweb.org/anthology/W19-8642 | |
| PWC | https://paperswithcode.com/paper/agreement-is-overrated-a-plea-for-correlation |
| Repo | |
| Framework | |
An Exploration of Placeholding in Neural Machine Translation
| Title | An Exploration of Placeholding in Neural Machine Translation |
| Authors | Matt Post, Shuoyang Ding, Marianna Martindale, Winston Wu |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6618/ |
| https://www.aclweb.org/anthology/W19-6618 | |
| PWC | https://paperswithcode.com/paper/an-exploration-of-placeholding-in-neural |
| Repo | |
| Framework | |
Overview of the Fourth Social Media Mining for Health (SMM4H) Shared Tasks at ACL 2019
| Title | Overview of the Fourth Social Media Mining for Health (SMM4H) Shared Tasks at ACL 2019 |
| Authors | Davy Weissenbacher, Abeed Sarker, Arjun Magge, Ashlynn Daughton, Karen O{'}Connor, Michael J. Paul, Gonzalez-Hern, Graciela ez |
| Abstract | The number of users of social media continues to grow, with nearly half of adults worldwide and two-thirds of all American adults using social networking. Advances in automated data processing, machine learning and NLP present the possibility of utilizing this massive data source for biomedical and public health applications, if researchers address the methodological challenges unique to this media. We present the Social Media Mining for Health Shared Tasks collocated with the ACL at Florence in 2019, which address these challenges for health monitoring and surveillance, utilizing state of the art techniques for processing noisy, real-world, and substantially creative language expressions from social media users. For the fourth execution of this challenge, we proposed four different tasks. Task 1 asked participants to distinguish tweets reporting an adverse drug reaction (ADR) from those that do not. Task 2, a follow-up to Task 1, asked participants to identify the span of text in tweets reporting ADRs. Task 3 is an end-to-end task where the goal was to first detect tweets mentioning an ADR and then map the extracted colloquial mentions of ADRs in the tweets to their corresponding standard concept IDs in the MedDRA vocabulary. Finally, Task 4 asked participants to classify whether a tweet contains a personal mention of one{'}s health, a more general discussion of the health issue, or is an unrelated mention. A total of 34 teams from around the world registered and 19 teams from 12 countries submitted a system run. We summarize here the corpora for this challenge which are freely available at https://competitions.codalab.org/competitions/22521, and present an overview of the methods and the results of the competing systems. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3203/ |
| https://www.aclweb.org/anthology/W19-3203 | |
| PWC | https://paperswithcode.com/paper/overview-of-the-fourth-social-media-mining |
| Repo | |
| Framework | |
Autosegmental Input Strictly Local Functions
| Title | Autosegmental Input Strictly Local Functions |
| Authors | Ch, Jane lee, Adam Jardine |
| Abstract | Autosegmental representations (ARs; Goldsmith, 1976) are claimed to enable local analyses of otherwise non-local phenomena Odden (1994). Focusing on the domain of tone, we investigate this ability of ARs using a computationally well-defined notion of locality extended from Chandlee (2014). The result is a more nuanced understanding of the way in which ARs interact with phonological locality. |
| Tasks | |
| Published | 2019-03-01 |
| URL | https://www.aclweb.org/anthology/Q19-1010/ |
| https://www.aclweb.org/anthology/Q19-1010 | |
| PWC | https://paperswithcode.com/paper/autosegmental-input-strictly-local-functions |
| Repo | |
| Framework | |
CoFiF: A Corpus of Financial Reports in French Language
| Title | CoFiF: A Corpus of Financial Reports in French Language |
| Authors | Tobias Daudert, Sina Ahmadi |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5504/ |
| https://www.aclweb.org/anthology/W19-5504 | |
| PWC | https://paperswithcode.com/paper/cofif-a-corpus-of-financial-reports-in-french |
| Repo | |
| Framework | |
Rationale Classification for Educational Trading Platforms
| Title | Rationale Classification for Educational Trading Platforms |
| Authors | Annie Ying, Pablo Duboue |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5503/ |
| https://www.aclweb.org/anthology/W19-5503 | |
| PWC | https://paperswithcode.com/paper/rationale-classification-for-educational |
| Repo | |
| Framework | |
Learning How to Active Learn by Dreaming
| Title | Learning How to Active Learn by Dreaming |
| Authors | Thuy-Trang Vu, Ming Liu, Dinh Phung, Gholamreza Haffari |
| Abstract | Heuristic-based active learning (AL) methods are limited when the data distribution of the underlying learning problems vary. Recent data-driven AL policy learning methods are also restricted to learn from closely related domains. We introduce a new sample-efficient method that learns the AL policy directly on the target domain of interest by using wake and dream cycles. Our approach interleaves between querying the annotation of the selected datapoints to update the underlying student learner and improving AL policy using simulation where the current student learner acts as an imperfect annotator. We evaluate our method on cross-domain and cross-lingual text classification and named entity recognition tasks. Experimental results show that our dream-based AL policy training strategy is more effective than applying the pretrained policy without further fine-tuning and better than the existing strong baseline methods that use heuristics or reinforcement learning. |
| Tasks | Active Learning, Named Entity Recognition, Text Classification |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1401/ |
| https://www.aclweb.org/anthology/P19-1401 | |
| PWC | https://paperswithcode.com/paper/learning-how-to-active-learn-by-dreaming |
| Repo | |
| Framework | |
Proceedings of Machine Translation Summit XVII Volume 2: Translator, Project and User Tracks
| Title | Proceedings of Machine Translation Summit XVII Volume 2: Translator, Project and User Tracks |
| Authors | |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6700/ |
| https://www.aclweb.org/anthology/W19-6700 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-machine-translation-summit-1 |
| Repo | |
| Framework | |
Pivot Machine Translation in INTERACT Project
| Title | Pivot Machine Translation in INTERACT Project |
| Authors | Chao-Hong Liu, Andy Way, Catarina Silva, Andr{'e} Martins |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6722/ |
| https://www.aclweb.org/anthology/W19-6722 | |
| PWC | https://paperswithcode.com/paper/pivot-machine-translation-in-interact-project |
| Repo | |
| Framework | |
Surveying the potential of using speech technologies for post-editing purposes in the context of international organizations: What do professional translators think?
| Title | Surveying the potential of using speech technologies for post-editing purposes in the context of international organizations: What do professional translators think? |
| Authors | Jeevanthi Liyanapathirana, Pierrette Bouillon, Bartolom{'e} Mesa-Lao |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6728/ |
| https://www.aclweb.org/anthology/W19-6728 | |
| PWC | https://paperswithcode.com/paper/surveying-the-potential-of-using-speech |
| Repo | |
| Framework | |
Dependently-Typed Montague Semantics in the Proof Assistant Agda-flat
| Title | Dependently-Typed Montague Semantics in the Proof Assistant Agda-flat |
| Authors | Colin Zwanziger |
| Abstract | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/W19-5704/ |
| https://www.aclweb.org/anthology/W19-5704 | |
| PWC | https://paperswithcode.com/paper/dependently-typed-montague-semantics-in-the |
| Repo | |
| Framework | |
CoSACT: A Collaborative Tool for Fine-Grained Sentiment Annotation and Consolidation of Text
| Title | CoSACT: A Collaborative Tool for Fine-Grained Sentiment Annotation and Consolidation of Text |
| Authors | Tobias Daudert, Manel Zarrouk, Brian Davis |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5506/ |
| https://www.aclweb.org/anthology/W19-5506 | |
| PWC | https://paperswithcode.com/paper/cosact-a-collaborative-tool-for-fine-grained |
| Repo | |
| Framework | |
