Paper Group NANR 109
Amazon at MRP 2019: Parsing Meaning Representations with Lexical and Phrasal Anchoring. How do we feel when a robot dies? Emotions expressed on Twitter before and after hitchBOT’s destruction. Automata Guided Skill Composition. A Character Level Convolutional BiLSTM for Arabic Dialect Identification. Is Word Segmentation Child’s Play in All Languag …
Amazon at MRP 2019: Parsing Meaning Representations with Lexical and Phrasal Anchoring
| Title | Amazon at MRP 2019: Parsing Meaning Representations with Lexical and Phrasal Anchoring |
| Authors | Jie Cao, Yi Zhang, Adel Youssef, Vivek Srikumar |
| Abstract | This paper describes the system submission of our team Amazon to the shared task on Cross Framework Meaning Representation Parsing (MRP) at the 2019 Conference for Computational Language Learning (CoNLL). Via extensive analysis of implicit alignments in AMR, we recategorize five meaning representations (MRs) into two classes: Lexical- Anchoring and Phrasal-Anchoring. Then we propose a unified graph-based parsing framework for the lexical-anchoring MRs, and a phrase-structure parsing for one of the phrasal- anchoring MRs, UCCA. Our system submission ranked 1st in the AMR subtask, and later improvements show promising results on other frameworks as well. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-2013/ |
| https://www.aclweb.org/anthology/K19-2013 | |
| PWC | https://paperswithcode.com/paper/amazon-at-mrp-2019-parsing-meaning |
| Repo | |
| Framework | |
How do we feel when a robot dies? Emotions expressed on Twitter before and after hitchBOT’s destruction
| Title | How do we feel when a robot dies? Emotions expressed on Twitter before and after hitchBOT’s destruction |
| Authors | Kathleen C. Fraser, Frauke Zeller, David Harris Smith, Saif Mohammad, Frank Rudzicz |
| Abstract | In 2014, a chatty but immobile robot called hitchBOT set out to hitchhike across Canada. It similarly made its way across Germany and the Netherlands, and had begun a trip across the USA when it was destroyed by vandals. In this work, we analyze the emotions and sentiments associated with words in tweets posted before and after hitchBOT{'}s destruction to answer two questions: Were there any differences in the emotions expressed across the different countries visited by hitchBOT? And how did the public react to the demise of hitchBOT? Our analyses indicate that while there were few cross-cultural differences in sentiment towards hitchBOT, there was a significant negative emotional reaction to its destruction, suggesting that people had formed an emotional connection with hitchBOT and perceived its destruction as morally wrong. We discuss potential implications of anthropomorphism and emotional attachment to robots from the perspective of robot ethics. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1308/ |
| https://www.aclweb.org/anthology/W19-1308 | |
| PWC | https://paperswithcode.com/paper/how-do-we-feel-when-a-robot-dies-emotions |
| Repo | |
| Framework | |
Automata Guided Skill Composition
| Title | Automata Guided Skill Composition |
| Authors | Xiao Li, Yao Ma, Calin Belta |
| Abstract | Skills learned through (deep) reinforcement learning often generalizes poorly across tasks and re-training is necessary when presented with a new task. We present a framework that combines techniques in formal methods with reinforcement learning (RL) that allows for the convenient specification of complex temporal dependent tasks with logical expressions and construction of new skills from existing ones with no additional exploration. We provide theoretical results for our composition technique and evaluate on a simple grid world simulation as well as a robotic manipulation task. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HkfwpiA9KX |
| https://openreview.net/pdf?id=HkfwpiA9KX | |
| PWC | https://paperswithcode.com/paper/automata-guided-skill-composition |
| Repo | |
| Framework | |
A Character Level Convolutional BiLSTM for Arabic Dialect Identification
| Title | A Character Level Convolutional BiLSTM for Arabic Dialect Identification |
| Authors | Mohamed Elaraby, Ahmed Zahran |
| Abstract | In this paper, we describe CU-RAISA teamcontribution to the 2019Madar shared task2, which focused on Twitter User fine-grained dialect identification.Among par-ticipating teams, our system ranked the4th(with 61.54{%}) F1-Macro measure.Our sys-tem is trained using a character level convo-lutional bidirectional long-short-term memorynetwork trained on 2k users{'} data. We showthat training on concatenated user tweets asinput is further superior to training on usertweets separately and assign user{'}s label on themode of user{'}s tweets{'} predictions. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4636/ |
| https://www.aclweb.org/anthology/W19-4636 | |
| PWC | https://paperswithcode.com/paper/a-character-level-convolutional-bilstm-for |
| Repo | |
| Framework | |
Is Word Segmentation Child’s Play in All Languages?
| Title | Is Word Segmentation Child’s Play in All Languages? |
| Authors | Georgia R. Loukatou, Steven Moran, Damian Blasi, Sabine Stoll, Alej Cristia, rina |
| Abstract | When learning language, infants need to break down the flow of input speech into minimal word-like units, a process best described as unsupervised bottom-up segmentation. Proposed strategies include several segmentation algorithms, but only cross-linguistically robust algorithms could be plausible candidates for human word learning, since infants have no initial knowledge of the ambient language. We report on the stability in performance of 11 conceptually diverse algorithms on a selection of 8 typologically distinct languages. The results consist evidence that some segmentation algorithms are cross-linguistically valid, thus could be considered as potential strategies employed by all infants. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1383/ |
| https://www.aclweb.org/anthology/P19-1383 | |
| PWC | https://paperswithcode.com/paper/is-word-segmentation-childs-play-in-all |
| Repo | |
| Framework | |
Better OOV Translation with Bilingual Terminology Mining
| Title | Better OOV Translation with Bilingual Terminology Mining |
| Authors | Matthias Huck, Viktor Hangya, Alex Fraser, er |
| Abstract | Unseen words, also called out-of-vocabulary words (OOVs), are difficult for machine translation. In neural machine translation, byte-pair encoding can be used to represent OOVs, but they are still often incorrectly translated. We improve the translation of OOVs in NMT using easy-to-obtain monolingual data. We look for OOVs in the text to be translated and translate them using simple-to-construct bilingual word embeddings (BWEs). In our MT experiments we take the 5-best candidates, which is motivated by intrinsic mining experiments. Using all five of the proposed target language words as queries we mine target-language sentences. We then back-translate, forcing the back-translation of each of the five proposed target-language OOV-translation-candidates to be the original source-language OOV. We show that by using this synthetic data to fine-tune our system the translation of OOVs can be dramatically improved. In our experiments we use a system trained on Europarl and mine sentences containing medical terms from monolingual data. |
| Tasks | Machine Translation, Word Embeddings |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1581/ |
| https://www.aclweb.org/anthology/P19-1581 | |
| PWC | https://paperswithcode.com/paper/better-oov-translation-with-bilingual |
| Repo | |
| Framework | |
LEARNING GENERATIVE MODELS FOR DEMIXING OF STRUCTURED SIGNALS FROM THEIR SUPERPOSITION USING GANS
| Title | LEARNING GENERATIVE MODELS FOR DEMIXING OF STRUCTURED SIGNALS FROM THEIR SUPERPOSITION USING GANS |
| Authors | Mohammadreza Soltani, Swayambhoo Jain, Abhinav V. Sambasivan |
| Abstract | Recently, Generative Adversarial Networks (GANs) have emerged as a popular alternative for modeling complex high dimensional distributions. Most of the existing works implicitly assume that the clean samples from the target distribution are easily available. However, in many applications, this assumption is violated. In this paper, we consider the problem of learning GANs under the observation setting when the samples from target distribution are given by the superposition of two structured components. We propose two novel frameworks: denoising-GAN and demixing-GAN. The denoising-GAN assumes access to clean samples from the second component and try to learn the other distribution, whereas demixing-GAN learns the distribution of the components at the same time. Through comprehensive numerical experiments, we demonstrate that proposed frameworks can generate clean samples from unknown distributions, and provide competitive performance in tasks such as denoising, demixing, and compressive sensing. |
| Tasks | Compressive Sensing, Denoising |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rkeqCoA5tX |
| https://openreview.net/pdf?id=rkeqCoA5tX | |
| PWC | https://paperswithcode.com/paper/learning-generative-models-for-demixing-of |
| Repo | |
| Framework | |
Overview of AIWolfDial 2019 Shared Task: Contest of Automatic Dialog Agents to Play the Werewolf Game through Conversations
| Title | Overview of AIWolfDial 2019 Shared Task: Contest of Automatic Dialog Agents to Play the Werewolf Game through Conversations |
| Authors | Yoshinobu Kano, Claus Aranha, Michimasa Inaba, Fujio Toriumi, Hirotaka Osawa, Daisuke Katagami, Takashi Otsuki, Issei Tsunoda, Shoji Nagayama, Dol{\c{c}}a Tellols, Yu Sugawara, Yohei Nakata |
| Abstract | |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8301/ |
| https://www.aclweb.org/anthology/W19-8301 | |
| PWC | https://paperswithcode.com/paper/overview-of-aiwolfdial-2019-shared-task |
| Repo | |
| Framework | |
An ELMo-inspired approach to SemDeep-5’s Word-in-Context task
| Title | An ELMo-inspired approach to SemDeep-5’s Word-in-Context task |
| Authors | Alan Ansell, Felipe Bravo-Marquez, Bernhard Pfahringer |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5804/ |
| https://www.aclweb.org/anthology/W19-5804 | |
| PWC | https://paperswithcode.com/paper/an-elmo-inspired-approach-to-semdeep-5s-word |
| Repo | |
| Framework | |
LIMSI-MULTISEM at the IJCAI SemDeep-5 WiC Challenge: Context Representations for Word Usage Similarity Estimation
| Title | LIMSI-MULTISEM at the IJCAI SemDeep-5 WiC Challenge: Context Representations for Word Usage Similarity Estimation |
| Authors | Aina Gar{'\i} Soler, Marianna Apidianaki, Alex Allauzen, re |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5802/ |
| https://www.aclweb.org/anthology/W19-5802 | |
| PWC | https://paperswithcode.com/paper/limsi-multisem-at-the-ijcai-semdeep-5-wic |
| Repo | |
| Framework | |
Are Talkative AI Agents More Likely to Win the Werewolf Game?
| Title | Are Talkative AI Agents More Likely to Win the Werewolf Game? |
| Authors | Dol{\c{c}}a Tellols |
| Abstract | |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8302/ |
| https://www.aclweb.org/anthology/W19-8302 | |
| PWC | https://paperswithcode.com/paper/are-talkative-ai-agents-more-likely-to-win |
| Repo | |
| Framework | |
Strategies for an Autonomous Agent Playing the ``Werewolf game’’ as a Stealth Werewolf
| Title | Strategies for an Autonomous Agent Playing the ``Werewolf game’’ as a Stealth Werewolf | |
| Authors | Shoji Nagayama, Jotaro Abe, Kosuke Oya, Kotaro Sakamoto, Hideyuki Shibuki, Tatsunori Mori, K, Noriko o |
| Abstract | |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8305/ |
| https://www.aclweb.org/anthology/W19-8305 | |
| PWC | https://paperswithcode.com/paper/strategies-for-an-autonomous-agent-playing |
| Repo | |
| Framework | |
A Survey of Explainable AI Terminology
| Title | A Survey of Explainable AI Terminology |
| Authors | Miruna-Adriana Clinciu, Helen Hastie |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-8403/ |
| https://www.aclweb.org/anthology/W19-8403 | |
| PWC | https://paperswithcode.com/paper/a-survey-of-explainable-ai-terminology |
| Repo | |
| Framework | |
Using hyperbolic large-margin classifiers for biological link prediction
| Title | Using hyperbolic large-margin classifiers for biological link prediction |
| Authors | Asan Agibetov, Georg Dorffner, Matthias Samwald |
| Abstract | |
| Tasks | Link Prediction |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5805/ |
| https://www.aclweb.org/anthology/W19-5805 | |
| PWC | https://paperswithcode.com/paper/using-hyperbolic-large-margin-classifiers-for |
| Repo | |
| Framework | |
Universal Derivations Kickoff: A Collection of Harmonized Derivational Resources for Eleven Languages
| Title | Universal Derivations Kickoff: A Collection of Harmonized Derivational Resources for Eleven Languages |
| Authors | Luk{'a}{\v{s}} Kyj{'a}nek, Zden{\v{e}}k {\v{Z}}abokrtsk{'y}, Magda {\v{S}}ev{\v{c}}{'\i}kov{'a}, Jon{'a}{\v{s}} Vidra |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8512/ |
| https://www.aclweb.org/anthology/W19-8512 | |
| PWC | https://paperswithcode.com/paper/universal-derivations-kickoff-a-collection-of |
| Repo | |
| Framework | |
