Paper Group NANR 218
Learning Prototypical Event Structure from Photo Albums. Scoring Disease-Medication Associations using Advanced NLP, Machine Learning, and Multiple Content Sources. 以多重表示選擇文章分類的樣本(Using Multiple Representations to Select Instances for Text Classification)[In Chinese]. Modifications of Machine Translation Evaluation Metrics by Using Word Embeddings. …
Learning Prototypical Event Structure from Photo Albums
| Title | Learning Prototypical Event Structure from Photo Albums |
| Authors | Antoine Bosselut, Jianfu Chen, David Warren, Hannaneh Hajishirzi, Yejin Choi |
| Abstract | |
| Tasks | Common Sense Reasoning |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1167/ |
| https://www.aclweb.org/anthology/P16-1167 | |
| PWC | https://paperswithcode.com/paper/learning-prototypical-event-structure-from |
| Repo | |
| Framework | |
Scoring Disease-Medication Associations using Advanced NLP, Machine Learning, and Multiple Content Sources
| Title | Scoring Disease-Medication Associations using Advanced NLP, Machine Learning, and Multiple Content Sources |
| Authors | D, Bharath ala, Murthy Devarakonda, Mihaela Bornea, Christopher Nielson |
| Abstract | Effective knowledge resources are critical for developing successful clinical decision support systems that alleviate the cognitive load on physicians in patient care. In this paper, we describe two new methods for building a knowledge resource of disease to medication associations. These methods use fundamentally different content and are based on advanced natural language processing and machine learning techniques. One method uses distributional semantics on large medical text, and the other uses data mining on a large number of patient records. The methods are evaluated using 25,379 unique disease-medication pairs extracted from 100 de-identified longitudinal patient records of a large multi-provider hospital system. We measured recall (R), precision (P), and F scores for positive and negative association prediction, along with coverage and accuracy. While individual methods performed well, a combined stacked classifier achieved the best performance, indicating the limitations and unique value of each resource and method. In predicting positive associations, the stacked combination significantly outperformed the baseline (a distant semi-supervised method on large medical text), achieving F scores of 0.75 versus 0.55 on the pairs seen in the patient records, and F scores of 0.69 and 0.35 on unique pairs. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5114/ |
| https://www.aclweb.org/anthology/W16-5114 | |
| PWC | https://paperswithcode.com/paper/scoring-disease-medication-associations-using |
| Repo | |
| Framework | |
以多重表示選擇文章分類的樣本(Using Multiple Representations to Select Instances for Text Classification)[In Chinese]
| Title | 以多重表示選擇文章分類的樣本(Using Multiple Representations to Select Instances for Text Classification)[In Chinese] |
| Authors | Yao-Hui Chen, Jhih-Wei Wang |
| Abstract | |
| Tasks | Text Classification |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/O16-1019/ |
| https://www.aclweb.org/anthology/O16-1019 | |
| PWC | https://paperswithcode.com/paper/aaee-coe-c-aec-using-multiple-representations |
| Repo | |
| Framework | |
Modifications of Machine Translation Evaluation Metrics by Using Word Embeddings
| Title | Modifications of Machine Translation Evaluation Metrics by Using Word Embeddings |
| Authors | Haozhou Wang, Paola Merlo |
| Abstract | Traditional machine translation evaluation metrics such as BLEU and WER have been widely used, but these metrics have poor correlations with human judgements because they badly represent word similarity and impose strict identity matching. In this paper, we propose some modifications to the traditional measures based on word embeddings for these two metrics. The evaluation results show that our modifications significantly improve their correlation with human judgements. |
| Tasks | Machine Translation, Semantic Textual Similarity, Word Embeddings |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4505/ |
| https://www.aclweb.org/anthology/W16-4505 | |
| PWC | https://paperswithcode.com/paper/modifications-of-machine-translation |
| Repo | |
| Framework | |
Predicting Post Severity in Mental Health Forums
| Title | Predicting Post Severity in Mental Health Forums |
| Authors | Shervin Malmasi, Marcos Zampieri, Mark Dras |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0314/ |
| https://www.aclweb.org/anthology/W16-0314 | |
| PWC | https://paperswithcode.com/paper/predicting-post-severity-in-mental-health |
| Repo | |
| Framework | |
Regret of Queueing Bandits
| Title | Regret of Queueing Bandits |
| Authors | Subhashini Krishnasamy, Rajat Sen, Ramesh Johari, Sanjay Shakkottai |
| Abstract | We consider a variant of the multiarmed bandit problem where jobs queue for service, and service rates of different servers may be unknown. We study algorithms that minimize queue-regret: the (expected) difference between the queue-lengths obtained by the algorithm, and those obtained by a genie-aided matching algorithm that knows exact service rates. A naive view of this problem would suggest that queue-regret should grow logarithmically: since queue-regret cannot be larger than classical regret, results for the standard MAB problem give algorithms that ensure queue-regret increases no more than logarithmically in time. Our paper shows surprisingly more complex behavior. In particular, the naive intuition is correct as long as the bandit algorithm’s queues have relatively long regenerative cycles: in this case queue-regret is similar to cumulative regret, and scales (essentially) logarithmically. However, we show that this “early stage” of the queueing bandit eventually gives way to a “late stage”, where the optimal queue-regret scaling is O(1/t). We demonstrate an algorithm that (order-wise) achieves this asymptotic queue-regret, and also exhibits close to optimal switching time from the early stage to the late stage. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6370-regret-of-queueing-bandits |
| http://papers.nips.cc/paper/6370-regret-of-queueing-bandits.pdf | |
| PWC | https://paperswithcode.com/paper/regret-of-queueing-bandits |
| Repo | |
| Framework | |
A Bandit Framework for Strategic Regression
| Title | A Bandit Framework for Strategic Regression |
| Authors | Yang Liu, Yiling Chen |
| Abstract | We consider a learner’s problem of acquiring data dynamically for training a regression model, where the training data are collected from strategic data sources. A fundamental challenge is to incentivize data holders to exert effort to improve the quality of their reported data, despite that the quality is not directly verifiable by the learner. In this work, we study a dynamic data acquisition process where data holders can contribute multiple times. Using a bandit framework, we leverage on the long-term incentive of future job opportunities to incentivize high-quality contributions. We propose a Strategic Regression-Upper Confidence Bound (SR-UCB) framework, an UCB-style index combined with a simple payment rule, where the index of a worker approximates the quality of his past contributions and is used by the learner to determine whether the worker receives future work. For linear regression and certain family of non-linear regression problems, we show that SR-UCB enables a $O(\sqrt{\log T/T})$-Bayesian Nash Equilibrium (BNE) where each worker exerting a target effort level that the learner has chosen, with $T$ being the number of data acquisition stages. The SR-UCB framework also has some other desirable properties: (1) The indexes can be updated in an online fashion (hence computationally light). (2) A slight variant, namely Private SR-UCB (PSR-UCB), is able to preserve $(O(\log^{-1} T), O(\log^{-1} T))$-differential privacy for workers’ data, with only a small compromise on incentives (achieving $O(\log^{6} T/\sqrt{T})$-BNE). |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6190-a-bandit-framework-for-strategic-regression |
| http://papers.nips.cc/paper/6190-a-bandit-framework-for-strategic-regression.pdf | |
| PWC | https://paperswithcode.com/paper/a-bandit-framework-for-strategic-regression |
| Repo | |
| Framework | |
The Teams Corpus and Entrainment in Multi-Party Spoken Dialogues
| Title | The Teams Corpus and Entrainment in Multi-Party Spoken Dialogues |
| Authors | Diane Litman, Susannah Paletz, Zahra Rahimi, Stefani Allegretti, Caitlin Rice |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1149/ |
| https://www.aclweb.org/anthology/D16-1149 | |
| PWC | https://paperswithcode.com/paper/the-teams-corpus-and-entrainment-in-multi |
| Repo | |
| Framework | |
Language technology tools and resources for the analysis of multimodal communication
| Title | Language technology tools and resources for the analysis of multimodal communication |
| Authors | L{'a}szl{'o} Hunyadi, Tam{'a}s V{'a}radi, Istv{'a}n Szekr{'e}nyes |
| Abstract | In this paper we describe how the complexity of human communication can be analysed with the help of language technology. We present the HuComTech corpus, a multimodal corpus containing 50 hours of videotaped interviews containing a rich annotation of about 2 million items annotated on 33 levels. The corpus serves as a general resource for a wide range of re-search addressing natural conversation between humans in their full complexity. It can benefit particularly digital humanities researchers working in the field of pragmatics, conversational analysis and discourse analysis. We will present a number of tools and automated methods that can help such enquiries. In particular, we will highlight the tool Theme, which is designed to uncover hidden temporal patterns (called T-patterns) in human interaction, and will show how it can applied to the study of multimodal communication. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4016/ |
| https://www.aclweb.org/anthology/W16-4016 | |
| PWC | https://paperswithcode.com/paper/language-technology-tools-and-resources-for |
| Repo | |
| Framework | |
Analyzing Biases in Human Perception of User Age and Gender from Text
| Title | Analyzing Biases in Human Perception of User Age and Gender from Text |
| Authors | Lucie Flekova, Jordan Carpenter, Salvatore Giorgi, Lyle Ungar, Daniel Preo{\c{t}}iuc-Pietro |
| Abstract | |
| Tasks | Recommendation Systems |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1080/ |
| https://www.aclweb.org/anthology/P16-1080 | |
| PWC | https://paperswithcode.com/paper/analyzing-biases-in-human-perception-of-user |
| Repo | |
| Framework | |
The RWTH Aachen University English-Romanian Machine Translation System for WMT 2016
| Title | The RWTH Aachen University English-Romanian Machine Translation System for WMT 2016 |
| Authors | Jan-Thorsten Peter, Tamer Alkhouli, Andreas Guta, Hermann Ney |
| Abstract | |
| Tasks | Language Modelling, Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2321/ |
| https://www.aclweb.org/anthology/W16-2321 | |
| PWC | https://paperswithcode.com/paper/the-rwth-aachen-university-english-romanian |
| Repo | |
| Framework | |
Processing Dialectal Arabic: Exploiting Variability and Similarity to Overcome Challenges and Discover Opportunities
| Title | Processing Dialectal Arabic: Exploiting Variability and Similarity to Overcome Challenges and Discover Opportunities |
| Authors | Mona Diab |
| Abstract | We recently witnessed an exponential growth in dialectal Arabic usage in both textual data and speech recordings especially in social media. Processing such media is of great utility for all kinds of applications ranging from information extraction to social media analytics for political and commercial purposes to building decision support systems. Compared to other languages, Arabic, especially the informal variety, poses a significant challenge to natural language processing algorithms since it comprises multiple dialects, linguistic code switching, and a lack of standardized orthographies, to top its relatively complex morphology. Inherently, the problem of processing Arabic in the context of social media is the problem of how to handle resource poor languages. In this talk I will go over some of our insights to some of these problems and show how there is a silver lining where we can generalize some of our solutions to other low resource language contexts. |
| Tasks | Machine Translation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4805/ |
| https://www.aclweb.org/anthology/W16-4805 | |
| PWC | https://paperswithcode.com/paper/processing-dialectal-arabic-exploiting |
| Repo | |
| Framework | |
QUEMDISSE? Reported speech in Portuguese
| Title | QUEMDISSE? Reported speech in Portuguese |
| Authors | Cl{'a}udia Freitas, Bianca Freitas, Diana Santos |
| Abstract | This paper presents some work on direct and indirect speech in Portuguese using corpus-based methods: we report on a study whose aim was to identify (i) Portuguese verbs used to introduce reported speech and (ii) syntactic patterns used to convey reported speech, in order to enhance the performance of a quotation extraction system, dubbed QUEMDISSE?. In addition, (iii) we present a Portuguese corpus annotated with reported speech, using the lexicon and rules provided by (i) and (ii), and discuss the process of their annotation and what was learned. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1698/ |
| https://www.aclweb.org/anthology/L16-1698 | |
| PWC | https://paperswithcode.com/paper/quemdisse-reported-speech-in-portuguese |
| Repo | |
| Framework | |
Visualizing and Curating Knowledge Graphs over Time and Space
| Title | Visualizing and Curating Knowledge Graphs over Time and Space |
| Authors | Tong Ge, Yafang Wang, Gerard de Melo, Haofeng Li, Baoquan Chen |
| Abstract | |
| Tasks | Knowledge Graphs, Named Entity Recognition |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-4005/ |
| https://www.aclweb.org/anthology/P16-4005 | |
| PWC | https://paperswithcode.com/paper/visualizing-and-curating-knowledge-graphs |
| Repo | |
| Framework | |
Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Keynote Speeches and Invited Talks
| Title | Proceedings of the 30th Pacific Asia Conference on Language, Information and Computation: Keynote Speeches and Invited Talks |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/Y16-1000/ |
| https://www.aclweb.org/anthology/Y16-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-30th-pacific-asia |
| Repo | |
| Framework | |
