Paper Group NANR 78
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop. Fast Similarity Search via Optimal Sparse Lifting. Diachronic degradation of language models: Insights from social media. Improving Feature Extraction for Pathology Reports with Precise Negation Scope Detecti …
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop
| Title | Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-4000/ |
| https://www.aclweb.org/anthology/N18-4000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2018-conference-of-the-1 |
| Repo | |
| Framework | |
Fast Similarity Search via Optimal Sparse Lifting
| Title | Fast Similarity Search via Optimal Sparse Lifting |
| Authors | Wenye Li, Jingwei Mao, Yin Zhang, Shuguang Cui |
| Abstract | Similarity search is a fundamental problem in computing science with various applications and has attracted significant research attention, especially in large-scale search with high dimensions. Motivated by the evidence in biological science, our work develops a novel approach for similarity search. Fundamentally different from existing methods that typically reduce the dimension of the data to lessen the computational complexity and speed up the search, our approach projects the data into an even higher-dimensional space while ensuring the sparsity of the data in the output space, with the objective of further improving precision and speed. Specifically, our approach has two key steps. Firstly, it computes the optimal sparse lifting for given input samples and increases the dimension of the data while approximately preserving their pairwise similarity. Secondly, it seeks the optimal lifting operator that best maps input samples to the optimal sparse lifting. Computationally, both steps are modeled as optimization problems that can be efficiently and effectively solved by the Frank-Wolfe algorithm. Simple as it is, our approach has reported significantly improved results in empirical evaluations, and exhibited its high potentials in solving practical problems. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7302-fast-similarity-search-via-optimal-sparse-lifting |
| http://papers.nips.cc/paper/7302-fast-similarity-search-via-optimal-sparse-lifting.pdf | |
| PWC | https://paperswithcode.com/paper/fast-similarity-search-via-optimal-sparse |
| Repo | |
| Framework | |
Diachronic degradation of language models: Insights from social media
| Title | Diachronic degradation of language models: Insights from social media |
| Authors | Kokil Jaidka, Niyati Chhaya, Lyle Ungar |
| Abstract | Natural languages change over time because they evolve to the needs of their users and the socio-technological environment. This study investigates the diachronic accuracy of pre-trained language models for downstream tasks in machine learning and user profiling. It asks the question: given that the social media platform and its users remain the same, how is language changing over time? How can these differences be used to track the changes in the affect around a particular topic? To our knowledge, this is the first study to show that it is possible to measure diachronic semantic drifts within social media and within the span of a few years. |
| Tasks | Word Embeddings |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2032/ |
| https://www.aclweb.org/anthology/P18-2032 | |
| PWC | https://paperswithcode.com/paper/diachronic-degradation-of-language-models |
| Repo | |
| Framework | |
Improving Feature Extraction for Pathology Reports with Precise Negation Scope Detection
| Title | Improving Feature Extraction for Pathology Reports with Precise Negation Scope Detection |
| Authors | Olga Zamaraeva, Kristen Howell, Adam Rhine |
| Abstract | We use a broad coverage, linguistically precise English Resource Grammar (ERG) to detect negation scope in sentences taken from pathology reports. We show that incorporating this information in feature extraction has a positive effect on classification of the reports with respect to cancer laterality compared with NegEx, a commonly used tool for negation detection. We analyze the differences between NegEx and ERG results on our dataset and how these differences indicate some directions for future work. |
| Tasks | Negation Detection |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1302/ |
| https://www.aclweb.org/anthology/C18-1302 | |
| PWC | https://paperswithcode.com/paper/improving-feature-extraction-for-pathology |
| Repo | |
| Framework | |
Why so gloomy? A Bayesian explanation of human pessimism bias in the multi-armed bandit task
| Title | Why so gloomy? A Bayesian explanation of human pessimism bias in the multi-armed bandit task |
| Authors | Dalin Guo, Angela J. Yu |
| Abstract | How humans make repeated choices among options with imperfectly known reward outcomes is an important problem in psychology and neuroscience. This is often studied using multi-armed bandits, which is also frequently studied in machine learning. We present data from a human stationary bandit experiment, in which we vary the average abundance and variability of reward availability (mean and variance of reward rate distributions). Surprisingly, we find subjects significantly underestimate prior mean of reward rates – based on their self-report, at the end of a game, on their reward expectation of non-chosen arms. Previously, human learning in the bandit task was found to be well captured by a Bayesian ideal learning model, the Dynamic Belief Model (DBM), albeit under an incorrect generative assumption of the temporal structure - humans assume reward rates can change over time even though they are actually fixed. We find that the “pessimism bias” in the bandit task is well captured by the prior mean of DBM when fitted to human choices; but it is poorly captured by the prior mean of the Fixed Belief Model (FBM), an alternative Bayesian model that (correctly) assumes reward rates to be constants. This pessimism bias is also incompletely captured by a simple reinforcement learning model (RL) commonly used in neuroscience and psychology, in terms of fitted initial Q-values. While it seems sub-optimal, and thus mysterious, that humans have an underestimated prior reward expectation, our simulations show that an underestimated prior mean helps to maximize long-term gain, if the observer assumes volatility when reward rates are stable and utilizes a softmax decision policy instead of the optimal one (obtainable by dynamic programming). This raises the intriguing possibility that the brain underestimates reward rates to compensate for the incorrect non-stationarity assumption in the generative model and a simplified decision policy. |
| Tasks | Multi-Armed Bandits |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7764-why-so-gloomy-a-bayesian-explanation-of-human-pessimism-bias-in-the-multi-armed-bandit-task |
| http://papers.nips.cc/paper/7764-why-so-gloomy-a-bayesian-explanation-of-human-pessimism-bias-in-the-multi-armed-bandit-task.pdf | |
| PWC | https://paperswithcode.com/paper/why-so-gloomy-a-bayesian-explanation-of-human |
| Repo | |
| Framework | |
Parallel Corpora for bi-lingual English-Ethiopian Languages Statistical Machine Translation
| Title | Parallel Corpora for bi-lingual English-Ethiopian Languages Statistical Machine Translation |
| Authors | Solomon Teferra Abate, Michael Melese, Martha Yifiru Tachbelie, Million Meshesha, Solomon Atinafu, Wondwossen Mulugeta, Yaregal Assabie, Hafte Abera, Binyam Ephrem, Tewodros Abebe, Wondimagegnhue Tsegaye, Amanuel Lemma, Tsegaye Andargie, Seifedin Shifaw |
| Abstract | In this paper, we describe an attempt towards the development of parallel corpora for English and Ethiopian Languages, such as Amharic, Tigrigna, Afan-Oromo, Wolaytta and Ge{'}ez. The corpora are used for conducting a bi-directional statistical machine translation experiments. The BLEU scores of the bi-directional Statistical Machine Translation (SMT) systems show a promising result. The morphological richness of the Ethiopian languages has a great impact on the performance of SMT specially when the targets are Ethiopian languages. Now we are working towards an optimal alignment for a bi-directional English-Ethiopian languages SMT. |
| Tasks | Machine Translation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1262/ |
| https://www.aclweb.org/anthology/C18-1262 | |
| PWC | https://paperswithcode.com/paper/parallel-corpora-for-bi-lingual-english |
| Repo | |
| Framework | |
Learning Sentiment Composition from Sentiment Lexicons
| Title | Learning Sentiment Composition from Sentiment Lexicons |
| Authors | Orith Toledo-Ronen, Roy Bar-Haim, Alon Halfon, Charles Jochim, Amir Menczel, Ranit Aharonov, Noam Slonim |
| Abstract | Sentiment composition is a fundamental sentiment analysis problem. Previous work relied on manual rules and manually-created lexical resources such as negator lists, or learned a composition function from sentiment-annotated phrases or sentences. We propose a new approach for learning sentiment composition from a large, unlabeled corpus, which only requires a word-level sentiment lexicon for supervision. We automatically generate large sentiment lexicons of bigrams and unigrams, from which we induce a set of lexicons for a variety of sentiment composition processes. The effectiveness of our approach is confirmed through manual annotation, as well as sentiment classification experiments with both phrase-level and sentence-level benchmarks. |
| Tasks | Sentiment Analysis |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1189/ |
| https://www.aclweb.org/anthology/C18-1189 | |
| PWC | https://paperswithcode.com/paper/learning-sentiment-composition-from-sentiment |
| Repo | |
| Framework | |
Transfer Learning for British Sign Language Modelling
| Title | Transfer Learning for British Sign Language Modelling |
| Authors | Boris Mocialov, Helen Hastie, Graham Turner |
| Abstract | Automatic speech recognition and spoken dialogue systems have made great advances through the use of deep machine learning methods. This is partly due to greater computing power but also through the large amount of data available in common languages, such as English. Conversely, research in minority languages, including sign languages, is hampered by the severe lack of data. This has led to work on transfer learning methods, whereby a model developed for one language is reused as the starting point for a model on a second language, which is less resourced. In this paper, we examine two transfer learning techniques of fine-tuning and layer substitution for language modelling of British Sign Language. Our results show improvement in perplexity when using transfer learning with standard stacked LSTM models, trained initially using a large corpus for standard English from the Penn Treebank corpus. |
| Tasks | Language Modelling, Speech Recognition, Spoken Dialogue Systems, Transfer Learning, Video Recognition |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3911/ |
| https://www.aclweb.org/anthology/W18-3911 | |
| PWC | https://paperswithcode.com/paper/transfer-learning-for-british-sign-language |
| Repo | |
| Framework | |
Structure-from-Motion-Aware PatchMatch for Adaptive Optical Flow Estimation
| Title | Structure-from-Motion-Aware PatchMatch for Adaptive Optical Flow Estimation |
| Authors | Daniel Maurer, Nico Marniok, Bastian Goldluecke, Andres Bruhn |
| Abstract | Many recent energy-based methods for optical flow estimation rely on a good initialization that is typically provided by some kind of feature matching. So far, however, these initial matching approaches are rather general: They do not incorporate any additional information that could help to improve the accuracy or the robustness of the estimation. In particular, they do not exploit potential cues on the camera poses and the thereby induced rigid motion of the scene. In the present paper, we tackle this problem. To this end, we propose a novel structure-from-motion-aware PatchMatch approach that, in contrast to existing matching techniques, combines two hierarchical feature matching methods: a recent two-frame PatchMatch approach for optical flow estimation (general motion) and a specifically tailored three-frame PatchMatch approach for rigid scene reconstruction (SfM). While the motion PatchMatch serves as baseline with good accuracy, the SfM counterpart takes over at occlusions and other regions with insufficient information. Experiments with our novel SfM-aware PatchMatch approach demonstrate its usefulness. They not only show excellent results for all major benchmarks (KITTI 2012/2015, MPI Sintel), but also improvements up to 50 percent compared to a PatchMatch approach without structure information. |
| Tasks | Optical Flow Estimation |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Daniel_Maurer_Structure-from-Motion-Aware_PatchMatch_for_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Daniel_Maurer_Structure-from-Motion-Aware_PatchMatch_for_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/structure-from-motion-aware-patchmatch-for |
| Repo | |
| Framework | |
Pay-Per-Request Deployment of Neural Network Models Using Serverless Architectures
| Title | Pay-Per-Request Deployment of Neural Network Models Using Serverless Architectures |
| Authors | Zhucheng Tu, Mengping Li, Jimmy Lin |
| Abstract | We demonstrate the serverless deployment of neural networks for model inferencing in NLP applications using Amazon{'}s Lambda service for feedforward evaluation and DynamoDB for storing word embeddings. Our architecture realizes a pay-per-request pricing model, requiring zero ongoing costs for maintaining server instances. All virtual machine management is handled behind the scenes by the cloud provider without any direct developer intervention. We describe a number of techniques that allow efficient use of serverless resources, and evaluations confirm that our design is both scalable and inexpensive. |
| Tasks | Answer Selection, Question Answering, Sentence Classification, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-5002/ |
| https://www.aclweb.org/anthology/N18-5002 | |
| PWC | https://paperswithcode.com/paper/pay-per-request-deployment-of-neural-network |
| Repo | |
| Framework | |
Annotating Reflections for Health Behavior Change Therapy
| Title | Annotating Reflections for Health Behavior Change Therapy |
| Authors | Guntak, Nishitha la, Rodney Nielsen |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1631/ |
| https://www.aclweb.org/anthology/L18-1631 | |
| PWC | https://paperswithcode.com/paper/annotating-reflections-for-health-behavior |
| Repo | |
| Framework | |
Stochastic Spectral and Conjugate Descent Methods
| Title | Stochastic Spectral and Conjugate Descent Methods |
| Authors | Dmitry Kovalev, Peter Richtarik, Eduard Gorbunov, Elnur Gasanov |
| Abstract | The state-of-the-art methods for solving optimization problems in big dimensions are variants of randomized coordinate descent (RCD). In this paper we introduce a fundamentally new type of acceleration strategy for RCD based on the augmentation of the set of coordinate directions by a few spectral or conjugate directions. As we increase the number of extra directions to be sampled from, the rate of the method improves, and interpolates between the linear rate of RCD and a linear rate independent of the condition number. We develop and analyze also inexact variants of these methods where the spectral and conjugate directions are allowed to be approximate only. We motivate the above development by proving several negative results which highlight the limitations of RCD with importance sampling. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7596-stochastic-spectral-and-conjugate-descent-methods |
| http://papers.nips.cc/paper/7596-stochastic-spectral-and-conjugate-descent-methods.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-spectral-and-conjugate-descent |
| Repo | |
| Framework | |
Integrating Egocentric Videos in Top-view Surveillance Videos: Joint Identification and Temporal Alignment
| Title | Integrating Egocentric Videos in Top-view Surveillance Videos: Joint Identification and Temporal Alignment |
| Authors | Shervin Ardeshir, Ali Borji |
| Abstract | Videos recorded from first person (egocentric) perspective have little visual appearance in common with those from third person perspective, especially with videos captured by top-view surveillance cameras. In this paper, we aim to relate these two sources of information from a surveillance standpoint, namely in terms of identification and temporal alignment. Given an egocentric video and a top-view video, our goals are to: a) identify the egocentric camera holder in the top-view video (self-identification), b) identify the humans visible in the content of the egocentric video, within the content of the top-view video (re-identification), and c) temporally align the two videos. The main challenge is that each of these tasks is highly dependent on the other two. We propose a unified framework to jointly solve all three problems. We evaluate the efficacy of the proposed approach on a publicly available dataset containing a variety of videos recorded in different scenarios. |
| Tasks | |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Shervin_Ardeshir_Integrating_Egocentric_Videos_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Shervin_Ardeshir_Integrating_Egocentric_Videos_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/integrating-egocentric-videos-in-top-view |
| Repo | |
| Framework | |
End-to-end speech recognition using lattice-free MMI
| Title | End-to-end speech recognition using lattice-free MMI |
| Authors | Hossein Hadian, Hossein Sameti, Daniel Povey, Sanjeev Khudanpur |
| Abstract | We present our work on end-to-end training of acoustic models using the lattice-free maximum mutual information (LF-MMI) objective function in the context of hidden Markov models. By end-to-end training, we mean flat-start training of a single DNN in one stage without using any previously trained models, forced alignments, or building state-tying decision trees. We use full biphones to enable context-dependent modeling without trees, and show that our end-to-end LF-MMI approach can achieve comparable results to regular LF-MMI on well-known large vocabulary tasks. We also compare with other end-to-end methods such as CTC in character-based and lexicon-free settings and show 5 to 25 percent relative reduction in word error rates on different large vocabulary tasks while using significantly smaller models. |
| Tasks | End-To-End Speech Recognition, Speech Recognition |
| Published | 2018-09-06 |
| URL | https://www.isca-speech.org/archive/Interspeech_2018/abstracts/1423.html |
| https://www.danielpovey.com/files/2018_interspeech_end2end.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-speech-recognition-using-lattice |
| Repo | |
| Framework | |
THU_NGN at SemEval-2018 Task 3: Tweet Irony Detection with Densely connected LSTM and Multi-task Learning
| Title | THU_NGN at SemEval-2018 Task 3: Tweet Irony Detection with Densely connected LSTM and Multi-task Learning |
| Authors | Chuhan Wu, Fangzhao Wu, Sixing Wu, Junxin Liu, Zhigang Yuan, Yongfeng Huang |
| Abstract | Detecting irony is an important task to mine fine-grained information from social web messages. Therefore, the Semeval-2018 task 3 is aimed to detect the ironic tweets (subtask A) and their ironic types (subtask B). In order to address this task, we propose a system based on a densely connected LSTM network with multi-task learning strategy. In our dense LSTM model, each layer will take all outputs from previous layers as input. The last LSTM layer will output the hidden representations of texts, and they will be used in three classification task. In addition, we incorporate several types of features to improve the model performance. Our model achieved an F-score of 70.54 (ranked 2/43) in the subtask A and 49.47 (ranked 3/29) in the subtask B. The experimental results validate the effectiveness of our system. |
| Tasks | Feature Engineering, Multi-Task Learning, Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1006/ |
| https://www.aclweb.org/anthology/S18-1006 | |
| PWC | https://paperswithcode.com/paper/thu_ngn-at-semeval-2018-task-3-tweet-irony |
| Repo | |
| Framework | |
