Paper Group NANR 103
The AFRL WMT17 Neural Machine Translation Training Task Submission. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Efficient Nonmyopic Active Search. How much progress have we made on RST discourse parsing? A replication study of recent results on the RST-DT. Do Not Trust the Trolls: …
The AFRL WMT17 Neural Machine Translation Training Task Submission
| Title | The AFRL WMT17 Neural Machine Translation Training Task Submission |
| Authors | Jeremy Gwinnup, Grant Erdmann, Katherine Young |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4781/ |
| https://www.aclweb.org/anthology/W17-4781 | |
| PWC | https://paperswithcode.com/paper/the-afrl-wmt17-neural-machine-translation |
| Repo | |
| Framework | |
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
| Title | Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1000/ |
| https://www.aclweb.org/anthology/P17-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-55th-annual-meeting-of-the-1 |
| Repo | |
| Framework | |
Efficient Nonmyopic Active Search
| Title | Efficient Nonmyopic Active Search |
| Authors | Shali Jiang, Gustavo Malkomes, Geoff Converse, Alyssa Shofner, Benjamin Moseley, Roman Garnett |
| Abstract | Active search is an active learning setting with the goal of identifying as many members of a given class as possible under a labeling budget. In this work, we first establish a theoretical hardness of active search, proving that no polynomial-time policy can achieve a constant factor approximation ratio with respect to the expected utility of the optimal policy. We also propose a novel, computationally efficient active search policy achieving exceptional performance on several real-world tasks. Our policy is nonmyopic, always considering the entire remaining search budget. It also automatically and dynamically balances exploration and exploitation consistent with the remaining budget, without relying on a parameter to control this tradeoff. We conduct experiments on diverse datasets from several domains: drug discovery, materials science, and a citation network. Our efficient nonmyopic policy recovers significantly more valuable points with the same budget than several alternatives from the literature, including myopic approximations to the optimal policy. |
| Tasks | Active Learning, Drug Discovery |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=553 |
| http://proceedings.mlr.press/v70/jiang17d/jiang17d.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-nonmyopic-active-search |
| Repo | |
| Framework | |
How much progress have we made on RST discourse parsing? A replication study of recent results on the RST-DT
| Title | How much progress have we made on RST discourse parsing? A replication study of recent results on the RST-DT |
| Authors | Mathieu Morey, Philippe Muller, Nicholas Asher |
| Abstract | This article evaluates purported progress over the past years in RST discourse parsing. Several studies report a relative error reduction of 24 to 51{%} on all metrics that authors attribute to the introduction of distributed representations of discourse units. We replicate the standard evaluation of 9 parsers, 5 of which use distributed representations, from 8 studies published between 2013 and 2017, using their predictions on the test set of the RST-DT. Our main finding is that most recently reported increases in RST discourse parser performance are an artefact of differences in implementations of the evaluation procedure. We evaluate all these parsers with the standard Parseval procedure to provide a more accurate picture of the actual RST discourse parsers performance in standard evaluation settings. Under this more stringent procedure, the gains attributable to distributed representations represent at most a 16{%} relative error reduction on fully-labelled structures. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1136/ |
| https://www.aclweb.org/anthology/D17-1136 | |
| PWC | https://paperswithcode.com/paper/how-much-progress-have-we-made-on-rst |
| Repo | |
| Framework | |
Do Not Trust the Trolls: Predicting Credibility in Community Question Answering Forums
| Title | Do Not Trust the Trolls: Predicting Credibility in Community Question Answering Forums |
| Authors | Preslav Nakov, Tsvetomila Mihaylova, Llu{'\i}s M{`a}rquez, Yashkumar Shiroya, Ivan Koychev |
| Abstract | We address information credibility in community forums, in a setting in which the credibility of an answer posted in a question thread by a particular user has to be predicted. First, we motivate the problem and we create a publicly available annotated English corpus by crowdsourcing. Second, we propose a large set of features to predict the credibility of the answers. The features model the user, the answer, the question, the thread as a whole, and the interaction between them. Our experiments with ranking SVMs show that the credibility labels can be predicted with high performance according to several standard IR ranking metrics, thus supporting the potential usage of this layer of credibility information in practical applications. The features modeling the profile of the user (in particular trollness) turn out to be most important, but embedding features modeling the answer and the similarity between the question and the answer are also very relevant. Overall, half of the gap between the baseline performance and the perfect classifier can be covered using the proposed features. |
| Tasks | Community Question Answering, Information Retrieval, Question Answering |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1072/ |
| https://doi.org/10.26615/978-954-452-049-6_072 | |
| PWC | https://paperswithcode.com/paper/do-not-trust-the-trolls-predicting |
| Repo | |
| Framework | |
Elementary Symmetric Polynomials for Optimal Experimental Design
| Title | Elementary Symmetric Polynomials for Optimal Experimental Design |
| Authors | Zelda E. Mariet, Suvrit Sra |
| Abstract | We revisit the classical problem of optimal experimental design (OED) under a new mathematical model grounded in a geometric motivation. Specifically, we introduce models based on elementary symmetric polynomials; these polynomials capture “partial volumes” and offer a graded interpolation between the widely used A-optimal and D-optimal design models, obtaining each of them as special cases. We analyze properties of our models, and derive both greedy and convex-relaxation algorithms for computing the associated designs. Our analysis establishes approximation guarantees on these algorithms, while our empirical results substantiate our claims and demonstrate a curious phenomenon concerning our greedy algorithm. Finally, as a byproduct, we obtain new results on the theory of elementary symmetric polynomials that may be of independent interest. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6809-elementary-symmetric-polynomials-for-optimal-experimental-design |
| http://papers.nips.cc/paper/6809-elementary-symmetric-polynomials-for-optimal-experimental-design.pdf | |
| PWC | https://paperswithcode.com/paper/elementary-symmetric-polynomials-for-optimal |
| Repo | |
| Framework | |
IIT-UHH at SemEval-2017 Task 3: Exploring Multiple Features for Community Question Answering and Implicit Dialogue Identification
| Title | IIT-UHH at SemEval-2017 Task 3: Exploring Multiple Features for Community Question Answering and Implicit Dialogue Identification |
| Authors | N, Titas i, Chris Biemann, Seid Muhie Yimam, Deepak Gupta, Sarah Kohail, Asif Ekbal, Pushpak Bhattacharyya |
| Abstract | In this paper we present the system for Answer Selection and Ranking in Community Question Answering, which we build as part of our participation in SemEval-2017 Task 3. We develop a Support Vector Machine (SVM) based system that makes use of textual, domain-specific, word-embedding and topic-modeling features. In addition, we propose a novel method for dialogue chain identification in comment threads. Our primary submission won subtask C, outperforming other systems in all the primary evaluation metrics. We performed well in other English subtasks, ranking third in subtask A and eighth in subtask B. We also developed open source toolkits for all the three English subtasks by the name cQARank [\url{https://github.com/TitasNandi/cQARank}]. |
| Tasks | Answer Selection, Community Question Answering, Question Answering, Question Similarity |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2009/ |
| https://www.aclweb.org/anthology/S17-2009 | |
| PWC | https://paperswithcode.com/paper/iit-uhh-at-semeval-2017-task-3-exploring |
| Repo | |
| Framework | |
SCIR-QA at SemEval-2017 Task 3: CNN Model Based on Similar and Dissimilar Information between Keywords for Question Similarity
| Title | SCIR-QA at SemEval-2017 Task 3: CNN Model Based on Similar and Dissimilar Information between Keywords for Question Similarity |
| Authors | Le Qi, Yu Zhang, Ting Liu |
| Abstract | We describe a method of calculating the similarity of questions in community QA. Question in cQA are usually very long and there are a lot of useless information about calculating the similarity of questions. Therefore,we implement a CNN model based on similar and dissimilar information between question{'}s keywords. We extract the keywords of questions, and then model the similar and dissimilar information between the keywords, and use the CNN model to calculate the similarity. |
| Tasks | Community Question Answering, Graph Ranking, Information Retrieval, Keyword Extraction, Question Answering, Question Similarity |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2049/ |
| https://www.aclweb.org/anthology/S17-2049 | |
| PWC | https://paperswithcode.com/paper/scir-qa-at-semeval-2017-task-3-cnn-model |
| Repo | |
| Framework | |
SimBow at SemEval-2017 Task 3: Soft-Cosine Semantic Similarity between Questions for Community Question Answering
| Title | SimBow at SemEval-2017 Task 3: Soft-Cosine Semantic Similarity between Questions for Community Question Answering |
| Authors | Delphine Charlet, G{'e}raldine Damnati |
| Abstract | This paper describes the SimBow system submitted at SemEval2017-Task3, for the question-question similarity subtask B. The proposed approach is a supervised combination of different unsupervised textual similarities. These textual similarities rely on the introduction of a relation matrix in the classical cosine similarity between bag-of-words, so as to get a soft-cosine that takes into account relations between words. According to the type of relation matrix embedded in the soft-cosine, semantic or lexical relations can be considered. Our system ranked first among the official submissions of subtask B. |
| Tasks | Community Question Answering, Knowledge Graphs, Question Answering, Question Similarity, Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2051/ |
| https://www.aclweb.org/anthology/S17-2051 | |
| PWC | https://paperswithcode.com/paper/simbow-at-semeval-2017-task-3-soft-cosine |
| Repo | |
| Framework | |
NLM_NIH at SemEval-2017 Task 3: from Question Entailment to Question Similarity for Community Question Answering
| Title | NLM_NIH at SemEval-2017 Task 3: from Question Entailment to Question Similarity for Community Question Answering |
| Authors | Asma Ben Abacha, Dina Demner-Fushman |
| Abstract | This paper describes our participation in SemEval-2017 Task 3 on Community Question Answering (cQA). The Question Similarity subtask (B) aims to rank a set of related questions retrieved by a search engine according to their similarity to the original question. We adapted our feature-based system for Recognizing Question Entailment (RQE) to the question similarity task. Tested on cQA-B-2016 test data, our RQE system outperformed the best system of the 2016 challenge in all measures with 77.47 MAP and 80.57 Accuracy. On cQA-B-2017 test data, performances of all systems dropped by around 30 points. Our primary system obtained 44.62 MAP, 67.27 Accuracy and 47.25 F1 score. The cQA-B-2017 best system achieved 47.22 MAP and 42.37 F1 score. Our system is ranked sixth in terms of MAP and third in terms of F1 out of 13 participating teams. |
| Tasks | Community Question Answering, Question Answering, Question Similarity |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2057/ |
| https://www.aclweb.org/anthology/S17-2057 | |
| PWC | https://paperswithcode.com/paper/nlm_nih-at-semeval-2017-task-3-from-question |
| Repo | |
| Framework | |
Source-Target Similarity Modelings for Multi-Source Transfer Gaussian Process Regression
| Title | Source-Target Similarity Modelings for Multi-Source Transfer Gaussian Process Regression |
| Authors | Pengfei Wei, Ramon Sagarna, Yiping Ke, Yew-Soon Ong, Chi-Keong Goh |
| Abstract | A key challenge in multi-source transfer learning is to capture the diverse inter-domain similarities. In this paper, we study different approaches based on Gaussian process models to solve the multi-source transfer regression problem. Precisely, we first investigate the feasibility and performance of a family of transfer covariance functions that represent the pairwise similarity of each source and the target domain. We theoretically show that using such a transfer covariance function for general Gaussian process modelling can only capture the same similarity coefficient for all the sources, and thus may result in unsatisfactory transfer performance. This leads us to propose TC$_{MS}$Stack, an integrated strategy incorporating the benefits of the transfer covariance function and stacking. Extensive experiments on one synthetic and two real-world datasets, with learning settings of up to 11 sources for the latter, demonstrate the effectiveness of our proposed TC$_{MS}$Stack. |
| Tasks | Transfer Learning |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=679 |
| http://proceedings.mlr.press/v70/wei17a/wei17a.pdf | |
| PWC | https://paperswithcode.com/paper/source-target-similarity-modelings-for-multi |
| Repo | |
| Framework | |
ECNU at SemEval-2017 Task 3: Using Traditional and Deep Learning Methods to Address Community Question Answering Task
| Title | ECNU at SemEval-2017 Task 3: Using Traditional and Deep Learning Methods to Address Community Question Answering Task |
| Authors | Guoshun Wu, Yixuan Sheng, Man Lan, Yuanbin Wu |
| Abstract | This paper describes the systems we submitted to the task 3 (Community Question Answering) in SemEval 2017 which contains three subtasks on English corpora, i.e., subtask A: Question-Comment Similarity, subtask B: Question-Question Similarity, and subtask C: Question-External Comment Similarity. For subtask A, we combined two different methods to represent question-comment pair, i.e., supervised model using traditional features and Convolutional Neural Network. For subtask B, we utilized the information of snippets returned from Search Engine with question subject as query. For subtask C, we ranked the comments by multiplying the probability of the pair related question comment being Good by the reciprocal rank of the related question. |
| Tasks | Community Question Answering, Question Answering, Question Similarity, Semantic Textual Similarity |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2060/ |
| https://www.aclweb.org/anthology/S17-2060 | |
| PWC | https://paperswithcode.com/paper/ecnu-at-semeval-2017-task-3-using-traditional |
| Repo | |
| Framework | |
Probabilistic Temporal Subspace Clustering
| Title | Probabilistic Temporal Subspace Clustering |
| Authors | Behnam Gholami, Vladimir Pavlovic |
| Abstract | Subspace clustering is a common modeling paradigm used to identify constituent modes of variation in data with locally linear structure. These structures are common to many problems in computer vision, including modeling time series of complex human motion. However classical subspace clustering algorithms learn the relationships within a set of data without considering the temporal dependency and then use a separate clustering step (e.g., spectral clustering) for final segmentation. Moreover, these, frequently optimization-based, algorithms assume that all observations have complete features. In contrast in real-world applications, some features are often missing, which results in incomplete data and substantial performance degeneration of these approaches. In this paper, we propose a unified non-parametric generative framework for temporal subspace clustering to segment data drawn from a sequentially ordered union of subspaces that deals with the missing features in a principled way. The non-parametric nature of our generative model makes it possible to infer the number of subspaces and their dimension automatically from data. Experimental results on human action datasets demonstrate that the proposed model consistently outperforms other state-of-the-art subspace clustering approaches. |
| Tasks | Time Series |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Gholami_Probabilistic_Temporal_Subspace_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Gholami_Probabilistic_Temporal_Subspace_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/probabilistic-temporal-subspace-clustering |
| Repo | |
| Framework | |
Semantic Vector Encoding and Similarity Search Using Fulltext Search Engines
| Title | Semantic Vector Encoding and Similarity Search Using Fulltext Search Engines |
| Authors | Jan Rygl, Jan Pomik{'a}lek, Radim {\v{R}}eh{\r{u}}{\v{r}}ek, Michal R{\r{u}}{\v{z}}i{\v{c}}ka, V{'\i}t Novotn{'y}, Petr Sojka |
| Abstract | Vector representations and vector space modeling (VSM) play a central role in modern machine learning. We propose a novel approach to {`}vector similarity searching{'} over dense semantic representations of words and documents that can be deployed on top of traditional inverted-index-based fulltext engines, taking advantage of their robustness, stability, scalability and ubiquity. We show that this approach allows the indexing and querying of dense vectors in text domains. This opens up exciting avenues for major efficiency gains, along with simpler deployment, scaling and monitoring. The end result is a fast and scalable vector database with a tunable trade-off between vector search performance and quality, backed by a standard fulltext engine such as Elasticsearch. We empirically demonstrate its querying performance and quality by applying this solution to the task of semantic searching over a dense vector representation of the entire English Wikipedia. | |
| Tasks | Information Retrieval, Representation Learning |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2611/ |
| https://www.aclweb.org/anthology/W17-2611 | |
| PWC | https://paperswithcode.com/paper/semantic-vector-encoding-and-similarity |
| Repo | |
| Framework | |
Incorporating Uncertainty into Deep Learning for Spoken Language Assessment
| Title | Incorporating Uncertainty into Deep Learning for Spoken Language Assessment |
| Authors | Andrey Malinin, Anton Ragni, Kate Knill, Mark Gales |
| Abstract | There is a growing demand for automatic assessment of spoken English proficiency. These systems need to handle large variations in input data owing to the wide range of candidate skill levels and L1s, and errors from ASR. Some candidates will be a poor match to the training data set, undermining the validity of the predicted grade. For high stakes tests it is essential for such systems not only to grade well, but also to provide a measure of their uncertainty in their predictions, enabling rejection to human graders. Previous work examined Gaussian Process (GP) graders which, though successful, do not scale well with large data sets. Deep Neural Network (DNN) may also be used to provide uncertainty using Monte-Carlo Dropout (MCD). This paper proposes a novel method to yield uncertainty and compares it to GPs and DNNs with MCD. The proposed approach explicitly teaches a DNN to have low uncertainty on training data and high uncertainty on generated artificial data. On experiments conducted on data from the Business Language Testing Service (BULATS), the proposed approach is found to outperform GPs and DNNs with MCD in uncertainty-based rejection whilst achieving comparable grading performance. |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2008/ |
| https://www.aclweb.org/anthology/P17-2008 | |
| PWC | https://paperswithcode.com/paper/incorporating-uncertainty-into-deep-learning |
| Repo | |
| Framework | |
