Paper Group NANR 174
Trick Me If You Can: Adversarial Writing of Trivia Challenge Questions. Relation Induction in Word Embeddings Revisited. Sketching Method for Large Scale Combinatorial Inference. Structured Alignment Networks for Matching Sentences. Constructing an Annotated Corpus of Verbal MWEs for English. HarriGT: A Tool for Linking News to Science. Interpretab …
Trick Me If You Can: Adversarial Writing of Trivia Challenge Questions
Title | Trick Me If You Can: Adversarial Writing of Trivia Challenge Questions |
Authors | Eric Wallace, Jordan Boyd-Graber |
Abstract | Modern question answering systems have been touted as approaching human performance. However, existing question answering datasets are imperfect tests. Questions are written with humans in mind, not computers, and often do not properly expose model limitations. To address this, we develop an adversarial writing setting, where humans interact with trained models and try to break them. This annotation process yields a challenge set, which despite being easy for trivia players to answer, systematically stumps automated question answering systems. Diagnosing model errors on the evaluation data provides actionable insights to explore in developing robust and generalizable question answering systems. |
Tasks | Question Answering |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/P18-3018/ |
https://www.aclweb.org/anthology/P18-3018 | |
PWC | https://paperswithcode.com/paper/trick-me-if-you-can-adversarial-writing-of-1 |
Repo | |
Framework | |
Relation Induction in Word Embeddings Revisited
Title | Relation Induction in Word Embeddings Revisited |
Authors | Zied Bouraoui, Shoaib Jameel, Steven Schockaert |
Abstract | Given a set of instances of some relation, the relation induction task is to predict which other word pairs are likely to be related in the same way. While it is natural to use word embeddings for this task, standard approaches based on vector translations turn out to perform poorly. To address this issue, we propose two probabilistic relation induction models. The first model is based on translations, but uses Gaussians to explicitly model the variability of these translations and to encode soft constraints on the source and target words that may be chosen. In the second model, we use Bayesian linear regression to encode the assumption that there is a linear relationship between the vector representations of related words, which is considerably weaker than the assumption underlying translation based models. |
Tasks | Knowledge Base Completion, Word Embeddings |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1138/ |
https://www.aclweb.org/anthology/C18-1138 | |
PWC | https://paperswithcode.com/paper/relation-induction-in-word-embeddings |
Repo | |
Framework | |
Sketching Method for Large Scale Combinatorial Inference
Title | Sketching Method for Large Scale Combinatorial Inference |
Authors | Wei Sun, Junwei Lu, Han Liu |
Abstract | We present computationally efficient algorithms to test various combinatorial structures of large-scale graphical models. In order to test the hypotheses on their topological structures, we propose two adjacency matrix sketching frameworks: neighborhood sketching and subgraph sketching. The neighborhood sketching algorithm is proposed to test the connectivity of graphical models. This algorithm randomly subsamples vertices and conducts neighborhood regression and screening. The global sketching algorithm is proposed to test the topological properties requiring exponential computation complexity, especially testing the chromatic number and the maximum clique. This algorithm infers the corresponding property based on the sampled subgraph. Our algorithms are shown to substantially accelerate the computation of existing methods. We validate our theory and method through both synthetic simulations and a real application in neuroscience. |
Tasks | |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/8259-sketching-method-for-large-scale-combinatorial-inference |
http://papers.nips.cc/paper/8259-sketching-method-for-large-scale-combinatorial-inference.pdf | |
PWC | https://paperswithcode.com/paper/sketching-method-for-large-scale |
Repo | |
Framework | |
Structured Alignment Networks for Matching Sentences
Title | Structured Alignment Networks for Matching Sentences |
Authors | Yang Liu, Matt Gardner, Mirella Lapata |
Abstract | Many tasks in natural language processing involve comparing two sentences to compute some notion of relevance, entailment, or similarity. Typically this comparison is done either at the word level or at the sentence level, with no attempt to leverage the inherent structure of the sentence. When sentence structure is used for comparison, it is obtained during a non-differentiable pre-processing step, leading to propagation of errors. We introduce a model of structured alignments between sentences, showing how to compare two sentences by matching their latent structures. Using a structured attention mechanism, our model matches candidate spans in the first sentence to candidate spans in the second sentence, simultaneously discovering the tree structure of each sentence. Our model is fully differentiable and trained only on the matching objective. We evaluate this model on two tasks, natural entailment detection and answer sentence selection, and find that modeling latent tree structures results in superior performance. Analysis of the learned sentence structures shows they can reflect some syntactic phenomena. |
Tasks | Natural Language Inference, Question Answering |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1184/ |
https://www.aclweb.org/anthology/D18-1184 | |
PWC | https://paperswithcode.com/paper/structured-alignment-networks-for-matching |
Repo | |
Framework | |
Constructing an Annotated Corpus of Verbal MWEs for English
Title | Constructing an Annotated Corpus of Verbal MWEs for English |
Authors | Abigail Walsh, Claire Bonial, Kristina Geeraert, John P. McCrae, Nathan Schneider, Clarissa Somers |
Abstract | This paper describes the construction and annotation of a corpus of verbal MWEs for English, as part of the PARSEME Shared Task 1.1 on automatic identification of verbal MWEs. The criteria for corpus selection, the categories of MWEs used, and the training process are discussed, along with the particular issues that led to revisions in edition 1.1 of the annotation guidelines. Finally, an overview of the characteristics of the final annotated corpus is presented, as well as some discussion on inter-annotator agreement. |
Tasks | Word Alignment |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/W18-4921/ |
https://www.aclweb.org/anthology/W18-4921 | |
PWC | https://paperswithcode.com/paper/constructing-an-annotated-corpus-of-verbal |
Repo | |
Framework | |
HarriGT: A Tool for Linking News to Science
Title | HarriGT: A Tool for Linking News to Science |
Authors | James Ravenscroft, Am Clare, a, Maria Liakata |
Abstract | Being able to reliably link scientific works to the newspaper articles that discuss them could provide a breakthrough in the way we rationalise and measure the impact of science on our society. Linking these articles is challenging because the language used in the two domains is very different, and the gathering of online resources to align the two is a substantial information retrieval endeavour. We present HarriGT, a semi-automated tool for building corpora of news articles linked to the scientific papers that they discuss. Our aim is to facilitate future development of information-retrieval tools for newspaper/scientific work citation linking. HarriGT retrieves newspaper articles from an archive containing 17 years of UK web content. It also integrates with 3 large external citation networks, leveraging named entity extraction, and document classification to surface relevant examples of scientific literature to the user. We also provide a tuned candidate ranking algorithm to highlight potential links between scientific papers and newspaper articles to the user, in order of likelihood. HarriGT is provided as an open source tool (\url{http://harrigt.xyz}). |
Tasks | Document Classification, Entity Extraction, Information Retrieval |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/P18-4004/ |
https://www.aclweb.org/anthology/P18-4004 | |
PWC | https://paperswithcode.com/paper/harrigt-a-tool-for-linking-news-to-science |
Repo | |
Framework | |
Interpretable Classification via Supervised Variational Autoencoders and Differentiable Decision Trees
Title | Interpretable Classification via Supervised Variational Autoencoders and Differentiable Decision Trees |
Authors | Eleanor Quint, Garrett Wirka, Jacob Williams, Stephen Scott, N.V. Vinodchandran |
Abstract | As deep learning-based classifiers are increasingly adopted in real-world applications, the importance of understanding how a particular label is chosen grows. Single decision trees are an example of a simple, interpretable classifier, but are unsuitable for use with complex, high-dimensional data. On the other hand, the variational autoencoder (VAE) is designed to learn a factored, low-dimensional representation of data, but typically encodes high-likelihood data in an intrinsically non-separable way. We introduce the differentiable decision tree (DDT) as a modular component of deep networks and a simple, differentiable loss function that allows for end-to-end optimization of a deep network to compress high-dimensional data for classification by a single decision tree. We also explore the power of labeled data in a supervised VAE (SVAE) with a Gaussian mixture prior, which leverages label information to produce a high-quality generative model with improved bounds on log-likelihood. We combine the SVAE with the DDT to get our classifier+VAE (C+VAE), which is competitive in both classification error and log-likelihood, despite optimizing both simultaneously and using a very simple encoder/decoder architecture. |
Tasks | |
Published | 2018-01-01 |
URL | https://openreview.net/forum?id=rJhR_pxCZ |
https://openreview.net/pdf?id=rJhR_pxCZ | |
PWC | https://paperswithcode.com/paper/interpretable-classification-via-supervised |
Repo | |
Framework | |
Phonological Features for Morphological Inflection
Title | Phonological Features for Morphological Inflection |
Authors | Adam Wiemerslage, Miikka Silfverberg, Mans Hulden |
Abstract | Modeling morphological inflection is an important task in Natural Language Processing. In contrast to earlier work that has largely used orthographic representations, we experiment with this task in a phonetic character space, representing inputs as either IPA segments or bundles of phonological distinctive features. We show that both of these inputs, somewhat counterintuitively, achieve similar accuracies on morphological inflection, slightly lower than orthographic models. We conclude that providing detailed phonological representations is largely redundant when compared to IPA segments, and that articulatory distinctions relevant for word inflection are already latently present in the distributional properties of many graphemic writing systems. |
Tasks | Machine Translation, Morphological Analysis, Morphological Inflection, Transfer Learning |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/W18-5818/ |
https://www.aclweb.org/anthology/W18-5818 | |
PWC | https://paperswithcode.com/paper/phonological-features-for-morphological |
Repo | |
Framework | |
Extracting Morphophonology from Small Corpora
Title | Extracting Morphophonology from Small Corpora |
Authors | Marina Ermolaeva |
Abstract | Probabilistic approaches have proven themselves well in learning phonological structure. In contrast, theoretical linguistics usually works with deterministic generalizations. The goal of this paper is to explore possible interactions between information-theoretic methods and deterministic linguistic knowledge and to examine some ways in which both can be used in tandem to extract phonological and morphophonological patterns from a small annotated dataset. Local and nonlocal processes in Mishar Tatar (Turkic/Kipchak) are examined as a case study. |
Tasks | |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/W18-5819/ |
https://www.aclweb.org/anthology/W18-5819 | |
PWC | https://paperswithcode.com/paper/extracting-morphophonology-from-small-corpora |
Repo | |
Framework | |
Jiangnan at SemEval-2018 Task 11: Deep Neural Network with Attention Method for Machine Comprehension Task
Title | Jiangnan at SemEval-2018 Task 11: Deep Neural Network with Attention Method for Machine Comprehension Task |
Authors | Jiangnan Xia |
Abstract | This paper describes our submission for the International Workshop on Semantic Evaluation (SemEval-2018) shared task 11{–} Machine Comprehension using Commonsense Knowledge (Ostermann et al., 2018b). We use a deep neural network model to choose the correct answer from the candidate answers pair when the document and question are given. The interactions between document, question and answers are modeled by attention mechanism and a variety of manual features are used to improve model performance. We also use CoVe (McCann et al., 2017) as an external source of knowledge which is not mentioned in the document. As a result, our system achieves 80.91{%} accuracy on the test data, which is on the third place of the leaderboard. |
Tasks | Machine Reading Comprehension, Named Entity Recognition, Question Answering, Reading Comprehension |
Published | 2018-06-01 |
URL | https://www.aclweb.org/anthology/S18-1178/ |
https://www.aclweb.org/anthology/S18-1178 | |
PWC | https://paperswithcode.com/paper/jiangnan-at-semeval-2018-task-11-deep-neural |
Repo | |
Framework | |
Annotating Measurable Quantitative Informationin Language: for an ISO Standard
Title | Annotating Measurable Quantitative Informationin Language: for an ISO Standard |
Authors | Tianyong Hao, Haotai Wang, Xinyu Cao, Kiyong Lee |
Abstract | |
Tasks | |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/W18-4708/ |
https://www.aclweb.org/anthology/W18-4708 | |
PWC | https://paperswithcode.com/paper/annotating-measurable-quantitative |
Repo | |
Framework | |
NLP Web Services for Resource-Scarce Languages
Title | NLP Web Services for Resource-Scarce Languages |
Authors | Martin Puttkammer, Roald Eiselen, Justin Hocking, Frederik Koen |
Abstract | In this paper, we present a project where existing text-based core technologies were ported to Java-based web services from various architectures. These technologies were developed over a period of eight years through various government funded projects for 10 resource-scarce languages spoken in South Africa. We describe the API and a simple web front-end capable of completing various predefined tasks. |
Tasks | |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/P18-4008/ |
https://www.aclweb.org/anthology/P18-4008 | |
PWC | https://paperswithcode.com/paper/nlp-web-services-for-resource-scarce |
Repo | |
Framework | |
Stance-Taking in Topics Extracted from Vaccine-Related Tweets and Discussion Forum Posts
Title | Stance-Taking in Topics Extracted from Vaccine-Related Tweets and Discussion Forum Posts |
Authors | Maria Skeppstedt, Manfred Stede, Andreas Kerren |
Abstract | The occurrence of stance-taking towards vaccination was measured in documents extracted by topic modelling from two different corpora, one discussion forum corpus and one tweet corpus. For some of the topics extracted, their most closely associated documents contained a proportion of vaccine stance-taking texts that exceeded the corpus average by a large margin. These extracted document sets would, therefore, form a useful resource in a process for computer-assisted analysis of argumentation on the subject of vaccination. |
Tasks | |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/W18-5902/ |
https://www.aclweb.org/anthology/W18-5902 | |
PWC | https://paperswithcode.com/paper/stance-taking-in-topics-extracted-from |
Repo | |
Framework | |
Answer-focused and Position-aware Neural Question Generation
Title | Answer-focused and Position-aware Neural Question Generation |
Authors | Xingwu Sun, Jing Liu, Yajuan Lyu, Wei He, Yanjun Ma, Shi Wang |
Abstract | In this paper, we focus on the problem of question generation (QG). Recent neural network-based approaches employ the sequence-to-sequence model which takes an answer and its context as input and generates a relevant question as output. However, we observe two major issues with these approaches: (1) The generated interrogative words (or question words) do not match the answer type. (2) The model copies the context words that are far from and irrelevant to the answer, instead of the words that are close and relevant to the answer. To address these two issues, we propose an answer-focused and position-aware neural question generation model. (1) By answer-focused, we mean that we explicitly model question word generation by incorporating the answer embedding, which can help generate an interrogative word matching the answer type. (2) By position-aware, we mean that we model the relative distance between the context words and the answer. Hence the model can be aware of the position of the context words when copying them to generate a question. We conduct extensive experiments to examine the effectiveness of our model. The experimental results show that our model significantly improves the baseline and outperforms the state-of-the-art system. |
Tasks | Machine Reading Comprehension, Question Answering, Question Generation, Reading Comprehension |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/D18-1427/ |
https://www.aclweb.org/anthology/D18-1427 | |
PWC | https://paperswithcode.com/paper/answer-focused-and-position-aware-neural |
Repo | |
Framework | |
未登錄詞之向量表示法模型於中文機器閱讀理解之應用 (An OOV Word Embedding Framework for Chinese Machine Reading Comprehension) [In Chinese]
Title | 未登錄詞之向量表示法模型於中文機器閱讀理解之應用 (An OOV Word Embedding Framework for Chinese Machine Reading Comprehension) [In Chinese] |
Authors | Shang-Bao Luo, Ching-Hsien Lee, Kuan-Yu Chen |
Abstract | |
Tasks | Machine Reading Comprehension, Reading Comprehension |
Published | 2018-10-01 |
URL | https://www.aclweb.org/anthology/O18-1014/ |
https://www.aclweb.org/anthology/O18-1014 | |
PWC | https://paperswithcode.com/paper/aceea1aee-co3-a14a-a-eecea1c-an-oov-word |
Repo | |
Framework | |