Paper Group NANR 60
Gender as a Variable in Natural-Language Processing: Ethical Considerations. A Polynomial-Time Dynamic Programming Algorithm for Phrase-Based Decoding with a Fixed Distortion Limit. Propbank Annotation of Danish Noun Frames. Neural Sequence-to-sequence Learning of Internal Word Structure. Using Complex Argumentative Interactions to Reconstruct the …
Gender as a Variable in Natural-Language Processing: Ethical Considerations
| Title | Gender as a Variable in Natural-Language Processing: Ethical Considerations |
| Authors | Brian Larson |
| Abstract | Researchers and practitioners in natural-language processing (NLP) and related fields should attend to ethical principles in study design, ascription of categories/variables to study participants, and reporting of findings or results. This paper discusses theoretical and ethical frameworks for using gender as a variable in NLP studies and proposes four guidelines for researchers and practitioners. The principles outlined here should guide practitioners, researchers, and peer reviewers, and they may be applicable to other social categories, such as race, applied to human beings connected to NLP research. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1601/ |
| https://www.aclweb.org/anthology/W17-1601 | |
| PWC | https://paperswithcode.com/paper/gender-as-a-variable-in-natural-language |
| Repo | |
| Framework | |
A Polynomial-Time Dynamic Programming Algorithm for Phrase-Based Decoding with a Fixed Distortion Limit
| Title | A Polynomial-Time Dynamic Programming Algorithm for Phrase-Based Decoding with a Fixed Distortion Limit |
| Authors | Yin-Wen Chang, Michael Collins |
| Abstract | Decoding of phrase-based translation models in the general case is known to be NP-complete, by a reduction from the traveling salesman problem (Knight, 1999). In practice, phrase-based systems often impose a hard distortion limit that limits the movement of phrases during translation. However, the impact on complexity after imposing such a constraint is not well studied. In this paper, we describe a dynamic programming algorithm for phrase-based decoding with a fixed distortion limit. The runtime of the algorithm is O(nd!lhd+1) where n is the sentence length, d is the distortion limit, l is a bound on the number of phrases starting at any position in the sentence, and h is related to the maximum number of target language translations for any source word. The algorithm makes use of a novel representation that gives a new perspective on decoding of phrase-based models. |
| Tasks | Machine Translation |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/Q17-1005/ |
| https://www.aclweb.org/anthology/Q17-1005 | |
| PWC | https://paperswithcode.com/paper/a-polynomial-time-dynamic-programming |
| Repo | |
| Framework | |
Propbank Annotation of Danish Noun Frames
| Title | Propbank Annotation of Danish Noun Frames |
| Authors | Eckhard Bick |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6902/ |
| https://www.aclweb.org/anthology/W17-6902 | |
| PWC | https://paperswithcode.com/paper/propbank-annotation-of-danish-noun-frames |
| Repo | |
| Framework | |
Neural Sequence-to-sequence Learning of Internal Word Structure
| Title | Neural Sequence-to-sequence Learning of Internal Word Structure |
| Authors | Tatyana Ruzsics, Tanja Samard{\v{z}}i{'c} |
| Abstract | Learning internal word structure has recently been recognized as an important step in various multilingual processing tasks and in theoretical language comparison. In this paper, we present a neural encoder-decoder model for learning canonical morphological segmentation. Our model combines character-level sequence-to-sequence transformation with a language model over canonical segments. We obtain up to 4{%} improvement over a strong character-level encoder-decoder baseline for three languages. Our model outperforms the previous state-of-the-art for two languages, while eliminating the need for external resources such as large dictionaries. Finally, by comparing the performance of encoder-decoder and classical statistical machine translation systems trained with and without corpus counts, we show that including corpus counts is beneficial to both approaches. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-1020/ |
| https://www.aclweb.org/anthology/K17-1020 | |
| PWC | https://paperswithcode.com/paper/neural-sequence-to-sequence-learning-of |
| Repo | |
| Framework | |
Using Complex Argumentative Interactions to Reconstruct the Argumentative Structure of Large-Scale Debates
| Title | Using Complex Argumentative Interactions to Reconstruct the Argumentative Structure of Large-Scale Debates |
| Authors | John Lawrence, Chris Reed |
| Abstract | In this paper we consider the insights that can be gained by considering large scale argument networks and the complex interactions between their constituent propositions. We investigate metrics for analysing properties of these networks, illustrating these using a corpus of arguments taken from the 2016 US Presidential Debates. We present techniques for determining these features directly from natural language text and show that there is a strong correlation between these automatically identified features and the argumentative structure contained within the text. Finally, we combine these metrics with argument mining techniques and show how the identification of argumentative relations can be improved by considering the larger context in which they occur. |
| Tasks | Argument Mining, Decision Making |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5114/ |
| https://www.aclweb.org/anthology/W17-5114 | |
| PWC | https://paperswithcode.com/paper/using-complex-argumentative-interactions-to |
| Repo | |
| Framework | |
Using Target-side Monolingual Data for Neural Machine Translation through Multi-task Learning
| Title | Using Target-side Monolingual Data for Neural Machine Translation through Multi-task Learning |
| Authors | Tobias Domhan, Felix Hieber |
| Abstract | The performance of Neural Machine Translation (NMT) models relies heavily on the availability of sufficient amounts of parallel data, and an efficient and effective way of leveraging the vastly available amounts of monolingual data has yet to be found. We propose to modify the decoder in a neural sequence-to-sequence model to enable multi-task learning for two strongly related tasks: target-side language modeling and translation. The decoder predicts the next target word through two channels, a target-side language model on the lowest layer, and an attentional recurrent model which is conditioned on the source representation. This architecture allows joint training on both large amounts of monolingual and moderate amounts of bilingual data to improve NMT performance. Initial results in the news domain for three language pairs show moderate but consistent improvements over a baseline trained on bilingual data only. |
| Tasks | Language Modelling, Machine Translation, Multi-Task Learning |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1158/ |
| https://www.aclweb.org/anthology/D17-1158 | |
| PWC | https://paperswithcode.com/paper/using-target-side-monolingual-data-for-neural |
| Repo | |
| Framework | |
Jejueo talking dictionary: A collaborative online database for language revitalization
| Title | Jejueo talking dictionary: A collaborative online database for language revitalization |
| Authors | Moira Saltzman |
| Abstract | |
| Tasks | Language Acquisition |
| Published | 2017-03-01 |
| URL | https://www.aclweb.org/anthology/W17-0117/ |
| https://www.aclweb.org/anthology/W17-0117 | |
| PWC | https://paperswithcode.com/paper/jejueo-talking-dictionary-a-collaborative |
| Repo | |
| Framework | |
Story Comprehension for Predicting What Happens Next
| Title | Story Comprehension for Predicting What Happens Next |
| Authors | Snigdha Chaturvedi, Haoruo Peng, Dan Roth |
| Abstract | Automatic story comprehension is a fundamental challenge in Natural Language Understanding, and can enable computers to learn about social norms, human behavior and commonsense. In this paper, we present a story comprehension model that explores three distinct semantic aspects: (i) the sequence of events described in the story, (ii) its emotional trajectory, and (iii) its plot consistency. We judge the model{'}s understanding of real-world stories by inquiring if, like humans, it can develop an expectation of what will happen next in a given story. Specifically, we use it to predict the correct ending of a given short story from possible alternatives. The model uses a hidden variable to weigh the semantic aspects in the context of the story. Our experiments demonstrate the potential of our approach to characterize these semantic aspects, and the strength of the hidden variable based approach. The model outperforms the state-of-the-art approaches and achieves best results on a publicly available dataset. |
| Tasks | Common Sense Reasoning, Reading Comprehension, Speaker Identification, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1168/ |
| https://www.aclweb.org/anthology/D17-1168 | |
| PWC | https://paperswithcode.com/paper/story-comprehension-for-predicting-what |
| Repo | |
| Framework | |
TakeLab at SemEval-2017 Task 4: Recent Deaths and the Power of Nostalgia in Sentiment Analysis in Twitter
| Title | TakeLab at SemEval-2017 Task 4: Recent Deaths and the Power of Nostalgia in Sentiment Analysis in Twitter |
| Authors | David Lozi{'c}, Doria {\v{S}}ari{'c}, Ivan Toki{'c}, Zoran Medi{'c}, Jan {\v{S}}najder |
| Abstract | This paper describes the system we submitted to SemEval-2017 Task 4 (Sentiment Analysis in Twitter), specifically subtasks A, B, and D. Our main focus was topic-based message polarity classification on a two-point scale (subtask B). The system we submitted uses a Support Vector Machine classifier with rich set of features, ranging from standard to more creative, task-specific features, including a series of rating-based features as well as features that account for sentimental reminiscence of past topics and deceased famous people. Our system ranked 14th out of 39 submissions in subtask A, 5th out of 24 submissions in subtask B, and 3rd out of 16 submissions in subtask D. |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2132/ |
| https://www.aclweb.org/anthology/S17-2132 | |
| PWC | https://paperswithcode.com/paper/takelab-at-semeval-2017-task-4-recent-deaths |
| Repo | |
| Framework | |
Efficient Discontinuous Phrase-Structure Parsing via the Generalized Maximum Spanning Arborescence
| Title | Efficient Discontinuous Phrase-Structure Parsing via the Generalized Maximum Spanning Arborescence |
| Authors | Caio Corro, Joseph Le Roux, Mathieu Lacroix |
| Abstract | We present a new method for the joint task of tagging and non-projective dependency parsing. We demonstrate its usefulness with an application to discontinuous phrase-structure parsing where decoding lexicalized spines and syntactic derivations is performed jointly. The main contributions of this paper are (1) a reduction from joint tagging and non-projective dependency parsing to the Generalized Maximum Spanning Arborescence problem, and (2) a novel decoding algorithm for this problem through Lagrangian relaxation. We evaluate this model and obtain state-of-the-art results despite strong independence assumptions. |
| Tasks | Dependency Parsing |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1172/ |
| https://www.aclweb.org/anthology/D17-1172 | |
| PWC | https://paperswithcode.com/paper/efficient-discontinuous-phrase-structure |
| Repo | |
| Framework | |
T"ubingen system in VarDial 2017 shared task: experiments with language identification and cross-lingual parsing
| Title | T"ubingen system in VarDial 2017 shared task: experiments with language identification and cross-lingual parsing |
| Authors | {\c{C}}a{\u{g}}r{\i} {\c{C}}{"o}ltekin, Taraka Rama |
| Abstract | This paper describes our systems and results on VarDial 2017 shared tasks. Besides three language/dialect discrimination tasks, we also participated in the cross-lingual dependency parsing (CLP) task using a simple methodology which we also briefly describe in this paper. For all the discrimination tasks, we used linear SVMs with character and word features. The system achieves competitive results among other systems in the shared task. We also report additional experiments with neural network models. The performance of neural network models was close but always below the corresponding SVM classifiers in the discrimination tasks. For the cross-lingual parsing task, we experimented with an approach based on automatically translating the source treebank to the target language, and training a parser on the translated treebank. We used off-the-shelf tools for both translation and parsing. Despite achieving better-than-baseline results, our scores in CLP tasks were substantially lower than the scores of the other participants. |
| Tasks | Dependency Parsing, Language Identification |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1218/ |
| https://www.aclweb.org/anthology/W17-1218 | |
| PWC | https://paperswithcode.com/paper/ta14bingen-system-in-vardial-2017-shared-task |
| Repo | |
| Framework | |
Neural Discontinuous Constituency Parsing
| Title | Neural Discontinuous Constituency Parsing |
| Authors | Milo{\v{s}} Stanojevi{'c}, Raquel G. Alhama |
| Abstract | One of the most pressing issues in discontinuous constituency transition-based parsing is that the relevant information for parsing decisions could be located in any part of the stack or the buffer. In this paper, we propose a solution to this problem by replacing the structured perceptron model with a recursive neural model that computes a global representation of the configuration, therefore allowing even the most remote parts of the configuration to influence the parsing decisions. We also provide a detailed analysis of how this representation should be built out of sub-representations of its core elements (words, trees and stack). Additionally, we investigate how different types of swap oracles influence the results. Our model is the first neural discontinuous constituency parser, and it outperforms all the previously published models on three out of four datasets while on the fourth it obtains second place by a tiny difference. |
| Tasks | Constituency Parsing |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1174/ |
| https://www.aclweb.org/anthology/D17-1174 | |
| PWC | https://paperswithcode.com/paper/neural-discontinuous-constituency-parsing |
| Repo | |
| Framework | |
High Dimensional Bayesian Optimization with Elastic Gaussian Process
| Title | High Dimensional Bayesian Optimization with Elastic Gaussian Process |
| Authors | Santu Rana, Cheng Li, Sunil Gupta, Vu Nguyen, Svetha Venkatesh |
| Abstract | Bayesian optimization is an efficient way to optimize expensive black-box functions such as designing a new product with highest quality or hyperparameter tuning of a machine learning algorithm. However, it has a serious limitation when the parameter space is high-dimensional as Bayesian optimization crucially depends on solving a global optimization of a surrogate utility function in the same sized dimensions. The surrogate utility function, known commonly as acquisition function is a continuous function but can be extremely sharp at high dimension - having only a few peaks marooned in a large terrain of almost flat surface. Global optimization algorithms such as DIRECT are infeasible at higher dimensions and gradient-dependent methods cannot move if initialized in the flat terrain. We propose an algorithm that enables local gradient-dependent algorithms to move through the flat terrain by using a sequence of gross-to-finer Gaussian process priors on the objective function as we leverage two underlying facts - a) there exists a large enough length-scales for which the acquisition function can be made to have a significant gradient at any location in the parameter space, and b) the extrema of the consecutive acquisition functions are close although they are different only due to a small difference in the length-scales. Theoretical guarantees are provided and experiments clearly demonstrate the utility of the proposed method at high dimension using both benchmark test functions and real-world case studies. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=554 |
| http://proceedings.mlr.press/v70/rana17a/rana17a.pdf | |
| PWC | https://paperswithcode.com/paper/high-dimensional-bayesian-optimization-with |
| Repo | |
| Framework | |
TAG Parsing with Neural Networks and Vector Representations of Supertags
| Title | TAG Parsing with Neural Networks and Vector Representations of Supertags |
| Authors | Jungo Kasai, Bob Frank, Tom McCoy, Owen Rambow, Alexis Nasr |
| Abstract | We present supertagging-based models for Tree Adjoining Grammar parsing that use neural network architectures and dense vector representation of supertags (elementary trees) to achieve state-of-the-art performance in unlabeled and labeled attachment scores. The shift-reduce parsing model eschews lexical information entirely, and uses only the 1-best supertags to parse a sentence, providing further support for the claim that supertagging is {``}almost parsing.{''} We demonstrate that the embedding vector representations the parser induces for supertags possess linguistically interpretable structure, supporting analogies between grammatical structures like those familiar from recent work in distributional semantics. This dense representation of supertags overcomes the drawbacks for statistical models of TAG as compared to CCG parsing, raising the possibility that TAG is a viable alternative for NLP tasks that require the assignment of richer structural descriptions to sentences. | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1180/ |
| https://www.aclweb.org/anthology/D17-1180 | |
| PWC | https://paperswithcode.com/paper/tag-parsing-with-neural-networks-and-vector |
| Repo | |
| Framework | |
End-to-End Neural Relation Extraction with Global Optimization
| Title | End-to-End Neural Relation Extraction with Global Optimization |
| Authors | Meishan Zhang, Yue Zhang, Guohong Fu |
| Abstract | Neural networks have shown promising results for relation extraction. State-of-the-art models cast the task as an end-to-end problem, solved incrementally using a local classifier. Yet previous work using statistical models have demonstrated that global optimization can achieve better performances compared to local classification. We build a globally optimized neural model for end-to-end relation extraction, proposing novel LSTM features in order to better learn context representations. In addition, we present a novel method to integrate syntactic information to facilitate global learning, yet requiring little background on syntactic grammars thus being easy to extend. Experimental results show that our proposed model is highly effective, achieving the best performances on two standard benchmarks. |
| Tasks | Relation Extraction, Representation Learning, Structured Prediction |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1182/ |
| https://www.aclweb.org/anthology/D17-1182 | |
| PWC | https://paperswithcode.com/paper/end-to-end-neural-relation-extraction-with |
| Repo | |
| Framework | |
