Paper Group NANR 25
Sentence Embedding for Neural Machine Translation Domain Adaptation. Semantics-Enhanced Task-Oriented Dialogue Translation: A Case Study on Hotel Booking. ADoCS: Automatic Designer of Conference Schedules. Efficient Benchmarking of NLP APIs using Multi-armed Bandits. Goal-Oriented Design for Ethical Machine Learning and NLP. TDB 1.1: Extensions on …
Sentence Embedding for Neural Machine Translation Domain Adaptation
| Title | Sentence Embedding for Neural Machine Translation Domain Adaptation |
| Authors | Rui Wang, Andrew Finch, Masao Utiyama, Eiichiro Sumita |
| Abstract | Although new corpora are becoming increasingly available for machine translation, only those that belong to the same or similar domains are typically able to improve translation performance. Recently Neural Machine Translation (NMT) has become prominent in the field. However, most of the existing domain adaptation methods only focus on phrase-based machine translation. In this paper, we exploit the NMT{'}s internal embedding of the source sentence and use the sentence embedding similarity to select the sentences which are close to in-domain data. The empirical adaptation results on the IWSLT English-French and NIST Chinese-English tasks show that the proposed methods can substantially improve NMT performance by 2.4-9.0 BLEU points, outperforming the existing state-of-the-art baseline by 2.3-4.5 BLEU points. |
| Tasks | Domain Adaptation, Language Modelling, Machine Translation, Sentence Embedding |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2089/ |
| https://www.aclweb.org/anthology/P17-2089 | |
| PWC | https://paperswithcode.com/paper/sentence-embedding-for-neural-machine |
| Repo | |
| Framework | |
Semantics-Enhanced Task-Oriented Dialogue Translation: A Case Study on Hotel Booking
| Title | Semantics-Enhanced Task-Oriented Dialogue Translation: A Case Study on Hotel Booking |
| Authors | Longyue Wang, Jinhua Du, Liangyou Li, Zhaopeng Tu, Andy Way, Qun Liu |
| Abstract | We showcase TODAY, a semantics-enhanced task-oriented dialogue translation system, whose novelties are: (i) task-oriented named entity (NE) definition and a hybrid strategy for NE recognition and translation; and (ii) a novel grounded semantic method for dialogue understanding and task-order management. TODAY is a case-study demo which can efficiently and accurately assist customers and agents in different languages to reach an agreement in a dialogue for the hotel booking. |
| Tasks | Dialogue Understanding, Machine Translation, Named Entity Recognition |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-3009/ |
| https://www.aclweb.org/anthology/I17-3009 | |
| PWC | https://paperswithcode.com/paper/semantics-enhanced-task-oriented-dialogue |
| Repo | |
| Framework | |
ADoCS: Automatic Designer of Conference Schedules
| Title | ADoCS: Automatic Designer of Conference Schedules |
| Authors | Diego Fern Vallejo Huanga, o, Paulina Adriana Morillo Alc{'\i}var, C{`e}sar Ferri Ram{'\i}rez |
| Abstract | Distributing papers into sessions in scientific conferences is a task consisting in grouping papers with common topics and considering the size restrictions imposed by the conference schedule. This problem can be seen as a semi-supervised clustering of scientific papers based on their features. This paper presents a web tool called ADoCS that solves the problem of configuring conference schedules by an automatic clustering of articles by similarity using a new algorithm considering size constraints. |
| Tasks | Information Retrieval, Tokenization |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-3011/ |
| https://www.aclweb.org/anthology/E17-3011 | |
| PWC | https://paperswithcode.com/paper/adocs-automatic-designer-of-conference |
| Repo | |
| Framework | |
Efficient Benchmarking of NLP APIs using Multi-armed Bandits
| Title | Efficient Benchmarking of NLP APIs using Multi-armed Bandits |
| Authors | Gholamreza Haffari, Tuan Dung Tran, Mark Carman |
| Abstract | Comparing NLP systems to select the best one for a task of interest, such as named entity recognition, is critical for practitioners and researchers. A rigorous approach involves setting up a hypothesis testing scenario using the performance of the systems on query documents. However, often the hypothesis testing approach needs to send a lot of document queries to the systems, which can be problematic. In this paper, we present an effective alternative based on the multi-armed bandit (MAB). We propose a hierarchical generative model to represent the uncertainty in the performance measures of the competing systems, to be used by Thompson Sampling to solve the resulting MAB. Experimental results on both synthetic and real data show that our approach requires significantly fewer queries compared to the standard benchmarking technique to identify the best system according to F-measure. |
| Tasks | Multi-Armed Bandits, Named Entity Recognition |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1039/ |
| https://www.aclweb.org/anthology/E17-1039 | |
| PWC | https://paperswithcode.com/paper/efficient-benchmarking-of-nlp-apis-using |
| Repo | |
| Framework | |
Goal-Oriented Design for Ethical Machine Learning and NLP
| Title | Goal-Oriented Design for Ethical Machine Learning and NLP |
| Authors | Tyler Schnoebelen |
| Abstract | The argument made in this paper is that to act ethically in machine learning and NLP requires focusing on goals. NLP projects are often classificatory systems that deal with human subjects, which means that goals from people affected by the systems should be included. The paper takes as its core example a model that detects criminality, showing the problems of training data, categories, and outcomes. The paper is oriented to the kinds of critiques on power and the reproduction of inequality that are found in social theory, but it also includes concrete suggestions on how to put goal-oriented design into practice. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1611/ |
| https://www.aclweb.org/anthology/W17-1611 | |
| PWC | https://paperswithcode.com/paper/goal-oriented-design-for-ethical-machine |
| Repo | |
| Framework | |
TDB 1.1: Extensions on Turkish Discourse Bank
| Title | TDB 1.1: Extensions on Turkish Discourse Bank |
| Authors | Deniz Zeyrek, Murathan Kurfal{\i} |
| Abstract | This paper presents the recent developments on Turkish Discourse Bank (TDB). First, the resource is summarized and an evaluation is presented. Then, TDB 1.1, i.e. enrichments on 10{%} of the corpus are described (namely, senses for explicit discourse connectives, and new annotations for three discourse relation types - implicit relations, entity relations and alternative lexicalizations). The method of annotation is explained and the data are evaluated. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-0809/ |
| https://www.aclweb.org/anthology/W17-0809 | |
| PWC | https://paperswithcode.com/paper/tdb-11-extensions-on-turkish-discourse-bank |
| Repo | |
| Framework | |
Action Centered Contextual Bandits
| Title | Action Centered Contextual Bandits |
| Authors | Kristjan Greenewald, Ambuj Tewari, Susan Murphy, Predag Klasnja |
| Abstract | Contextual bandits have become popular as they offer a middle ground between very simple approaches based on multi-armed bandits and very complex approaches using the full power of reinforcement learning. They have demonstrated success in web applications and have a rich body of associated theoretical guarantees. Linear models are well understood theoretically and preferred by practitioners because they are not only easily interpretable but also simple to implement and debug. Furthermore, if the linear model is true, we get very strong performance guarantees. Unfortunately, in emerging applications in mobile health, the time-invariant linear model assumption is untenable. We provide an extension of the linear model for contextual bandits that has two parts: baseline reward and treatment effect. We allow the former to be complex but keep the latter simple. We argue that this model is plausible for mobile health applications. At the same time, it leads to algorithms with strong performance guarantees as in the linear model setting, while still allowing for complex nonlinear baseline modeling. Our theory is supported by experiments on data gathered in a recently concluded mobile health study. |
| Tasks | Multi-Armed Bandits |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7179-action-centered-contextual-bandits |
| http://papers.nips.cc/paper/7179-action-centered-contextual-bandits.pdf | |
| PWC | https://paperswithcode.com/paper/action-centered-contextual-bandits |
| Repo | |
| Framework | |
End-to-End Non-Factoid Question Answering with an Interactive Visualization of Neural Attention Weights
| Title | End-to-End Non-Factoid Question Answering with an Interactive Visualization of Neural Attention Weights |
| Authors | Andreas R{"u}ckl{'e}, Iryna Gurevych |
| Abstract | |
| Tasks | Answer Selection, Machine Translation, Question Answering |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-4004/ |
| https://www.aclweb.org/anthology/P17-4004 | |
| PWC | https://paperswithcode.com/paper/end-to-end-non-factoid-question-answering |
| Repo | |
| Framework | |
Handling Cold-Start Problem in Review Spam Detection by Jointly Embedding Texts and Behaviors
| Title | Handling Cold-Start Problem in Review Spam Detection by Jointly Embedding Texts and Behaviors |
| Authors | Xuepeng Wang, Kang Liu, Jun Zhao |
| Abstract | Solving cold-start problem in review spam detection is an urgent and significant task. It can help the on-line review websites to relieve the damage of spammers in time, but has never been investigated by previous work. This paper proposes a novel neural network model to detect review spam for cold-start problem, by learning to represent the new reviewers{'} review with jointly embedded textual and behavioral information. Experimental results prove the proposed model achieves an effective performance and possesses preferable domain-adaptability. It is also applicable to a large scale dataset in an unsupervised way. |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1034/ |
| https://www.aclweb.org/anthology/P17-1034 | |
| PWC | https://paperswithcode.com/paper/handling-cold-start-problem-in-review-spam |
| Repo | |
| Framework | |
Book Review: Biomedical Natural Language Processing by Kevin Bretonnel Cohen and Dina Demner-Fushman
| Title | Book Review: Biomedical Natural Language Processing by Kevin Bretonnel Cohen and Dina Demner-Fushman |
| Authors | Jin-Dong Kim |
| Abstract | |
| Tasks | Named Entity Recognition, Relation Extraction |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/J17-1007/ |
| https://www.aclweb.org/anthology/J17-1007 | |
| PWC | https://paperswithcode.com/paper/book-review-biomedical-natural-language |
| Repo | |
| Framework | |
Transliterated Mobile Keyboard Input via Weighted Finite-State Transducers
| Title | Transliterated Mobile Keyboard Input via Weighted Finite-State Transducers |
| Authors | Lars Hellsten, Brian Roark, Prasoon Goyal, Cyril Allauzen, Fran{\c{c}}oise Beaufays, Tom Ouyang, Michael Riley, David Rybach |
| Abstract | |
| Tasks | Language Modelling, Optical Character Recognition, Speech Recognition, Transliteration |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4002/ |
| https://www.aclweb.org/anthology/W17-4002 | |
| PWC | https://paperswithcode.com/paper/transliterated-mobile-keyboard-input-via |
| Repo | |
| Framework | |
Integrated Learning of Dialog Strategies and Semantic Parsing
| Title | Integrated Learning of Dialog Strategies and Semantic Parsing |
| Authors | Aishwarya Padmakumar, Jesse Thomason, Raymond J. Mooney |
| Abstract | Natural language understanding and dialog management are two integral components of interactive dialog systems. Previous research has used machine learning techniques to individually optimize these components, with different forms of direct and indirect supervision. We present an approach to integrate the learning of both a dialog strategy using reinforcement learning, and a semantic parser for robust natural language understanding, using only natural dialog interaction for supervision. Experimental results on a simulated task of robot instruction demonstrate that joint learning of both components improves dialog performance over learning either of these components alone. |
| Tasks | Semantic Parsing |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1052/ |
| https://www.aclweb.org/anthology/E17-1052 | |
| PWC | https://paperswithcode.com/paper/integrated-learning-of-dialog-strategies-and |
| Repo | |
| Framework | |
Data Augmentation for Morphological Reinflection
| Title | Data Augmentation for Morphological Reinflection |
| Authors | Miikka Silfverberg, Adam Wiemerslage, Ling Liu, Lingshuang Jack Mao |
| Abstract | |
| Tasks | Data Augmentation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-2010/ |
| https://www.aclweb.org/anthology/K17-2010 | |
| PWC | https://paperswithcode.com/paper/data-augmentation-for-morphological |
| Repo | |
| Framework | |
The LMU System for the CoNLL-SIGMORPHON 2017 Shared Task on Universal Morphological Reinflection
| Title | The LMU System for the CoNLL-SIGMORPHON 2017 Shared Task on Universal Morphological Reinflection |
| Authors | Katharina Kann, Hinrich Sch{"u}tze |
| Abstract | |
| Tasks | Data Augmentation, Domain Adaptation, Morphological Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-2003/ |
| https://www.aclweb.org/anthology/K17-2003 | |
| PWC | https://paperswithcode.com/paper/the-lmu-system-for-the-conll-sigmorphon-2017 |
| Repo | |
| Framework | |
Linguistically Rich Vector Representations of Supertags for TAG Parsing
| Title | Linguistically Rich Vector Representations of Supertags for TAG Parsing |
| Authors | Dan Friedman, Jungo Kasai, R. Thomas McCoy, Robert Frank, Forrest Davis, Owen Rambow |
| Abstract | |
| Tasks | CCG Supertagging |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6213/ |
| https://www.aclweb.org/anthology/W17-6213 | |
| PWC | https://paperswithcode.com/paper/linguistically-rich-vector-representations-of |
| Repo | |
| Framework | |
