Paper Group NANR 86
Emulating the Expert: Inverse Optimization through Online Learning. 探究使用基於類神經網路之特徵於文本可讀性分類 (Exploring the Use of Neural Network based Features for Text Readability Classification) [In Chinese]. Multi-Lingual Phrase-Based Statistical Machine Translation for Arabic-English. Generating titles for millions of browse pages on an e-Commerce site. Unbabel …
Emulating the Expert: Inverse Optimization through Online Learning
| Title | Emulating the Expert: Inverse Optimization through Online Learning |
| Authors | Andreas Bärmann, Sebastian Pokutta, Oskar Schneider |
| Abstract | In this paper, we demonstrate how to learn the objective function of a decision maker while only observing the problem input data and the decision maker’s corresponding decisions over multiple rounds. Our approach is based on online learning techniques and works for linear objectives over arbitrary sets for which we have a linear optimization oracle and as such generalizes previous work based on KKT-system decomposition and dualization approaches. The applicability of our framework for learning linear constraints is also discussed briefly. Our algorithm converges at a rate of O(1/sqrt(T)), and we demonstrate its effectiveness and applications in preliminary computational results. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=865 |
| http://proceedings.mlr.press/v70/barmann17a/barmann17a.pdf | |
| PWC | https://paperswithcode.com/paper/emulating-the-expert-inverse-optimization |
| Repo | |
| Framework | |
探究使用基於類神經網路之特徵於文本可讀性分類 (Exploring the Use of Neural Network based Features for Text Readability Classification) [In Chinese]
| Title | 探究使用基於類神經網路之特徵於文本可讀性分類 (Exploring the Use of Neural Network based Features for Text Readability Classification) [In Chinese] |
| Authors | Hou-Chiang Tseng, Berlin Chen, Yao-Ting Sung |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/O17-3004/ |
| https://www.aclweb.org/anthology/O17-3004 | |
| PWC | https://paperswithcode.com/paper/ca12c-ao14eccc2e-a1c1a3414a-eae-exploring-the |
| Repo | |
| Framework | |
Multi-Lingual Phrase-Based Statistical Machine Translation for Arabic-English
| Title | Multi-Lingual Phrase-Based Statistical Machine Translation for Arabic-English |
| Authors | Ahmed Bastawisy, Mohamed Elmahdy |
| Abstract | In this paper, we implement a multilingual Statistical Machine Translation (SMT) system for Arabic-English Translation. Arabic Text can be categorized into standard and dialectal Arabic. These two forms of Arabic differ significantly. Different mono-lingual and multi-lingual hybrid SMT approaches are compared. Mono-lingual systems do always results in better translation accuracy in one Arabic form and poor accuracy in the other. Multi-lingual SMT models that are trained with pooled parallel MSA/dialectal data result in better accuracy. However, since the available parallel MSA data are much larger compared to dialectal data, multilingual models are biased to MSA. We propose in the work, a multi-lingual combination of different mono-lingual systems using an Arabic form classifier. The outcome of the classier directs the system to use the appropriate mono-lingual models (standard, dialectal, or mixture). Testing the different SMT systems shows that the proposed classifier-based SMT system outperforms mono-lingual and data pooled multi-lingual systems. |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1013/ |
| https://doi.org/10.26615/978-954-452-049-6_013 | |
| PWC | https://paperswithcode.com/paper/multi-lingual-phrase-based-statistical |
| Repo | |
| Framework | |
Generating titles for millions of browse pages on an e-Commerce site
| Title | Generating titles for millions of browse pages on an e-Commerce site |
| Authors | Prashant Mathur, Nicola Ueffing, Gregor Leusch |
| Abstract | We present two approaches to generate titles for browse pages in five different languages, namely English, German, French, Italian and Spanish. These browse pages are structured search pages in an e-commerce domain. We first present a rule-based approach to generate these browse page titles. In addition, we also present a hybrid approach which uses a phrase-based statistical machine translation engine on top of the rule-based system to assemble the best title. For the two languages English and German we have access to a large amount of already available rule-based generated and curated titles. For these languages we present an automatic post-editing approach which learns how to post-edit the rule-based titles into curated titles. |
| Tasks | Automatic Post-Editing, Machine Translation, Question Answering, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3525/ |
| https://www.aclweb.org/anthology/W17-3525 | |
| PWC | https://paperswithcode.com/paper/generating-titles-for-millions-of-browse |
| Repo | |
| Framework | |
Unbabel’s Participation in the WMT17 Translation Quality Estimation Shared Task
| Title | Unbabel’s Participation in the WMT17 Translation Quality Estimation Shared Task |
| Authors | Andr{'e} F. T. Martins, Fabio Kepler, Jos{'e} Monteiro |
| Abstract | |
| Tasks | Automatic Post-Editing, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4764/ |
| https://www.aclweb.org/anthology/W17-4764 | |
| PWC | https://paperswithcode.com/paper/unbabels-participation-in-the-wmt17 |
| Repo | |
| Framework | |
An Evolutionary Algorithm for Automatic Summarization
| Title | An Evolutionary Algorithm for Automatic Summarization |
| Authors | Aur{'e}lien Bossard, Christophe Rodrigues |
| Abstract | This paper proposes a novel method to select sentences for automatic summarization based on an evolutionary algorithm. The algorithm explores candidate summaries space following an objective function computed over ngrams probability distributions of the candidate summary and the source documents. This method does not consider a summary as a stack of independent sentences but as a whole text, and makes use of advances in unsupervised summarization evaluation. We compare this sentence extraction method to one of the best existing methods which is based on integer linear programming, and show its efficiency on three different acknowledged corpora. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1017/ |
| https://doi.org/10.26615/978-954-452-049-6_017 | |
| PWC | https://paperswithcode.com/paper/an-evolutionary-algorithm-for-automatic |
| Repo | |
| Framework | |
Role-based model for Named Entity Recognition
| Title | Role-based model for Named Entity Recognition |
| Authors | Pablo Calleja, Ra{'u}l Garc{'\i}a-Castro, Guadalupe Aguado-de-Cea, Asunci{'o}n G{'o}mez-P{'e}rez |
| Abstract | Named Entity Recognition (NER) poses new challenges in real-world documents in which there are entities with different roles according to their purpose or meaning. Retrieving all the possible entities in scenarios in which only a subset of them based on their role is needed, produces noise on the overall precision. This work proposes a NER model that relies on role classification models that support recognizing entities with a specific role. The proposed model has been implemented in two use cases using Spanish drug Summary of Product Characteristics: identification of therapeutic indications and identification of adverse reactions. The results show how precision is increased using a NER model that is oriented towards a specific role and discards entities out of scope. |
| Tasks | Named Entity Recognition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1021/ |
| https://doi.org/10.26615/978-954-452-049-6_021 | |
| PWC | https://paperswithcode.com/paper/role-based-model-for-named-entity-recognition |
| Repo | |
| Framework | |
Sentence-Level Multilingual Multi-modal Embedding for Natural Language Processing
| Title | Sentence-Level Multilingual Multi-modal Embedding for Natural Language Processing |
| Authors | Iacer Calixto, Qun Liu |
| Abstract | We propose a novel discriminative ranking model that learns embeddings from multilingual and multi-modal data, meaning that our model can take advantage of images and descriptions in multiple languages to improve embedding quality. To that end, we introduce an objective function that uses pairwise ranking adapted to the case of three or more input sources. We compare our model against different baselines, and evaluate the robustness of our embeddings on image{–}sentence ranking (ISR), semantic textual similarity (STS), and neural machine translation (NMT). We find that the additional multilingual signals lead to improvements on all three tasks, and we highlight that our model can be used to consistently improve the adequacy of translations generated with NMT models when re-ranking n-best lists. |
| Tasks | Machine Translation, Semantic Textual Similarity |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1020/ |
| https://doi.org/10.26615/978-954-452-049-6_020 | |
| PWC | https://paperswithcode.com/paper/sentence-level-multilingual-multi-modal |
| Repo | |
| Framework | |
Towards the Improvement of Automatic Emotion Pre-annotation with Polarity and Subjective Information
| Title | Towards the Improvement of Automatic Emotion Pre-annotation with Polarity and Subjective Information |
| Authors | Lea Canales, Walter Daelemans, Ester Boldrini, Patricio Mart{'\i}nez-Barco |
| Abstract | Emotion detection has a high potential positive impact on the benefit of business, society, politics or education. Given this, the main objective of our research is to contribute to the resolution of one of the most important challenges in textual emotion detection: emotional corpora annotation. This will be tackled by proposing a semi-automatic methodology. It consists in two main phases: (1) an automatic process to pre-annotate the unlabelled sentences with a reduced number of emotional categories; and (2) a manual process of refinement where human annotators will determine which is the dominant emotion between the pre-defined set. Our objective in this paper is to show the pre-annotation process, as well as to evaluate the usability of subjective and polarity information in this process. The evaluation performed confirms clearly the benefits of employing the polarity and subjective information on emotion detection and thus endorses the relevance of our approach. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1022/ |
| https://doi.org/10.26615/978-954-452-049-6_022 | |
| PWC | https://paperswithcode.com/paper/towards-the-improvement-of-automatic-emotion |
| Repo | |
| Framework | |
Underspecification in Natural Language Understanding for Dialog Automation
| Title | Underspecification in Natural Language Understanding for Dialog Automation |
| Authors | John Chen, Srinivas Bangalore |
| Abstract | With the increasing number of communication platforms that offer variety of ways of connecting two interlocutors, there is a resurgence of chat-based dialog systems. These systems, typically known as \textit{chatbots} have beensuccessfully applied in a range of consumer and enterprise applications. A keytechnology in such chat-bots is robust natural language understanding (NLU)which can significantly influence and impact the efficacy of the conversationand ultimately the user-experience. While NLU is far from perfect, this paperillustrates the role of \textit{underspecification} and its impact on successfuldialog completion. |
| Tasks | Speech Recognition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1023/ |
| https://doi.org/10.26615/978-954-452-049-6_023 | |
| PWC | https://paperswithcode.com/paper/underspecification-in-natural-language |
| Repo | |
| Framework | |
Guiding Neural Machine Translation Decoding with External Knowledge
| Title | Guiding Neural Machine Translation Decoding with External Knowledge |
| Authors | Rajen Chatterjee, Matteo Negri, Marco Turchi, Marcello Federico, Lucia Specia, Fr{'e}d{'e}ric Blain |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4716/ |
| https://www.aclweb.org/anthology/W17-4716 | |
| PWC | https://paperswithcode.com/paper/guiding-neural-machine-translation-decoding |
| Repo | |
| Framework | |
Automatically Acquired Lexical Knowledge Improves Japanese Joint Morphological and Dependency Analysis
| Title | Automatically Acquired Lexical Knowledge Improves Japanese Joint Morphological and Dependency Analysis |
| Authors | Daisuke Kawahara, Yuta Hayashibe, Hajime Morita, Sadao Kurohashi |
| Abstract | This paper presents a joint model for morphological and dependency analysis based on automatically acquired lexical knowledge. This model takes advantage of rich lexical knowledge to simultaneously resolve word segmentation, POS, and dependency ambiguities. In our experiments on Japanese, we show the effectiveness of our joint model over conventional pipeline models. |
| Tasks | Lemmatization, Morphological Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6301/ |
| https://www.aclweb.org/anthology/W17-6301 | |
| PWC | https://paperswithcode.com/paper/automatically-acquired-lexical-knowledge |
| Repo | |
| Framework | |
If Sentences Could See: Investigating Visual Information for Semantic Textual Similarity
| Title | If Sentences Could See: Investigating Visual Information for Semantic Textual Similarity |
| Authors | Goran Glava{\v{s}}, Ivan Vuli{'c}, Simone Paolo Ponzetto |
| Abstract | |
| Tasks | Machine Translation, Semantic Textual Similarity |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6809/ |
| https://www.aclweb.org/anthology/W17-6809 | |
| PWC | https://paperswithcode.com/paper/if-sentences-could-see-investigating-visual |
| Repo | |
| Framework | |
Rhetorical relations markers in Russian RST Treebank
| Title | Rhetorical relations markers in Russian RST Treebank |
| Authors | Svetlana Toldova, Dina Pisarevskaya, Margarita Ananyeva, Maria Kobozeva, Alex Nasedkin, er, Sofia Nikiforova, Irina Pavlova, Alexey Shelepov |
| Abstract | |
| Tasks | Coreference Resolution, Question Answering, Text Summarization |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3604/ |
| https://www.aclweb.org/anthology/W17-3604 | |
| PWC | https://paperswithcode.com/paper/rhetorical-relations-markers-in-russian-rst |
| Repo | |
| Framework | |
Segmentation Granularity in Dependency Representations for Korean
| Title | Segmentation Granularity in Dependency Representations for Korean |
| Authors | Jungyeul Park |
| Abstract | |
| Tasks | Dependency Parsing, Morphological Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6522/ |
| https://www.aclweb.org/anthology/W17-6522 | |
| PWC | https://paperswithcode.com/paper/segmentation-granularity-in-dependency |
| Repo | |
| Framework | |
