Paper Group NANR 54
Deliberation as Genre: Mapping Argumentation through Relational Discourse Structure. The Good, the Bad, and the Disagreement: Complex ground truth in rhetorical structure analysis. What Sentence are you Referring to and Why? Identifying Cited Sentences in Scientific Literature. NITE: A Neural Inductive Teaching Framework for Domain Specific NER. Se …
Deliberation as Genre: Mapping Argumentation through Relational Discourse Structure
| Title | Deliberation as Genre: Mapping Argumentation through Relational Discourse Structure |
| Authors | Oier Imaz, Mikel Iruskieta |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3601/ |
| https://www.aclweb.org/anthology/W17-3601 | |
| PWC | https://paperswithcode.com/paper/deliberation-as-genre-mapping-argumentation |
| Repo | |
| Framework | |
The Good, the Bad, and the Disagreement: Complex ground truth in rhetorical structure analysis
| Title | The Good, the Bad, and the Disagreement: Complex ground truth in rhetorical structure analysis |
| Authors | Debopam Das, Manfred Stede, Maite Taboada |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-3602/ |
| https://www.aclweb.org/anthology/W17-3602 | |
| PWC | https://paperswithcode.com/paper/the-good-the-bad-and-the-disagreement-complex |
| Repo | |
| Framework | |
What Sentence are you Referring to and Why? Identifying Cited Sentences in Scientific Literature
| Title | What Sentence are you Referring to and Why? Identifying Cited Sentences in Scientific Literature |
| Authors | Ahmed AbuRa{'}ed, Luis Chiruzzo, Horacio Saggion |
| Abstract | In the current context of scientific information overload, text mining tools are of paramount importance for researchers who have to read scientific papers and assess their value. Current citation networks, which link papers by citation relationships (reference and citing paper), are useful to quantitatively understand the value of a piece of scientific work, however they are limited in that they do not provide information about what specific part of the reference paper the citing paper is referring to. This qualitative information is very important, for example, in the context of current community-based scientific summarization activities. In this paper, and relying on an annotated dataset of co-citation sentences, we carry out a number of experiments aimed at, given a citation sentence, automatically identify a part of a reference paper being cited. Additionally our algorithm predicts the specific reason why such reference sentence has been cited out of five possible reasons. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1002/ |
| https://doi.org/10.26615/978-954-452-049-6_002 | |
| PWC | https://paperswithcode.com/paper/what-sentence-are-you-referring-to-and-why |
| Repo | |
| Framework | |
NITE: A Neural Inductive Teaching Framework for Domain Specific NER
| Title | NITE: A Neural Inductive Teaching Framework for Domain Specific NER |
| Authors | Siliang Tang, Ning Zhang, Jinjiang Zhang, Fei Wu, Yueting Zhuang |
| Abstract | In domain-specific NER, due to insufficient labeled training data, deep models usually fail to behave normally. In this paper, we proposed a novel Neural Inductive TEaching framework (NITE) to transfer knowledge from existing domain-specific NER models into an arbitrary deep neural network in a teacher-student training manner. NITE is a general framework that builds upon transfer learning and multiple instance learning, which collaboratively not only transfers knowledge to a deep student network but also reduces the noise from teachers. NITE can help deep learning methods to effectively utilize existing resources (i.e., models, labeled and unlabeled data) in a small domain. The experiment resulted on Disease NER proved that without using any labeled data, NITE can significantly boost the performance of a CNN-bidirectional LSTM-CRF NER neural network nearly over 30{%} in terms of F1-score. |
| Tasks | Document Classification, Multiple Instance Learning, Named Entity Recognition, Transfer Learning |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1280/ |
| https://www.aclweb.org/anthology/D17-1280 | |
| PWC | https://paperswithcode.com/paper/nite-a-neural-inductive-teaching-framework |
| Repo | |
| Framework | |
Sequence Effects in Crowdsourced Annotations
| Title | Sequence Effects in Crowdsourced Annotations |
| Authors | Nitika Mathur, Timothy Baldwin, Trevor Cohn |
| Abstract | Manual data annotation is a vital component of NLP research. When designing annotation tasks, properties of the annotation interface can unintentionally lead to artefacts in the resulting dataset, biasing the evaluation. In this paper, we explore sequence effects where annotations of an item are affected by the preceding items. Having assigned one label to an instance, the annotator may be less (or more) likely to assign the same label to the next. During rating tasks, seeing a low quality item may affect the score given to the next item either positively or negatively. We see clear evidence of both types of effects using auto-correlation studies over three different crowdsourced datasets. We then recommend a simple way to minimise sequence effects. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1306/ |
| https://www.aclweb.org/anthology/D17-1306 | |
| PWC | https://paperswithcode.com/paper/sequence-effects-in-crowdsourced-annotations |
| Repo | |
| Framework | |
Towards Normalising Konkani-English Code-Mixed Social Media Text
| Title | Towards Normalising Konkani-English Code-Mixed Social Media Text |
| Authors | Akshata Phadte, Gaurish Thakkar |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7511/ |
| https://www.aclweb.org/anthology/W17-7511 | |
| PWC | https://paperswithcode.com/paper/towards-normalising-konkani-english-code |
| Repo | |
| Framework | |
Exploring Cross-Lingual Transfer of Morphological Knowledge In Sequence-to-Sequence Models
| Title | Exploring Cross-Lingual Transfer of Morphological Knowledge In Sequence-to-Sequence Models |
| Authors | Huiming Jin, Katharina Kann |
| Abstract | Multi-task training is an effective method to mitigate the data sparsity problem. It has recently been applied for cross-lingual transfer learning for paradigm completion{—}the task of producing inflected forms of lemmata{—}with sequence-to-sequence networks. However, it is still vague how the model transfers knowledge across languages, as well as if and which information is shared. To investigate this, we propose a set of data-dependent experiments using an existing encoder-decoder recurrent neural network for the task. Our results show that indeed the performance gains surpass a pure regularization effect and that knowledge about language and morphology can be transferred. |
| Tasks | Cross-Lingual Transfer, Language Modelling, Multi-Task Learning, Transfer Learning |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4110/ |
| https://www.aclweb.org/anthology/W17-4110 | |
| PWC | https://paperswithcode.com/paper/exploring-cross-lingual-transfer-of |
| Repo | |
| Framework | |
Universal Dependencies to Logical Form with Negation Scope
| Title | Universal Dependencies to Logical Form with Negation Scope |
| Authors | Federico Fancellu, Siva Reddy, Adam Lopez, Bonnie Webber |
| Abstract | Many language technology applications would benefit from the ability to represent negation and its scope on top of widely-used linguistic resources. In this paper, we investigate the possibility of obtaining a first-order logic representation with negation scope marked using \textit{Universal Dependencies}. To do so, we enhance \textit{UDepLambda}, a framework that converts dependency graphs to logical forms. The resulting \textit{UDepLambda$\lnot$ }is able to handle phenomena related to scope by means of an higher-order type theory, relevant not only to negation but also to universal quantification and other complex semantic phenomena. The initial conversion we did for English is promising, in that one can represent the scope of negation also in the presence of more complex phenomena such as universal quantifiers. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1804/ |
| https://www.aclweb.org/anthology/W17-1804 | |
| PWC | https://paperswithcode.com/paper/universal-dependencies-to-logical-form-with |
| Repo | |
| Framework | |
Weighted Set-Theoretic Alignment of Comparable Sentences
| Title | Weighted Set-Theoretic Alignment of Comparable Sentences |
| Authors | Andoni Azpeitia, Thierry Etchegoyhen, Eva Mart{'\i}nez Garcia |
| Abstract | This article presents the STACCw system for the BUCC 2017 shared task on parallel sentence extraction from comparable corpora. The original STACC approach, based on set-theoretic operations over bags of words, had been previously shown to be efficient and portable across domains and alignment scenarios. Wedescribe an extension of this approach with a new weighting scheme and show that it provides significant improvements on the datasets provided for the shared task. |
| Tasks | Machine Translation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2508/ |
| https://www.aclweb.org/anthology/W17-2508 | |
| PWC | https://paperswithcode.com/paper/weighted-set-theoretic-alignment-of |
| Repo | |
| Framework | |
Tractability in Structured Probability Spaces
| Title | Tractability in Structured Probability Spaces |
| Authors | Arthur Choi, Yujia Shen, Adnan Darwiche |
| Abstract | Recently, the Probabilistic Sentential Decision Diagram (PSDD) has been proposed as a framework for systematically inducing and learning distributions over structured objects, including combinatorial objects such as permutations and rankings, paths and matchings on a graph, etc. In this paper, we study the scalability of such models in the context of representing and learning distributions over routes on a map. In particular, we introduce the notion of a hierarchical route distribution and show how they can be leveraged to construct tractable PSDDs over route distributions, allowing them to scale to larger maps. We illustrate the utility of our model empirically, in a route prediction task, showing how accuracy can be increased significantly compared to Markov models. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6939-tractability-in-structured-probability-spaces |
| http://papers.nips.cc/paper/6939-tractability-in-structured-probability-spaces.pdf | |
| PWC | https://paperswithcode.com/paper/tractability-in-structured-probability-spaces |
| Repo | |
| Framework | |
Using Social Networks to Improve Language Variety Identification with Neural Networks
| Title | Using Social Networks to Improve Language Variety Identification with Neural Networks |
| Authors | Yasuhide Miura, Tomoki Taniguchi, Motoki Taniguchi, Shotaro Misawa, Tomoko Ohkuma |
| Abstract | We propose a hierarchical neural network model for language variety identification that integrates information from a social network. Recently, language variety identification has enjoyed heightened popularity as an advanced task of language identification. The proposed model uses additional texts from a social network to improve language variety identification from two perspectives. First, they are used to introduce the effects of homophily. Secondly, they are used as expanded training data for shared layers of the proposed model. By introducing information from social networks, the model improved its accuracy by 1.67-5.56. Compared to state-of-the-art baselines, these improved performances are better in English and comparable in Spanish. Furthermore, we analyzed the cases of Portuguese and Arabic when the model showed weak performances, and found that the effect of homophily is likely to be weak due to sparsity and noises compared to languages with the strong performances. |
| Tasks | Language Identification |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2045/ |
| https://www.aclweb.org/anthology/I17-2045 | |
| PWC | https://paperswithcode.com/paper/using-social-networks-to-improve-language |
| Repo | |
| Framework | |
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers
| Title | Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2000/ |
| https://www.aclweb.org/anthology/E17-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-15th-conference-of-the-1 |
| Repo | |
| Framework | |
Lemmatization of Multi-word Common Noun Phrases and Named Entities in Polish
| Title | Lemmatization of Multi-word Common Noun Phrases and Named Entities in Polish |
| Authors | Micha{\l} Marci{'n}czuk |
| Abstract | In the paper we present a tool for lemmatization of multi-word common noun phrases and named entities for Polish called LemmaPL. The tool is based on a set of manually crafted rules and heuristics utilizing a set of dictionaries (including morphological, named entities and inflection patterns). The accuracy of lemmatization obtained by the tool reached 97.99{%} on a dataset with multi-word common noun phrases and 86.17{%} for case-sensitive evaluation on a dataset with named entities. |
| Tasks | Lemmatization |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1064/ |
| https://doi.org/10.26615/978-954-452-049-6_064 | |
| PWC | https://paperswithcode.com/paper/lemmatization-of-multi-word-common-noun |
| Repo | |
| Framework | |
Predicting User Views in Online News
| Title | Predicting User Views in Online News |
| Authors | Daniel Hardt, Owen Rambow |
| Abstract | We analyze user viewing behavior on an online news site. We collect data from 64,000 news articles, and use text features to predict frequency of user views. We compare predictiveness of the headline and {``}teaser{''} (viewed before clicking) and the body (viewed after clicking). Both are predictive of clicking behavior, with the full article text being most predictive. | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4202/ |
| https://www.aclweb.org/anthology/W17-4202 | |
| PWC | https://paperswithcode.com/paper/predicting-user-views-in-online-news |
| Repo | |
| Framework | |
A Corpus-based Analysis of Near-Synonymous Sentence-final Particles in Mandarin Chinese: bale'' and eryi’’
| Title | A Corpus-based Analysis of Near-Synonymous Sentence-final Particles in Mandarin Chinese: bale'' and eryi’’ |
| Authors | Xuefeng Gao, Yat-Mei Lee |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/Y17-1031/ |
| https://www.aclweb.org/anthology/Y17-1031 | |
| PWC | https://paperswithcode.com/paper/a-corpus-based-analysis-of-near-synonymous |
| Repo | |
| Framework | |
