Paper Group NANR 187
Annotating and Predicting Non-Restrictive Noun Phrase Modifications. Object based Scene Representations using Fisher Scores of Local Subspace Projections. OPAL at SemEval-2016 Task 4: the Challenge of Porting a Sentiment Analysis System to the ``Real’’ World. RICOH at SemEval-2016 Task 1: IR-based Semantic Textual Similarity Estimation. Surveys: A …
Annotating and Predicting Non-Restrictive Noun Phrase Modifications
| Title | Annotating and Predicting Non-Restrictive Noun Phrase Modifications |
| Authors | Gabriel Stanovsky, Ido Dagan |
| Abstract | |
| Tasks | Abstractive Text Summarization, Knowledge Base Population, Question Answering, Semantic Role Labeling, Sentence Compression |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1119/ |
| https://www.aclweb.org/anthology/P16-1119 | |
| PWC | https://paperswithcode.com/paper/annotating-and-predicting-non-restrictive |
| Repo | |
| Framework | |
Object based Scene Representations using Fisher Scores of Local Subspace Projections
| Title | Object based Scene Representations using Fisher Scores of Local Subspace Projections |
| Authors | Mandar D. Dixit, Nuno Vasconcelos |
| Abstract | Several works have shown that deep CNN classifiers can be easily transferred across datasets, e.g. the transfer of a CNN trained to recognize objects on ImageNET to an object detector on Pascal VOC. Less clear, however, is the ability of CNNs to transfer knowledge across tasks. A common example of such transfer is the problem of scene classification that should leverage localized object detections to recognize holistic visual concepts. While this problem is currently addressed with Fisher vector representations, these are now shown ineffective for the high-dimensional and highly non-linear features extracted by modern CNNs. It is argued that this is mostly due to the reliance on a model, the Gaussian mixture of diagonal covariances, which has a very limited ability to capture the second order statistics of CNN features. This problem is addressed by the adoption of a better model, the mixture of factor analyzers (MFA), which approximates the non-linear data manifold by a collection of local subspaces. The Fisher score with respect to the MFA (MFA-FS) is derived and proposed as an image representation for holistic image classifiers. Extensive experiments show that the MFA-FS has state of the art performance for object-to-scene transfer and this transfer actually outperforms the training of a scene CNN from a large scene dataset. The two representations are also shown to be complementary, in the sense that their combination outperforms each of the representations by itself. When combined, they produce a state of the art scene classifier. |
| Tasks | Scene Classification |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6343-object-based-scene-representations-using-fisher-scores-of-local-subspace-projections |
| http://papers.nips.cc/paper/6343-object-based-scene-representations-using-fisher-scores-of-local-subspace-projections.pdf | |
| PWC | https://paperswithcode.com/paper/object-based-scene-representations-using |
| Repo | |
| Framework | |
OPAL at SemEval-2016 Task 4: the Challenge of Porting a Sentiment Analysis System to the ``Real’’ World
| Title | OPAL at SemEval-2016 Task 4: the Challenge of Porting a Sentiment Analysis System to the ``Real’’ World | |
| Authors | Alex Balahur, ra |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1041/ |
| https://www.aclweb.org/anthology/S16-1041 | |
| PWC | https://paperswithcode.com/paper/opal-at-semeval-2016-task-4-the-challenge-of |
| Repo | |
| Framework | |
RICOH at SemEval-2016 Task 1: IR-based Semantic Textual Similarity Estimation
| Title | RICOH at SemEval-2016 Task 1: IR-based Semantic Textual Similarity Estimation |
| Authors | Hideo Itoh |
| Abstract | |
| Tasks | Information Retrieval, Semantic Textual Similarity, Word Alignment |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1106/ |
| https://www.aclweb.org/anthology/S16-1106 | |
| PWC | https://paperswithcode.com/paper/ricoh-at-semeval-2016-task-1-ir-based |
| Repo | |
| Framework | |
Surveys: A Survey of Word Reordering in Statistical Machine Translation: Computational Models and Language Phenomena
| Title | Surveys: A Survey of Word Reordering in Statistical Machine Translation: Computational Models and Language Phenomena |
| Authors | Arianna Bisazza, Marcello Federico |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/J16-2001/ |
| https://www.aclweb.org/anthology/J16-2001 | |
| PWC | https://paperswithcode.com/paper/surveys-a-survey-of-word-reordering-in |
| Repo | |
| Framework | |
Integrating Type Theory and Distributional Semantics: A Case Study on Adjective–Noun Compositions
| Title | Integrating Type Theory and Distributional Semantics: A Case Study on Adjective–Noun Compositions |
| Authors | Nicholas Asher, Tim Van de Cruys, Antoine Bride, M{'a}rta Abrus{'a}n |
| Abstract | |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/J16-4005/ |
| https://www.aclweb.org/anthology/J16-4005 | |
| PWC | https://paperswithcode.com/paper/integrating-type-theory-and-distributional |
| Repo | |
| Framework | |
On the Use of a Serious Game for Recording a Speech Corpus of People with Intellectual Disabilities
| Title | On the Use of a Serious Game for Recording a Speech Corpus of People with Intellectual Disabilities |
| Authors | Mario Corrales-Astorgano, David Escudero-Mancebo, Yurena Guti{'e}rrez-Gonz{'a}lez, Valle Flores-Lucas, C{'e}sar Gonz{'a}lez-Ferreras, Valent{'\i}n Carde{~n}oso-Payo |
| Abstract | This paper describes the recording of a speech corpus focused on prosody of people with intellectual disabilities. To do this, a video game is used with the aim of improving the user{'}s motivation. Moreover, the player{'}s profiles and the sentences recorded during the game sessions are described. With the purpose of identifying the main prosodic troubles of people with intellectual disabilities, some prosodic features are extracted from recordings, like fundamental frequency, energy and pauses. After that, a comparison is made between the recordings of people with intellectual disabilities and people without intellectual disabilities. This comparison shows that pauses are the best discriminative feature between these groups. To check this, a study has been done using machine learning techniques, with a classification rate superior to 80{%}. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1332/ |
| https://www.aclweb.org/anthology/L16-1332 | |
| PWC | https://paperswithcode.com/paper/on-the-use-of-a-serious-game-for-recording-a |
| Repo | |
| Framework | |
Inferring Discourse Relations from PDTB-style Discourse Labels for Argumentative Revision Classification
| Title | Inferring Discourse Relations from PDTB-style Discourse Labels for Argumentative Revision Classification |
| Authors | Fan Zhang, Diane Litman, Katherine Forbes Riley |
| Abstract | Penn Discourse Treebank (PDTB)-style annotation focuses on labeling local discourse relations between text spans and typically ignores larger discourse contexts. In this paper we propose two approaches to infer discourse relations in a paragraph-level context from annotated PDTB labels. We investigate the utility of inferring such discourse information using the task of revision classification. Experimental results demonstrate that the inferred information can significantly improve classification performance compared to baselines, not only when PDTB annotation comes from humans but also from automatic parsers. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1246/ |
| https://www.aclweb.org/anthology/C16-1246 | |
| PWC | https://paperswithcode.com/paper/inferring-discourse-relations-from-pdtb-style |
| Repo | |
| Framework | |
Feature-Rich Error Detection in Scientific Writing Using Logistic Regression
| Title | Feature-Rich Error Detection in Scientific Writing Using Logistic Regression |
| Authors | Madeline Remse, Mohsen Mesgar, Michael Strube |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0518/ |
| https://www.aclweb.org/anthology/W16-0518 | |
| PWC | https://paperswithcode.com/paper/feature-rich-error-detection-in-scientific |
| Repo | |
| Framework | |
Bundled Gap Filling: A New Paradigm for Unambiguous Cloze Exercises
| Title | Bundled Gap Filling: A New Paradigm for Unambiguous Cloze Exercises |
| Authors | Michael Wojatzki, Oren Melamud, Torsten Zesch |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0519/ |
| https://www.aclweb.org/anthology/W16-0519 | |
| PWC | https://paperswithcode.com/paper/bundled-gap-filling-a-new-paradigm-for |
| Repo | |
| Framework | |
Proceedings of the 2nd Workshop on Semantics-Driven Machine Translation (SedMT 2016)
| Title | Proceedings of the 2nd Workshop on Semantics-Driven Machine Translation (SedMT 2016) |
| Authors | |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0600/ |
| https://www.aclweb.org/anthology/W16-0600 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2nd-workshop-on-semantics |
| Repo | |
| Framework | |
Contextual stance classification of opinions: A step towards enthymeme reconstruction in online reviews
| Title | Contextual stance classification of opinions: A step towards enthymeme reconstruction in online reviews |
| Authors | Pavithra Rajendran, Danushka Bollegala, Simon Parsons |
| Abstract | |
| Tasks | Argument Mining |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2804/ |
| https://www.aclweb.org/anthology/W16-2804 | |
| PWC | https://paperswithcode.com/paper/contextual-stance-classification-of-opinions |
| Repo | |
| Framework | |
Challenges of Argument Mining: Generating an Argument Synthesis based on the Qualia Structure
| Title | Challenges of Argument Mining: Generating an Argument Synthesis based on the Qualia Structure |
| Authors | Patrick Saint-Dizier |
| Abstract | |
| Tasks | Abstract Argumentation, Argument Mining, Text Generation |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-6613/ |
| https://www.aclweb.org/anthology/W16-6613 | |
| PWC | https://paperswithcode.com/paper/challenges-of-argument-mining-generating-an |
| Repo | |
| Framework | |
Attention-based Multimodal Neural Machine Translation
| Title | Attention-based Multimodal Neural Machine Translation |
| Authors | Po-Yao Huang, Frederick Liu, Sz-Rung Shiang, Jean Oh, Chris Dyer |
| Abstract | |
| Tasks | Image Captioning, Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2360/ |
| https://www.aclweb.org/anthology/W16-2360 | |
| PWC | https://paperswithcode.com/paper/attention-based-multimodal-neural-machine |
| Repo | |
| Framework | |
A Neural Lemmatizer for Bengali
| Title | A Neural Lemmatizer for Bengali |
| Authors | Abhisek Chakrabarty, Akshay Chaturvedi, Utpal Garain |
| Abstract | We propose a novel neural lemmatization model which is language independent and supervised in nature. To handle the words in a neural framework, word embedding technique is used to represent words as vectors. The proposed lemmatizer makes use of contextual information of the surface word to be lemmatized. Given a word along with its contextual neighbours as input, the model is designed to produce the lemma of the concerned word as output. We introduce a new network architecture that permits only dimension specific connections between the input and the output layer of the model. For the present work, Bengali is taken as the reference language. Two datasets are prepared for training and testing purpose consisting of 19,159 and 2,126 instances respectively. As Bengali is a resource scarce language, these datasets would be beneficial for the respective research community. Evaluation method shows that the neural lemmatizer achieves 69.57{%} accuracy on the test dataset and outperforms the simple cosine similarity based baseline strategy by a margin of 1.37{%}. |
| Tasks | Lemmatization |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1406/ |
| https://www.aclweb.org/anthology/L16-1406 | |
| PWC | https://paperswithcode.com/paper/a-neural-lemmatizer-for-bengali |
| Repo | |
| Framework | |
