Paper Group NANR 38
Proceedings of the 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities. Improved Representation Learning for Question Answer Matching. Entropy Converges Between Dialogue Participants: Explanations from an Information-Theoretic Perspective. Constructing a Norwegian Academic Wordlist. aueb.twitter.sentim …
Proceedings of the 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities
| Title | Proceedings of the 10th SIGHUM Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2100/ |
| https://www.aclweb.org/anthology/W16-2100 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-10th-sighum-workshop-on |
| Repo | |
| Framework | |
Improved Representation Learning for Question Answer Matching
| Title | Improved Representation Learning for Question Answer Matching |
| Authors | Ming Tan, Cicero dos Santos, Bing Xiang, Bowen Zhou |
| Abstract | |
| Tasks | Answer Selection, Natural Language Inference, Question Answering, Representation Learning |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1044/ |
| https://www.aclweb.org/anthology/P16-1044 | |
| PWC | https://paperswithcode.com/paper/improved-representation-learning-for-question |
| Repo | |
| Framework | |
Entropy Converges Between Dialogue Participants: Explanations from an Information-Theoretic Perspective
| Title | Entropy Converges Between Dialogue Participants: Explanations from an Information-Theoretic Perspective |
| Authors | Yang Xu, David Reitter |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1051/ |
| https://www.aclweb.org/anthology/P16-1051 | |
| PWC | https://paperswithcode.com/paper/entropy-converges-between-dialogue |
| Repo | |
| Framework | |
Constructing a Norwegian Academic Wordlist
| Title | Constructing a Norwegian Academic Wordlist |
| Authors | Janne M Johannessen, Arash Saidi, Kristin Hagen |
| Abstract | We present the development of a Norwegian Academic Wordlist (AKA list) for the Norwegian Bokm{"a}l variety. To identify specific academic vocabulary we developed a 100-million-word academic corpus based on the University of Oslo archive of digital publications. Other corpora were used for testing and developing general word lists. We tried two different methods, those of Carlund et al. (2012) and Gardner {&} Davies (2013), and compared them. The resulting list is presented on a web site, where the words can be inspected in different ways, and freely downloaded. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1232/ |
| https://www.aclweb.org/anthology/L16-1232 | |
| PWC | https://paperswithcode.com/paper/constructing-a-norwegian-academic-wordlist |
| Repo | |
| Framework | |
aueb.twitter.sentiment at SemEval-2016 Task 4: A Weighted Ensemble of SVMs for Twitter Sentiment Analysis
| Title | aueb.twitter.sentiment at SemEval-2016 Task 4: A Weighted Ensemble of SVMs for Twitter Sentiment Analysis |
| Authors | Stavros Giorgis, Apostolos Rousas, John Pavlopoulos, Prodromos Malakasiotis, Ion Androutsopoulos |
| Abstract | |
| Tasks | Sentiment Analysis, Twitter Sentiment Analysis, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1012/ |
| https://www.aclweb.org/anthology/S16-1012 | |
| PWC | https://paperswithcode.com/paper/auebtwittersentiment-at-semeval-2016-task-4-a |
| Repo | |
| Framework | |
Finki at SemEval-2016 Task 4: Deep Learning Architecture for Twitter Sentiment Analysis
| Title | Finki at SemEval-2016 Task 4: Deep Learning Architecture for Twitter Sentiment Analysis |
| Authors | Dario Stojanovski, Gjorgji Strezoski, Gjorgji Madjarov, Ivica Dimitrovski |
| Abstract | |
| Tasks | Sentiment Analysis, Twitter Sentiment Analysis, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1022/ |
| https://www.aclweb.org/anthology/S16-1022 | |
| PWC | https://paperswithcode.com/paper/finki-at-semeval-2016-task-4-deep-learning |
| Repo | |
| Framework | |
Meaning Matters: Senses of Words are More Informative than Words for Cross-domain Sentiment Analysis
| Title | Meaning Matters: Senses of Words are More Informative than Words for Cross-domain Sentiment Analysis |
| Authors | Raksha Sharma, Sudha Bhingardive, Pushpak Bhattacharyya |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-6315/ |
| https://www.aclweb.org/anthology/W16-6315 | |
| PWC | https://paperswithcode.com/paper/meaning-matters-senses-of-words-are-more |
| Repo | |
| Framework | |
Addressing the MFS Bias in WSD systems
| Title | Addressing the MFS Bias in WSD systems |
| Authors | Marten Postma, Ruben Izquierdo, Eneko Agirre, German Rigau, Piek Vossen |
| Abstract | Word Sense Disambiguation (WSD) systems tend to have a strong bias towards assigning the Most Frequent Sense (MFS), which results in high performance on the MFS but in a very low performance on the less frequent senses. We addressed the MFS bias in WSD systems by combining the output from a WSD system with a set of mostly static features to create a MFS classifier to decide when to and not to choose the MFS. The output from this MFS classifier, which is based on the Random Forest algorithm, is then used to modify the output from the original WSD system. We applied our classifier to one of the state-of-the-art supervised WSD systems, i.e. IMS, and to of the best state-of-the-art unsupervised WSD systems, i.e. UKB. Our main finding is that we are able to improve the system output in terms of choosing between the MFS and the less frequent senses. When we apply the MFS classifier to fine-grained WSD, we observe an improvement on the less frequent sense cases, whereas we maintain the overall recall. |
| Tasks | Word Sense Disambiguation |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1268/ |
| https://www.aclweb.org/anthology/L16-1268 | |
| PWC | https://paperswithcode.com/paper/addressing-the-mfs-bias-in-wsd-systems |
| Repo | |
| Framework | |
Hierarchical Object Representation for Open-Ended Object Category Learning and Recognition
| Title | Hierarchical Object Representation for Open-Ended Object Category Learning and Recognition |
| Authors | Seyed Hamidreza Kasaei, Ana Maria Tomé, Luís Seabra Lopes |
| Abstract | Most robots lack the ability to learn new objects from past experiences. To migrate a robot to a new environment one must often completely re-generate the knowledge- base that it is running with. Since in open-ended domains the set of categories to be learned is not predefined, it is not feasible to assume that one can pre-program all object categories required by robots. Therefore, autonomous robots must have the ability to continuously execute learning and recognition in a concurrent and interleaved fashion. This paper proposes an open-ended 3D object recognition system which concurrently learns both the object categories and the statistical features for encoding objects. In particular, we propose an extension of Latent Dirichlet Allocation to learn structural semantic features (i.e. topics) from low-level feature co-occurrences for each category independently. Moreover, topics in each category are discovered in an unsupervised fashion and are updated incrementally using new object views. The approach contains similarities with the organization of the visual cortex and builds a hierarchy of increasingly sophisticated representations. Results show the fulfilling performance of this approach on different types of objects. Moreover, this system demonstrates the capability of learning from few training examples and competes with state-of-the-art systems. |
| Tasks | 3D Object Recognition, Object Recognition |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6539-hierarchical-object-representation-for-open-ended-object-category-learning-and-recognition |
| http://papers.nips.cc/paper/6539-hierarchical-object-representation-for-open-ended-object-category-learning-and-recognition.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-object-representation-for-open |
| Repo | |
| Framework | |
A Computational Perspective on the Romanian Dialects
| Title | A Computational Perspective on the Romanian Dialects |
| Authors | Alina Maria Ciobanu, Liviu P. Dinu |
| Abstract | In this paper we conduct an initial study on the dialects of Romanian. We analyze the differences between Romanian and its dialects using the Swadesh list. We analyze the predictive power of the orthographic and phonetic features of the words, building a classification problem for dialect identification. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1522/ |
| https://www.aclweb.org/anthology/L16-1522 | |
| PWC | https://paperswithcode.com/paper/a-computational-perspective-on-the-romanian |
| Repo | |
| Framework | |
Specialising Paragraph Vectors for Text Polarity Detection
| Title | Specialising Paragraph Vectors for Text Polarity Detection |
| Authors | Fabio Tamburini |
| Abstract | This paper presents some experiments for specialising Paragraph Vectors, a new technique for creating text fragment (phrase, sentence, paragraph, text, …) embedding vectors, for text polarity detection. The first extension regards the injection of polarity information extracted from a polarity lexicon into embeddings and the second extension aimed at inserting word order information into Paragraph Vectors. These two extensions, when training a logistic-regression classifier on the combined embeddings, were able to produce a relevant gain in performance when compared to the standard Paragraph Vector methods proposed by Le and Mikolov (2014). |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1189/ |
| https://www.aclweb.org/anthology/L16-1189 | |
| PWC | https://paperswithcode.com/paper/specialising-paragraph-vectors-for-text |
| Repo | |
| Framework | |
Global Open Resources and Information for Language and Linguistic Analysis (GORILLA)
| Title | Global Open Resources and Information for Language and Linguistic Analysis (GORILLA) |
| Authors | Damir Cavar, Malgorzata Cavar, Lwin Moe |
| Abstract | The infrastructure Global Open Resources and Information for Language and Linguistic Analysis (GORILLA) was created as a resource that provides a bridge between disciplines such as documentary, theoretical, and corpus linguistics, speech and language technologies, and digital language archiving services. GORILLA is designed as an interface between digital language archive services and language data producers. It addresses various problems of common digital language archive infrastructures. At the same time it serves the speech and language technology communities by providing a platform to create and share speech and language data from low-resourced and endangered languages. It hosts an initial collection of language models for speech and natural language processing (NLP), and technologies or software tools for corpus creation and annotation. GORILLA is designed to address the Transcription Bottleneck in language documentation, and, at the same time to provide solutions to the general Language Resource Bottleneck in speech and language technologies. It does so by facilitating the cooperation between documentary and theoretical linguistics, and speech and language technologies research and development, in particular for low-resourced and endangered languages. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1710/ |
| https://www.aclweb.org/anthology/L16-1710 | |
| PWC | https://paperswithcode.com/paper/global-open-resources-and-information-for |
| Repo | |
| Framework | |
Neural Shift-Reduce CCG Semantic Parsing
| Title | Neural Shift-Reduce CCG Semantic Parsing |
| Authors | Dipendra Kumar Misra, Yoav Artzi |
| Abstract | |
| Tasks | Amr Parsing, Decision Making, Dependency Parsing, Semantic Parsing |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1183/ |
| https://www.aclweb.org/anthology/D16-1183 | |
| PWC | https://paperswithcode.com/paper/neural-shift-reduce-ccg-semantic-parsing |
| Repo | |
| Framework | |
Visualisation and Exploration of High-Dimensional Distributional Features in Lexical Semantic Classification
| Title | Visualisation and Exploration of High-Dimensional Distributional Features in Lexical Semantic Classification |
| Authors | Maximilian K{"o}per, Melanie Zai{\ss}, Qi Han, Steffen Koch, Sabine Schulte im Walde |
| Abstract | Vector space models and distributional information are widely used in NLP. The models typically rely on complex, high-dimensional objects. We present an interactive visualisation tool to explore salient lexical-semantic features of high-dimensional word objects and word similarities. Most visualisation tools provide only one low-dimensional map of the underlying data, so they are not capable of retaining the local and the global structure. We overcome this limitation by providing an additional trust-view to obtain a more realistic picture of the actual object distances. Additional tool options include the reference to a gold standard classification, the reference to a cluster analysis as well as listing the most salient (common) features for a selected subset of the words. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1191/ |
| https://www.aclweb.org/anthology/L16-1191 | |
| PWC | https://paperswithcode.com/paper/visualisation-and-exploration-of-high |
| Repo | |
| Framework | |
CogALex-V Shared Task: LOPE
| Title | CogALex-V Shared Task: LOPE |
| Authors | Kanan Luce, Jiaxing Yu, Shu-Kai Hsieh |
| Abstract | Automatic discovery of semantically-related words is one of the most important NLP tasks, and has great impact on the theoretical psycholinguistic modeling of the mental lexicon. In this shared task, we employ the word embeddings model to testify two thoughts explicitly or implicitly assumed by the NLP community: (1). Word embedding models can reflect syntagmatic similarities in usage between words to distances in projected vector space. (2). Word embedding models can reflect paradigmatic relationships between words. |
| Tasks | Word Embeddings |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5315/ |
| https://www.aclweb.org/anthology/W16-5315 | |
| PWC | https://paperswithcode.com/paper/cogalex-v-shared-task-lope |
| Repo | |
| Framework | |
