Paper Group NANR 222
The red one!: On learning to refer to things based on discriminative properties. Two-View Label Propagation to Semi-supervised Reader Emotion Classification. An Unsupervised Method for Automatic Translation Memory Cleaning. Towards Generalizable Sentence Embeddings. Compositional Learning of Embeddings for Relation Paths in Knowledge Base and Text. …
The red one!: On learning to refer to things based on discriminative properties
| Title | The red one!: On learning to refer to things based on discriminative properties |
| Authors | Angeliki Lazaridou, Nghia The Pham, Marco Baroni |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2035/ |
| https://www.aclweb.org/anthology/P16-2035 | |
| PWC | https://paperswithcode.com/paper/the-red-one-on-learning-to-refer-to-things |
| Repo | |
| Framework | |
Two-View Label Propagation to Semi-supervised Reader Emotion Classification
| Title | Two-View Label Propagation to Semi-supervised Reader Emotion Classification |
| Authors | Shoushan Li, Jian Xu, Dong Zhang, Guodong Zhou |
| Abstract | In the literature, various supervised learning approaches have been adopted to address the task of reader emotion classification. However, the classification performance greatly suffers when the size of the labeled data is limited. In this paper, we propose a two-view label propagation approach to semi-supervised reader emotion classification by exploiting two views, namely source text and response text in a label propagation algorithm. Specifically, our approach depends on two word-document bipartite graphs to model the relationship among the samples in the two views respectively. Besides, the two bipartite graphs are integrated by linking each source text sample with its corresponding response text sample via a length-sensitive transition probability. In this way, our two-view label propagation approach to semi-supervised reader emotion classification largely alleviates the reliance on the strong sufficiency and independence assumptions of the two views, as required in co-training. Empirical evaluation demonstrates the effectiveness of our two-view label propagation approach to semi-supervised reader emotion classification. |
| Tasks | Emotion Classification |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1249/ |
| https://www.aclweb.org/anthology/C16-1249 | |
| PWC | https://paperswithcode.com/paper/two-view-label-propagation-to-semi-supervised |
| Repo | |
| Framework | |
An Unsupervised Method for Automatic Translation Memory Cleaning
| Title | An Unsupervised Method for Automatic Translation Memory Cleaning |
| Authors | Masoud Jalili Sabet, Matteo Negri, Marco Turchi, Eduard Barbu |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2047/ |
| https://www.aclweb.org/anthology/P16-2047 | |
| PWC | https://paperswithcode.com/paper/an-unsupervised-method-for-automatic |
| Repo | |
| Framework | |
Towards Generalizable Sentence Embeddings
| Title | Towards Generalizable Sentence Embeddings |
| Authors | Eleni Triantafillou, Jamie Ryan Kiros, Raquel Urtasun, Richard Zemel |
| Abstract | |
| Tasks | Information Retrieval, Natural Language Inference, One-Shot Learning, Representation Learning, Sentence Embeddings, Text Summarization, Transfer Learning |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1628/ |
| https://www.aclweb.org/anthology/W16-1628 | |
| PWC | https://paperswithcode.com/paper/towards-generalizable-sentence-embeddings |
| Repo | |
| Framework | |
Compositional Learning of Embeddings for Relation Paths in Knowledge Base and Text
| Title | Compositional Learning of Embeddings for Relation Paths in Knowledge Base and Text |
| Authors | Kristina Toutanova, Victoria Lin, Wen-tau Yih, Hoifung Poon, Chris Quirk |
| Abstract | |
| Tasks | Open-Domain Question Answering, Question Answering, Relational Reasoning |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-1136/ |
| https://www.aclweb.org/anthology/P16-1136 | |
| PWC | https://paperswithcode.com/paper/compositional-learning-of-embeddings-for |
| Repo | |
| Framework | |
SAMER: A Semi-Automatically Created Lexical Resource for Arabic Verbal Multiword Expressions Tokens Paradigm and their Morphosyntactic Features
| Title | SAMER: A Semi-Automatically Created Lexical Resource for Arabic Verbal Multiword Expressions Tokens Paradigm and their Morphosyntactic Features |
| Authors | Mohamed Al-Badrashiny, Abdelati Hawwari, Mahmoud Ghoneim, Mona Diab |
| Abstract | Although MWE are relatively morphologically and syntactically fixed expressions, several types of flexibility can be observed in MWE, verbal MWE in particular. Identifying the degree of morphological and syntactic flexibility of MWE is very important for many Lexicographic and NLP tasks. Adding MWE variants/tokens to a dictionary resource requires characterizing the flexibility among other morphosyntactic features. Carrying out the task manually faces several challenges since it is a very laborious task time and effort wise, as well as it will suffer from coverage limitation. The problem is exacerbated in rich morphological languages where the average word in Arabic could have 12 possible inflection forms. Accordingly, in this paper we introduce a semi-automatic Arabic multiwords expressions resource (SAMER). We propose an automated method that identifies the morphological and syntactic flexibility of Arabic Verbal Multiword Expressions (AVMWE). All observed morphological variants and syntactic pattern alternations of an AVMWE are automatically acquired using large scale corpora. We look for three morphosyntactic aspects of AVMWE types investigating derivational and inflectional variations and syntactic templates, namely: 1) inflectional variation (inflectional paradigm) and calculating degree of flexibility; 2) derivational productivity; and 3) identifying and classifying the different syntactic types. We build a comprehensive list of AVMWE. Every token in the AVMWE list is lemmatized and tagged with POS information. We then search Arabic Gigaword and All ATBs for all possible flexible matches. For each AVMWE type we generate: a) a statistically ranked list of MWE-lexeme inflections and syntactic pattern alternations; b) An abstract syntactic template; and c) The most frequent form. Our technique is validated using a Golden MWE annotated list. The results shows that the quality of the generated resource is 80.04{%}. |
| Tasks | Machine Translation |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5414/ |
| https://www.aclweb.org/anthology/W16-5414 | |
| PWC | https://paperswithcode.com/paper/samer-a-semi-automatically-created-lexical |
| Repo | |
| Framework | |
Automatic Text Generation by Learning from Literary Structures
| Title | Automatic Text Generation by Learning from Literary Structures |
| Authors | Angel Daza, Hiram Calvo, Jes{'u}s Figueroa-Nazuno |
| Abstract | |
| Tasks | Common Sense Reasoning, Text Generation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0202/ |
| https://www.aclweb.org/anthology/W16-0202 | |
| PWC | https://paperswithcode.com/paper/automatic-text-generation-by-learning-from |
| Repo | |
| Framework | |
Learning Translations for Tagged Words: Extending the Translation Lexicon of an ITG for Low Resource Languages
| Title | Learning Translations for Tagged Words: Extending the Translation Lexicon of an ITG for Low Resource Languages |
| Authors | Markus Saers, Dekai Wu |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1207/ |
| https://www.aclweb.org/anthology/W16-1207 | |
| PWC | https://paperswithcode.com/paper/learning-translations-for-tagged-words |
| Repo | |
| Framework | |
OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles
| Title | OpenSubtitles2016: Extracting Large Parallel Corpora from Movie and TV Subtitles |
| Authors | Pierre Lison, J{"o}rg Tiedemann |
| Abstract | We present a new major release of the OpenSubtitles collection of parallel corpora. The release is compiled from a large database of movie and TV subtitles and includes a total of 1689 bitexts spanning 2.6 billion sentences across 60 languages. The release also incorporates a number of enhancements in the preprocessing and alignment of the subtitles, such as the automatic correction of OCR errors and the use of meta-data to estimate the quality of each subtitle and score subtitle pairs. |
| Tasks | Optical Character Recognition |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1147/ |
| https://www.aclweb.org/anthology/L16-1147 | |
| PWC | https://paperswithcode.com/paper/opensubtitles2016-extracting-large-parallel |
| Repo | |
| Framework | |
Author Name Disambiguation in MEDLINE Based on Journal Descriptors and Semantic Types
| Title | Author Name Disambiguation in MEDLINE Based on Journal Descriptors and Semantic Types |
| Authors | Dina Vishnyakova, Raul Rodriguez-Esteban, Khan Ozol, Fabio Rinaldi |
| Abstract | Author name disambiguation (AND) in publication and citation resources is a well-known problem. Often, information about email address and other details in the affiliation is missing. In cases where such information is not available, identifying the authorship of publications becomes very challenging. Consequently, there have been attempts to resolve such cases by utilizing external resources as references. However, such external resources are heterogeneous and are not always reliable regarding the correctness of information. To solve the AND task, especially when information about an author is not complete we suggest the use of new features such as journal descriptors (JD) and semantic types (ST). The evaluation of different feature models shows that their inclusion has an impact equivalent to that of other important features such as email address. Using such features we show that our system outperforms the state of the art. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-5115/ |
| https://www.aclweb.org/anthology/W16-5115 | |
| PWC | https://paperswithcode.com/paper/author-name-disambiguation-in-medline-based |
| Repo | |
| Framework | |
Pynini: A Python library for weighted finite-state grammar compilation
| Title | Pynini: A Python library for weighted finite-state grammar compilation |
| Authors | Kyle Gorman |
| Abstract | |
| Tasks | Optical Character Recognition, Speech Recognition |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2409/ |
| https://www.aclweb.org/anthology/W16-2409 | |
| PWC | https://paperswithcode.com/paper/pynini-a-python-library-for-weighted-finite |
| Repo | |
| Framework | |
DUEL: A Multi-lingual Multimodal Dialogue Corpus for Disfluency, Exclamations and Laughter
| Title | DUEL: A Multi-lingual Multimodal Dialogue Corpus for Disfluency, Exclamations and Laughter |
| Authors | Julian Hough, Ye Tian, Laura de Ruiter, Simon Betz, Spyros Kousidis, David Schlangen, Jonathan Ginzburg |
| Abstract | We present the DUEL corpus, consisting of 24 hours of natural, face-to-face, loosely task-directed dialogue in German, French and Mandarin Chinese. The corpus is uniquely positioned as a cross-linguistic, multimodal dialogue resource controlled for domain. DUEL includes audio, video and body tracking data and is transcribed and annotated for disfluency, laughter and exclamations. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1281/ |
| https://www.aclweb.org/anthology/L16-1281 | |
| PWC | https://paperswithcode.com/paper/duel-a-multi-lingual-multimodal-dialogue |
| Repo | |
| Framework | |
From Extractive to Abstractive Summarization: A Journey
| Title | From Extractive to Abstractive Summarization: A Journey |
| Authors | Parth Mehta |
| Abstract | |
| Tasks | Abstractive Text Summarization, Information Retrieval, Machine Translation, Text Generation, Text Summarization |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-3015/ |
| https://www.aclweb.org/anthology/P16-3015 | |
| PWC | https://paperswithcode.com/paper/from-extractive-to-abstractive-summarization |
| Repo | |
| Framework | |
Unsupervised Authorial Clustering Based on Syntactic Structure
| Title | Unsupervised Authorial Clustering Based on Syntactic Structure |
| Authors | Alon Daks, Aidan Clark |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-3017/ |
| https://www.aclweb.org/anthology/P16-3017 | |
| PWC | https://paperswithcode.com/paper/unsupervised-authorial-clustering-based-on |
| Repo | |
| Framework | |
Real-Time Discovery and Geospatial Visualization of Mobility and Industry Events from Large-Scale, Heterogeneous Data Streams
| Title | Real-Time Discovery and Geospatial Visualization of Mobility and Industry Events from Large-Scale, Heterogeneous Data Streams |
| Authors | Leonhard Hennig, Philippe Thomas, Renlong Ai, Johannes Kirschnick, He Wang, Jakob Pannier, Nora Zimmermann, Sven Schmeier, Feiyu Xu, Jan Ostwald, Hans Uszkoreit |
| Abstract | |
| Tasks | Decision Making, Domain Adaptation, Named Entity Recognition |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-4007/ |
| https://www.aclweb.org/anthology/P16-4007 | |
| PWC | https://paperswithcode.com/paper/real-time-discovery-and-geospatial |
| Repo | |
| Framework | |
