Paper Group NANR 157
WOLVESAAR at SemEval-2016 Task 1: Replicating the Success of Monolingual Word Alignment and Neural Embeddings for Semantic Textual Similarity. SimiHawk at SemEval-2016 Task 1: A Deep Ensemble System for Semantic Textual Similarity. Korean FrameNet Expansion Based on Projection of Japanese FrameNet. Improved Word Embeddings with Implicit Structure I …
WOLVESAAR at SemEval-2016 Task 1: Replicating the Success of Monolingual Word Alignment and Neural Embeddings for Semantic Textual Similarity
| Title | WOLVESAAR at SemEval-2016 Task 1: Replicating the Success of Monolingual Word Alignment and Neural Embeddings for Semantic Textual Similarity |
| Authors | Hannah Bechara, Rohit Gupta, Liling Tan, Constantin Or{\u{a}}san, Ruslan Mitkov, Josef van Genabith |
| Abstract | |
| Tasks | Information Retrieval, Machine Translation, Semantic Textual Similarity, Text Summarization, Word Alignment, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1096/ |
| https://www.aclweb.org/anthology/S16-1096 | |
| PWC | https://paperswithcode.com/paper/wolvesaar-at-semeval-2016-task-1-replicating |
| Repo | |
| Framework | |
SimiHawk at SemEval-2016 Task 1: A Deep Ensemble System for Semantic Textual Similarity
| Title | SimiHawk at SemEval-2016 Task 1: A Deep Ensemble System for Semantic Textual Similarity |
| Authors | Peter Potash, William Boag, Alexey Romanov, Vasili Ramanishka, Anna Rumshisky |
| Abstract | |
| Tasks | Machine Translation, Natural Language Inference, Semantic Textual Similarity, Word Alignment, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1115/ |
| https://www.aclweb.org/anthology/S16-1115 | |
| PWC | https://paperswithcode.com/paper/simihawk-at-semeval-2016-task-1-a-deep |
| Repo | |
| Framework | |
Korean FrameNet Expansion Based on Projection of Japanese FrameNet
| Title | Korean FrameNet Expansion Based on Projection of Japanese FrameNet |
| Authors | Jeong-uk Kim, Younggyun Hahm, Key-Sun Choi |
| Abstract | FrameNet project has begun from Berkeley in 1997, and is now supported in several countries reflecting characteristics of each language. The work for generating Korean FrameNet was already done by converting annotated English sentences into Korean with trained translators. However, high cost of frame-preservation and error revision was a huge burden on further expansion of FrameNet. This study makes use of linguistic similarity between Japanese and Korean to increase Korean FrameNet corpus with low cost. We also suggest adapting PubAnnotation and Korean-friendly valence patterns to FrameNet for increased accessibility. |
| Tasks | Machine Translation, Reading Comprehension, Semantic Role Labeling |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2037/ |
| https://www.aclweb.org/anthology/C16-2037 | |
| PWC | https://paperswithcode.com/paper/korean-framenet-expansion-based-on-projection |
| Repo | |
| Framework | |
Improved Word Embeddings with Implicit Structure Information
| Title | Improved Word Embeddings with Implicit Structure Information |
| Authors | Jie Shen, Cong Liu |
| Abstract | Distributed word representation is an efficient method for capturing semantic and syntactic word relations. In this work, we introduce an extension to the continuous bag-of-words model for learning word representations efficiently by using implicit structure information. Instead of relying on a syntactic parser which might be noisy and slow to build, we compute weights representing probabilities of syntactic relations based on the Huffman softmax tree in an efficient heuristic. The constructed {``}implicit graphs{''} from these weights show that these weights contain useful implicit structure information. Extensive experiments performed on several word similarity and word analogy tasks show gains compared to the basic continuous bag-of-words model. | |
| Tasks | Dependency Parsing, Language Modelling, Learning Word Embeddings, Machine Translation, Part-Of-Speech Tagging, Sentiment Analysis, Word Embeddings |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1227/ |
| https://www.aclweb.org/anthology/C16-1227 | |
| PWC | https://paperswithcode.com/paper/improved-word-embeddings-with-implicit |
| Repo | |
| Framework | |
Examples are not enough, learn to criticize! Criticism for Interpretability
| Title | Examples are not enough, learn to criticize! Criticism for Interpretability |
| Authors | Been Kim, Rajiv Khanna, Oluwasanmi O. Koyejo |
| Abstract | Example-based explanations are widely used in the effort to improve the interpretability of highly complex distributions. However, prototypes alone are rarely sufficient to represent the gist of the complexity. In order for users to construct better mental models and understand complex data distributions, we also need {\em criticism} to explain what are \textit{not} captured by prototypes. Motivated by the Bayesian model criticism framework, we develop \texttt{MMD-critic} which efficiently learns prototypes and criticism, designed to aid human interpretability. A human subject pilot study shows that the \texttt{MMD-critic} selects prototypes and criticism that are useful to facilitate human understanding and reasoning. We also evaluate the prototypes selected by \texttt{MMD-critic} via a nearest prototype classifier, showing competitive performance compared to baselines. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6300-examples-are-not-enough-learn-to-criticize-criticism-for-interpretability |
| http://papers.nips.cc/paper/6300-examples-are-not-enough-learn-to-criticize-criticism-for-interpretability.pdf | |
| PWC | https://paperswithcode.com/paper/examples-are-not-enough-learn-to-criticize |
| Repo | |
| Framework | |
Arabizi Identification in Twitter Data
| Title | Arabizi Identification in Twitter Data |
| Authors | Taha Tobaili |
| Abstract | |
| Tasks | Sentiment Analysis |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-3008/ |
| https://www.aclweb.org/anthology/P16-3008 | |
| PWC | https://paperswithcode.com/paper/arabizi-identification-in-twitter-data |
| Repo | |
| Framework | |
PAT workbench: Annotation and Evaluation of Text and Pictures in Multimodal Instructions
| Title | PAT workbench: Annotation and Evaluation of Text and Pictures in Multimodal Instructions |
| Authors | Ielka van der Sluis, Lennart Kloppenburg, Gisela Redeker |
| Abstract | This paper presents a tool to investigate the design of multimodal instructions (MIs), i.e., instructions that contain both text and pictures. The benefit of including pictures in information presentation has been established, but the characteristics of those pictures and of their textual counterparts and the rela-tion(s) between them have not been researched in a systematic manner. We present the PAT Work-bench, a tool to store, annotate and retrieve MIs based on a validated coding scheme with currently 42 categories that describe instructions in terms of textual features, pictorial elements, and relations be-tween text and pictures. We describe how the PAT Workbench facilitates collaborative annotation and inter-annotator agreement calculation. Future work on the tool includes expanding its functionality and usability by (i) making the MI annotation scheme dynamic for adding relevant features based on empirical evaluations of the MIs, (ii) implementing algorithms for automatic tagging of MI features, and (iii) implementing automatic MI evaluation algorithms based on results obtained via e.g. crowdsourced assessments of MIs. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4018/ |
| https://www.aclweb.org/anthology/W16-4018 | |
| PWC | https://paperswithcode.com/paper/pat-workbench-annotation-and-evaluation-of |
| Repo | |
| Framework | |
Dictionaries as Networks: Identifying the graph structure of Ogden’s Basic English
| Title | Dictionaries as Networks: Identifying the graph structure of Ogden’s Basic English |
| Authors | Camilo Garrido, Claudio Gutierrez |
| Abstract | We study the network structure underlying dictionaries. We systematize the properties of such networks and show their relevance for linguistics. As case of study, we apply this technique to identify the graph structure of Ogden{'}s Basic English. We show that it constitutes a strong core of the English language network and that classic centrality measures fail to capture this set of words. |
| Tasks | |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1336/ |
| https://www.aclweb.org/anthology/C16-1336 | |
| PWC | https://paperswithcode.com/paper/dictionaries-as-networks-identifying-the |
| Repo | |
| Framework | |
Poet Admits // Mute Cypher: Beam Search to find Mutually Enciphering Poetic Texts
| Title | Poet Admits // Mute Cypher: Beam Search to find Mutually Enciphering Poetic Texts |
| Authors | Cole Peterson, Alona Fyshe |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1141/ |
| https://www.aclweb.org/anthology/D16-1141 | |
| PWC | https://paperswithcode.com/paper/poet-admits-mute-cypher-beam-search-to-find |
| Repo | |
| Framework | |
Shallow Discourse Parsing Using Convolutional Neural Network
| Title | Shallow Discourse Parsing Using Convolutional Neural Network |
| Authors | Lianhui Qin, Zhisong Zhang, Hai Zhao |
| Abstract | |
| Tasks | Feature Engineering, Feature Selection, Language Modelling |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/K16-2010/ |
| https://www.aclweb.org/anthology/K16-2010 | |
| PWC | https://paperswithcode.com/paper/shallow-discourse-parsing-using-convolutional |
| Repo | |
| Framework | |
What’s up on Twitter? Catch up with TWIST!
| Title | What’s up on Twitter? Catch up with TWIST! |
| Authors | Marina Litvak, Natalia Vanetik, Efi Levi, Michael Roistacher |
| Abstract | Event detection and analysis with respect to public opinions and sentiments in social media is a broad and well-addressed research topic. However, the characteristics and sheer volume of noisy Twitter messages make this a difficult task. This demonstration paper describes a TWItter event Summarizer and Trend detector (TWIST) system for event detection, visualization, textual description, and geo-sentiment analysis of real-life events reported in Twitter. |
| Tasks | Sentiment Analysis |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2045/ |
| https://www.aclweb.org/anthology/C16-2045 | |
| PWC | https://paperswithcode.com/paper/whatas-up-on-twitter-catch-up-with-twist |
| Repo | |
| Framework | |
Twitter Named Entity Extraction and Linking Using Differential Evolution
| Title | Twitter Named Entity Extraction and Linking Using Differential Evolution |
| Authors | Utpal Kumar Sikdar, Bj{"o}rn Gamb{"a}ck |
| Abstract | |
| Tasks | Entity Extraction, Entity Linking, Machine Translation, Question Answering |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-6326/ |
| https://www.aclweb.org/anthology/W16-6326 | |
| PWC | https://paperswithcode.com/paper/twitter-named-entity-extraction-and-linking |
| Repo | |
| Framework | |
WISDOM X, DISAANA and D-SUMM: Large-scale NLP Systems for Analyzing Textual Big Data
| Title | WISDOM X, DISAANA and D-SUMM: Large-scale NLP Systems for Analyzing Textual Big Data |
| Authors | Junta Mizuno, Masahiro Tanaka, Kiyonori Ohtake, Jong-Hoon Oh, Julien Kloetzer, Chikara Hashimoto, Kentaro Torisawa |
| Abstract | We demonstrate our large-scale NLP systems: WISDOM X, DISAANA, and D-SUMM. WISDOM X provides numerous possible answers including unpredictable ones to widely diverse natural language questions to provide deep insights about a broad range of issues. DISAANA and D-SUMM enable us to assess the damage caused by large-scale disasters in real time using Twitter as an information source. |
| Tasks | Open-Domain Question Answering, Question Answering |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2055/ |
| https://www.aclweb.org/anthology/C16-2055 | |
| PWC | https://paperswithcode.com/paper/wisdom-x-disaana-and-d-summ-large-scale-nlp |
| Repo | |
| Framework | |
Illinois Cross-Lingual Wikifier: Grounding Entities in Many Languages to the English Wikipedia
| Title | Illinois Cross-Lingual Wikifier: Grounding Entities in Many Languages to the English Wikipedia |
| Authors | Chen-Tse Tsai, Dan Roth |
| Abstract | We release a cross-lingual wikification system for all languages in Wikipedia. Given a piece of text in any supported language, the system identifies names of people, locations, organizations, and grounds these names to the corresponding English Wikipedia entries. The system is based on two components: a cross-lingual named entity recognition (NER) model and a cross-lingual mention grounding model. The cross-lingual NER model is a language-independent model which can extract named entity mentions in the text of any language in Wikipedia. The extracted mentions are then grounded to the English Wikipedia using the cross-lingual mention grounding model. The only resources required to train the proposed system are the multilingual Wikipedia dump and existing training data for English NER. The system is online at \url{http://cogcomp.cs.illinois.edu/page/demo_view/xl_wikifier} |
| Tasks | Entity Linking, Named Entity Recognition, Tokenization |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-2031/ |
| https://www.aclweb.org/anthology/C16-2031 | |
| PWC | https://paperswithcode.com/paper/illinois-cross-lingual-wikifier-grounding |
| Repo | |
| Framework | |
Deep Learning of Audio and Language Features for Humor Prediction
| Title | Deep Learning of Audio and Language Features for Humor Prediction |
| Authors | Dario Bertero, Pascale Fung |
| Abstract | We propose a comparison between various supervised machine learning methods to predict and detect humor in dialogues. We retrieve our humorous dialogues from a very popular TV sitcom: {``}The Big Bang Theory{''}. We build a corpus where punchlines are annotated using the canned laughter embedded in the audio track. Our comparative study involves a linear-chain Conditional Random Field over a Recurrent Neural Network and a Convolutional Neural Network. Using a combination of word-level and audio frame-level features, the CNN outperforms the other methods, obtaining the best F-score of 68.5{%} over 66.5{%} by CRF and 52.9{%} by RNN. Our work is a starting point to developing more effective machine learning and neural network models on the humor prediction task, as well as developing machines capable in understanding humor in general. | |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1079/ |
| https://www.aclweb.org/anthology/L16-1079 | |
| PWC | https://paperswithcode.com/paper/deep-learning-of-audio-and-language-features |
| Repo | |
| Framework | |
