Paper Group NANR 118
International Journal of Computational Linguistics & Chinese Language Processing, Volume 22, Number 1, June 2017. Online Learning for Multivariate Hawkes Processes. Real-Time News Summarization with Adaptation to Media Attention. Biomedical Event Extraction using Abstract Meaning Representation. Unsupervised Context-Sensitive Spelling Correction o …
International Journal of Computational Linguistics & Chinese Language Processing, Volume 22, Number 1, June 2017
| Title | International Journal of Computational Linguistics & Chinese Language Processing, Volume 22, Number 1, June 2017 |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-06-01 |
| URL | https://www.aclweb.org/anthology/O17-2000/ |
| https://www.aclweb.org/anthology/O17-2000 | |
| PWC | https://paperswithcode.com/paper/international-journal-of-computational-10 |
| Repo | |
| Framework | |
Online Learning for Multivariate Hawkes Processes
| Title | Online Learning for Multivariate Hawkes Processes |
| Authors | Yingxiang Yang, Jalal Etesami, Niao He, Negar Kiyavash |
| Abstract | We develop a nonparametric and online learning algorithm that estimates the triggering functions of a multivariate Hawkes process (MHP). The approach we take approximates the triggering function $f_{i,j}(t)$ by functions in a reproducing kernel Hilbert space (RKHS), and maximizes a time-discretized version of the log-likelihood, with Tikhonov regularization. Theoretically, our algorithm achieves an $\calO(\log T)$ regret bound. Numerical results show that our algorithm offers a competing performance to that of the nonparametric batch learning algorithm, with a run time comparable to the parametric online learning algorithm. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7079-online-learning-for-multivariate-hawkes-processes |
| http://papers.nips.cc/paper/7079-online-learning-for-multivariate-hawkes-processes.pdf | |
| PWC | https://paperswithcode.com/paper/online-learning-for-multivariate-hawkes |
| Repo | |
| Framework | |
Real-Time News Summarization with Adaptation to Media Attention
| Title | Real-Time News Summarization with Adaptation to Media Attention |
| Authors | Andreas R{"u}ckl{'e}, Iryna Gurevych |
| Abstract | Real-time summarization of news events (RTS) allows persons to stay up-to-date on important topics that develop over time. With the occurrence of major sub-events, media attention increases and a large number of news articles are published. We propose a summarization approach that detects such changes and selects a suitable summarization configuration at run-time. In particular, at times with high media attention, our approach exploits the redundancy in content to produce a more precise summary and avoid emitting redundant information. We find that our approach significantly outperforms a strong non-adaptive RTS baseline in terms of the emitted summary updates and achieves the best results on a recent web-scale dataset. It can successfully be applied to a different real-world dataset without requiring additional modifications. |
| Tasks | Decision Making |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1079/ |
| https://doi.org/10.26615/978-954-452-049-6_079 | |
| PWC | https://paperswithcode.com/paper/real-time-news-summarization-with-adaptation |
| Repo | |
| Framework | |
Biomedical Event Extraction using Abstract Meaning Representation
| Title | Biomedical Event Extraction using Abstract Meaning Representation |
| Authors | Sudha Rao, Daniel Marcu, Kevin Knight, Hal Daum{'e} III |
| Abstract | We propose a novel, Abstract Meaning Representation (AMR) based approach to identifying molecular events/interactions in biomedical text. Our key contributions are: (1) an empirical validation of our hypothesis that an event is a subgraph of the AMR graph, (2) a neural network-based model that identifies such an event subgraph given an AMR, and (3) a distant supervision based approach to gather additional training data. We evaluate our approach on the 2013 Genia Event Extraction dataset and show promising results. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2315/ |
| https://www.aclweb.org/anthology/W17-2315 | |
| PWC | https://paperswithcode.com/paper/biomedical-event-extraction-using-abstract |
| Repo | |
| Framework | |
Unsupervised Context-Sensitive Spelling Correction of Clinical Free-Text with Word and Character N-Gram Embeddings
| Title | Unsupervised Context-Sensitive Spelling Correction of Clinical Free-Text with Word and Character N-Gram Embeddings |
| Authors | Pieter Fivez, Simon {\v{S}}uster, Walter Daelemans |
| Abstract | We present an unsupervised context-sensitive spelling correction method for clinical free-text that uses word and character n-gram embeddings. Our method generates misspelling replacement candidates and ranks them according to their semantic fit, by calculating a weighted cosine similarity between the vectorized representation of a candidate and the misspelling context. We greatly outperform two baseline off-the-shelf spelling correction tools on a manually annotated MIMIC-III test set, and counter the frequency bias of an optimized noisy channel model, showing that neural embeddings can be successfully exploited to include context-awareness in a spelling correction model. |
| Tasks | Spelling Correction |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2317/ |
| https://www.aclweb.org/anthology/W17-2317 | |
| PWC | https://paperswithcode.com/paper/unsupervised-context-sensitive-spelling |
| Repo | |
| Framework | |
Intension, Attitude, and Tense Annotation in a High-Fidelity Semantic Representation
| Title | Intension, Attitude, and Tense Annotation in a High-Fidelity Semantic Representation |
| Authors | Gene Kim, Lenhart Schubert |
| Abstract | This paper describes current efforts in developing an annotation schema and guidelines for sentences in Episodic Logic (EL). We focus on important distinctions for representing modality, attitudes, and tense and present an annotation schema that makes these distinctions. EL has proved competitive with other logical formulations in speed and inference-enablement, while expressing a wider array of natural language phenomena including intensional modification of predicates and sentences, propositional attitudes, and tense and aspect. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1802/ |
| https://www.aclweb.org/anthology/W17-1802 | |
| PWC | https://paperswithcode.com/paper/intension-attitude-and-tense-annotation-in-a |
| Repo | |
| Framework | |
NTNU-1@ScienceIE at SemEval-2017 Task 10: Identifying and Labelling Keyphrases with Conditional Random Fields
| Title | NTNU-1@ScienceIE at SemEval-2017 Task 10: Identifying and Labelling Keyphrases with Conditional Random Fields |
| Authors | Erwin Marsi, Utpal Kumar Sikdar, Cristina Marco, Biswanath Barik, Rune S{\ae}tre |
| Abstract | We present NTNU{'}s systems for Task A (prediction of keyphrases) and Task B (labelling as Material, Process or Task) at SemEval 2017 Task 10: Extracting Keyphrases and Relations from Scientific Publications (Augenstein et al., 2017). Our approach relies on supervised machine learning using Conditional Random Fields. Our system yields a micro F-score of 0.34 for Tasks A and B combined on the test data. For Task C (relation extraction), we relied on an independently developed system described in (Barik and Marsi, 2017). For the full Scenario 1 (including relations), our approach reaches a micro F-score of 0.33 (5th place). Here we describe our systems, report results and discuss errors. |
| Tasks | Dependency Parsing, Named Entity Recognition, Relation Extraction |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2162/ |
| https://www.aclweb.org/anthology/S17-2162 | |
| PWC | https://paperswithcode.com/paper/ntnu-1scienceie-at-semeval-2017-task-10 |
| Repo | |
| Framework | |
Characterization of Divergence in Impaired Speech of ALS Patients
| Title | Characterization of Divergence in Impaired Speech of ALS Patients |
| Authors | Archna Bhatia, Bonnie Dorr, Kristy Hollingshead, Samuel L. Phillips, Barbara McKenzie |
| Abstract | Approximately 80{%} to 95{%} of patients with Amyotrophic Lateral Sclerosis (ALS) eventually develop speech impairments, such as defective articulation, slow laborious speech and hypernasality. The relationship between impaired speech and asymptomatic speech may be seen as a divergence from a baseline. This relationship can be characterized in terms of measurable combinations of phonological characteristics that are indicative of the degree to which the two diverge. We demonstrate that divergence measurements based on phonological characteristics of speech correlate with physiological assessments of ALS. Speech-based assessments offer benefits over commonly-used physiological assessments in that they are inexpensive, non-intrusive, and do not require trained clinical personnel for administering and interpreting the results. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2318/ |
| https://www.aclweb.org/anthology/W17-2318 | |
| PWC | https://paperswithcode.com/paper/characterization-of-divergence-in-impaired |
| Repo | |
| Framework | |
An End-to-End Deep Framework for Answer Triggering with a Novel Group-Level Objective
| Title | An End-to-End Deep Framework for Answer Triggering with a Novel Group-Level Objective |
| Authors | Jie Zhao, Yu Su, Ziyu Guan, Huan Sun |
| Abstract | Given a question and a set of answer candidates, answer triggering determines whether the candidate set contains any correct answers. If yes, it then outputs a correct one. In contrast to existing pipeline methods which first consider individual candidate answers separately and then make a prediction based on a threshold, we propose an end-to-end deep neural network framework, which is trained by a novel group-level objective function that directly optimizes the answer triggering performance. Our objective function penalizes three potential types of error and allows training the framework in an end-to-end manner. Experimental results on the WikiQA benchmark show that our framework outperforms the state of the arts by a 6.6{%} absolute gain under F1 measure. |
| Tasks | Multiple Instance Learning, Question Answering |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1131/ |
| https://www.aclweb.org/anthology/D17-1131 | |
| PWC | https://paperswithcode.com/paper/an-end-to-end-deep-framework-for-answer |
| Repo | |
| Framework | |
Annotating tense, mood and voice for English, French and German
| Title | Annotating tense, mood and voice for English, French and German |
| Authors | Anita Ramm, Sharid Lo{'a}iciga, Annemarie Friedrich, Alex Fraser, er |
| Abstract | |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-4001/ |
| https://www.aclweb.org/anthology/P17-4001 | |
| PWC | https://paperswithcode.com/paper/annotating-tense-mood-and-voice-for-english |
| Repo | |
| Framework | |
Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing
| Title | Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing |
| Authors | |
| Abstract | |
| Tasks | Structured Prediction |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4300/ |
| https://www.aclweb.org/anthology/W17-4300 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2nd-workshop-on-structured |
| Repo | |
| Framework | |
Consistent k-Clustering
| Title | Consistent k-Clustering |
| Authors | Silvio Lattanzi, Sergei Vassilvitskii |
| Abstract | The study of online algorithms and competitive analysis provides a solid foundation for studying the quality of irrevocable decision making when the data arrives in an online manner. While in some scenarios the decisions are indeed irrevocable, there are many practical situations when changing a previous decision is not impossible, but simply expensive. In this work we formalize this notion and introduce the consistent k-clustering problem. With points arriving online, the goal is to maintain a constant approximate solution, while minimizing the number of reclusterings necessary. We prove a lower bound, showing that $\Omega(k \log n)$ changes are necessary in the worst case for a wide range of objective functions. On the positive side, we give an algorithm that needs only $O(k^2 \log^4n)$ changes to maintain a constant competitive solution, an exponential improvement on the naive solution of reclustering at every time step. Finally, we show experimentally that our approach performs much better than the theoretical bound, with the number of changes growing approximately as $O(\log n)$. |
| Tasks | Decision Making |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=588 |
| http://proceedings.mlr.press/v70/lattanzi17a/lattanzi17a.pdf | |
| PWC | https://paperswithcode.com/paper/consistent-k-clustering |
| Repo | |
| Framework | |
Book Review: Linked Lexical Knowledge Bases Foundations and Applications by Iryna Gurevych, Judith Eckle-er and Michael Matuschek
| Title | Book Review: Linked Lexical Knowledge Bases Foundations and Applications by Iryna Gurevych, Judith Eckle-er and Michael Matuschek |
| Authors | Maud Ehrmann |
| Abstract | |
| Tasks | Information Retrieval, Question Answering, Word Sense Disambiguation |
| Published | 2017-06-01 |
| URL | https://www.aclweb.org/anthology/J17-2007/ |
| https://www.aclweb.org/anthology/J17-2007 | |
| PWC | https://paperswithcode.com/paper/book-review-linked-lexical-knowledge-bases |
| Repo | |
| Framework | |
Event Timeline Generation from History Textbooks
| Title | Event Timeline Generation from History Textbooks |
| Authors | Harsimran Bedi, Sangameshwar Patil, Swapnil Hingmire, Girish Palshikar |
| Abstract | Event timeline serves as the basic structure of history, and it is used as a disposition of key phenomena in studying history as a subject in secondary school. In order to enable a student to understand a historical phenomenon as a series of connected events, we present a system for automatic event timeline generation from history textbooks. Additionally, we propose Message Sequence Chart (MSC) and time-map based visualization techniques to visualize an event timeline. We also identify key computational challenges in developing natural language processing based applications for history textbooks. |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-5912/ |
| https://www.aclweb.org/anthology/W17-5912 | |
| PWC | https://paperswithcode.com/paper/event-timeline-generation-from-history |
| Repo | |
| Framework | |
A Dataset for Multi-Target Stance Detection
| Title | A Dataset for Multi-Target Stance Detection |
| Authors | Parinaz Sobhani, Diana Inkpen, Xiaodan Zhu |
| Abstract | Current models for stance classification often treat each target independently, but in many applications, there exist natural dependencies among targets, e.g., stance towards two or more politicians in an election or towards several brands of the same product. In this paper, we focus on the problem of multi-target stance detection. We present a new dataset that we built for this task. Furthermore, We experiment with several neural models on the dataset and show that they are more effective in jointly modeling the overall position towards two related targets compared to independent predictions and other models of joint learning, such as cascading classification. We make the new dataset publicly available, in order to facilitate further research in multi-target stance classification. |
| Tasks | Stance Detection |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2088/ |
| https://www.aclweb.org/anthology/E17-2088 | |
| PWC | https://paperswithcode.com/paper/a-dataset-for-multi-target-stance-detection |
| Repo | |
| Framework | |
