Paper Group NANR 165
Robust Coreference Resolution and Entity Linking on Dialogues: Character Identification on TV Show Transcripts. Will my auxiliary tagging task help? Estimating Auxiliary Tasks Effectivity in Multi-Task Learning. CIC-FBK Approach to Native Language Identification. Carrier Sentence Selection for Fill-in-the-blank Items. Vision and Language Integratio …
Robust Coreference Resolution and Entity Linking on Dialogues: Character Identification on TV Show Transcripts
| Title | Robust Coreference Resolution and Entity Linking on Dialogues: Character Identification on TV Show Transcripts |
| Authors | Henry Y. Chen, Ethan Zhou, Jinho D. Choi |
| Abstract | This paper presents a novel approach to character identification, that is an entity linking task that maps mentions to characters in dialogues from TV show transcripts. We first augment and correct several cases of annotation errors in an existing corpus so the corpus is clearer and cleaner for statistical learning. We also introduce the agglomerative convolutional neural network that takes groups of features and learns mention and mention-pair embeddings for coreference resolution. We then propose another neural model that employs the embeddings learned and creates cluster embeddings for entity linking. Our coreference resolution model shows comparable results to other state-of-the-art systems. Our entity linking model significantly outperforms the previous work, showing the F1 score of 86.76{%} and the accuracy of 95.30{%} for character identification. |
| Tasks | Coreference Resolution, Entity Linking, Entity Resolution, Question Answering |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-1023/ |
| https://www.aclweb.org/anthology/K17-1023 | |
| PWC | https://paperswithcode.com/paper/robust-coreference-resolution-and-entity |
| Repo | |
| Framework | |
Will my auxiliary tagging task help? Estimating Auxiliary Tasks Effectivity in Multi-Task Learning
| Title | Will my auxiliary tagging task help? Estimating Auxiliary Tasks Effectivity in Multi-Task Learning |
| Authors | Johannes Bjerva |
| Abstract | |
| Tasks | Multi-Task Learning |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0225/ |
| https://www.aclweb.org/anthology/W17-0225 | |
| PWC | https://paperswithcode.com/paper/will-my-auxiliary-tagging-task-help |
| Repo | |
| Framework | |
CIC-FBK Approach to Native Language Identification
| Title | CIC-FBK Approach to Native Language Identification |
| Authors | Ilia Markov, Lingzhen Chen, Carlo Strapparava, Grigori Sidorov |
| Abstract | We present the CIC-FBK system, which took part in the Native Language Identification (NLI) Shared Task 2017. Our approach combines features commonly used in previous NLI research, i.e., word n-grams, lemma n-grams, part-of-speech n-grams, and function words, with recently introduced character n-grams from misspelled words, and features that are novel in this task, such as typed character n-grams, and syntactic n-grams of words and of syntactic relation tags. We use log-entropy weighting scheme and perform classification using the Support Vector Machines (SVM) algorithm. Our system achieved 0.8808 macro-averaged F1-score and shared the 1st rank in the NLI Shared Task 2017 scoring. |
| Tasks | Language Identification, Native Language Identification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5042/ |
| https://www.aclweb.org/anthology/W17-5042 | |
| PWC | https://paperswithcode.com/paper/cic-fbk-approach-to-native-language |
| Repo | |
| Framework | |
Carrier Sentence Selection for Fill-in-the-blank Items
| Title | Carrier Sentence Selection for Fill-in-the-blank Items |
| Authors | Shu Jiang, John Lee |
| Abstract | Fill-in-the-blank items are a common form of exercise in computer-assisted language learning systems. To automatically generate an effective item, the system must be able to select a high-quality carrier sentence that illustrates the usage of the target word. Previous approaches for carrier sentence selection have considered sentence length, vocabulary difficulty, the position of the target word and the presence of finite verbs. This paper investigates the utility of word co-occurrence statistics and lexical similarity as selection criteria. In an evaluation on generating fill-in-the-blank items for learning Chinese as a foreign language, we show that these two criteria can improve carrier sentence quality. |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-5903/ |
| https://www.aclweb.org/anthology/W17-5903 | |
| PWC | https://paperswithcode.com/paper/carrier-sentence-selection-for-fill-in-the |
| Repo | |
| Framework | |
Vision and Language Integration: Moving beyond Objects
| Title | Vision and Language Integration: Moving beyond Objects |
| Authors | Ravi Shekhar, S Pezzelle, ro, Aur{'e}lie Herbelot, Moin Nabi, Enver Sangineto, Raffaella Bernardi |
| Abstract | |
| Tasks | Action Classification, Image Captioning, Object Classification, Question Answering, Visual Question Answering |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6938/ |
| https://www.aclweb.org/anthology/W17-6938 | |
| PWC | https://paperswithcode.com/paper/vision-and-language-integration-moving-beyond |
| Repo | |
| Framework | |
Hindi Shabdamitra: A Wordnet based E-Learning Tool for Language Learning and Teaching
| Title | Hindi Shabdamitra: A Wordnet based E-Learning Tool for Language Learning and Teaching |
| Authors | Hanumant Redkar, S Singh, hya, Meenakshi Somasundaram, Dhara Gorasia, Malhar Kulkarni, Pushpak Bhattacharyya |
| Abstract | In today{'}s technology driven digital era, education domain is undergoing a transformation from traditional approaches to more learner controlled and flexible methods of learning. This transformation has opened the new avenues for interdisciplinary research in the field of educational technology and natural language processing in developing quality digital aids for learning and teaching. The tool presented here - Hindi Shabhadamitra, developed using Hindi Wordnet for Hindi language learning, is one such e-learning tool. It has been developed as a teaching and learning aid suitable for formal school based curriculum and informal setup for self learning users. Besides vocabulary, it also provides word based grammar along with images and pronunciation for better learning and retention. This aid demonstrates that how a rich lexical resource like wordnet can be systematically remodeled for practical usage in the educational domain. |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-5904/ |
| https://www.aclweb.org/anthology/W17-5904 | |
| PWC | https://paperswithcode.com/paper/hindi-shabdamitra-a-wordnet-based-e-learning |
| Repo | |
| Framework | |
Suggesting Sentences for ESL using Kernel Embeddings
| Title | Suggesting Sentences for ESL using Kernel Embeddings |
| Authors | Kent Shioda, Mamoru Komachi, Rue Ikeya, Daichi Mochihashi |
| Abstract | Sentence retrieval is an important NLP application for English as a Second Language (ESL) learners. ESL learners are familiar with web search engines, but generic web search results may not be adequate for composing documents in a specific domain. However, if we build our own search system specialized to a domain, it may be subject to the data sparseness problem. Recently proposed word2vec partially addresses the data sparseness problem, but fails to extract sentences relevant to queries owing to the modeling of the latent intent of the query. Thus, we propose a method of retrieving example sentences using kernel embeddings and N-gram windows. This method implicitly models latent intent of query and sentences, and alleviates the problem of noisy alignment. Our results show that our method achieved higher precision in sentence retrieval for ESL in the domain of a university press release corpus, as compared to a previous unsupervised method used for a semantic textual similarity task. |
| Tasks | Semantic Textual Similarity |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-5911/ |
| https://www.aclweb.org/anthology/W17-5911 | |
| PWC | https://paperswithcode.com/paper/suggesting-sentences-for-esl-using-kernel |
| Repo | |
| Framework | |
The Sentimental Value of Chinese Sub-Character Components
| Title | The Sentimental Value of Chinese Sub-Character Components |
| Authors | Yassine Benajiba, Or Biran, Zhiliang Weng, Yong Zhang, Jin Sun |
| Abstract | Sub-character components of Chinese characters carry important semantic information, and recent studies have shown that utilizing this information can improve performance on core semantic tasks. In this paper, we hypothesize that in addition to semantic information, sub-character components may also carry emotional information, and that utilizing it should improve performance on sentiment analysis tasks. We conduct a series of experiments on four Chinese sentiment data sets and show that we can significantly improve the performance in various tasks over that of a character-level embeddings baseline. We then focus on qualitatively assessing multiple examples and trying to explain how the sub-character components affect the results in each case. |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-6003/ |
| https://www.aclweb.org/anthology/W17-6003 | |
| PWC | https://paperswithcode.com/paper/the-sentimental-value-of-chinese-sub |
| Repo | |
| Framework | |
Character Sequence-to-Sequence Model with Global Attention for Universal Morphological Reinflection
| Title | Character Sequence-to-Sequence Model with Global Attention for Universal Morphological Reinflection |
| Authors | Qile Zhu, Yanjun Li, Xiaolin Li |
| Abstract | |
| Tasks | Machine Translation, Question Answering |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-2009/ |
| https://www.aclweb.org/anthology/K17-2009 | |
| PWC | https://paperswithcode.com/paper/character-sequence-to-sequence-model-with |
| Repo | |
| Framework | |
基於鑑別式自編碼解碼器之錄音回放攻擊偵測系統 (A Replay Spoofing Detection System Based on Discriminative Autoencoders) [In Chinese]
| Title | 基於鑑別式自編碼解碼器之錄音回放攻擊偵測系統 (A Replay Spoofing Detection System Based on Discriminative Autoencoders) [In Chinese] |
| Authors | Yu-Ding Lu, Hung-Shin Lee, Yu Tsao, Hsin-Min Wang |
| Abstract | |
| Tasks | Speaker Verification |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/O17-1010/ |
| https://www.aclweb.org/anthology/O17-1010 | |
| PWC | https://paperswithcode.com/paper/ao14eaa14eac-c14ec14a-a1ee3a34a-c3c-a-replay-1 |
| Repo | |
| Framework | |
Rule-Enhanced Penalized Regression by Column Generation using Rectangular Maximum Agreement
| Title | Rule-Enhanced Penalized Regression by Column Generation using Rectangular Maximum Agreement |
| Authors | Jonathan Eckstein, Noam Goldberg, Ai Kagawa |
| Abstract | We describe a learning procedure enhancing L1-penalized regression by adding dynamically generated rules describing multidimensional “box” sets. Our rule-adding procedure is based on the classical column generation method for high-dimensional linear programming. The pricing problem for our column generation procedure reduces to the NP-hard rectangular maximum agreement (RMA) problem of finding a box that best discriminates between two weighted datasets. We solve this problem exactly using a parallel branch-and-bound procedure. The resulting rule-enhanced regression procedure is computation-intensive, but has promising prediction performance. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=604 |
| http://proceedings.mlr.press/v70/eckstein17a/eckstein17a.pdf | |
| PWC | https://paperswithcode.com/paper/rule-enhanced-penalized-regression-by-column |
| Repo | |
| Framework | |
Coordination in TAG without the Conjoin Operation
| Title | Coordination in TAG without the Conjoin Operation |
| Authors | Chung-hye Han, Anoop Sarkar |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6205/ |
| https://www.aclweb.org/anthology/W17-6205 | |
| PWC | https://paperswithcode.com/paper/coordination-in-tag-without-the-conjoin |
| Repo | |
| Framework | |
Multiword Expression-Aware A* TAG Parsing Revisited
| Title | Multiword Expression-Aware A* TAG Parsing Revisited |
| Authors | Jakub Waszczuk, Agata Savary, Yannick Parmentier |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6209/ |
| https://www.aclweb.org/anthology/W17-6209 | |
| PWC | https://paperswithcode.com/paper/multiword-expression-aware-a-tag-parsing |
| Repo | |
| Framework | |
TAG Parser Evaluation using Textual Entailments
| Title | TAG Parser Evaluation using Textual Entailments |
| Authors | Pauli Xu, Robert Frank, Jungo Kasai, Owen Rambow |
| Abstract | |
| Tasks | Natural Language Inference |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6214/ |
| https://www.aclweb.org/anthology/W17-6214 | |
| PWC | https://paperswithcode.com/paper/tag-parser-evaluation-using-textual |
| Repo | |
| Framework | |
Nyström Method with Kernel K-means++ Samples as Landmarks
| Title | Nyström Method with Kernel K-means++ Samples as Landmarks |
| Authors | Dino Oglic, Thomas Gärtner |
| Abstract | We investigate, theoretically and empirically, the effectiveness of kernel K-means++ samples as landmarks in the Nyström method for low-rank approximation of kernel matrices. Previous empirical studies (Zhang et al., 2008; Kumar et al.,2012) observe that the landmarks obtained using (kernel) K-means clustering define a good low-rank approximation of kernel matrices. However, the existing work does not provide a theoretical guarantee on the approximation error for this approach to landmark selection. We close this gap and provide the first bound on the approximation error of the Nyström method with kernel K-means++ samples as landmarks. Moreover, for the frequently used Gaussian kernel we provide a theoretically sound motivation for performing Lloyd refinements of kernel K-means++ landmarks in the instance space. We substantiate our theoretical results empirically by comparing the approach to several state-of-the-art algorithms. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=595 |
| http://proceedings.mlr.press/v70/oglic17a/oglic17a.pdf | |
| PWC | https://paperswithcode.com/paper/nystrom-method-with-kernel-k-means-samples-as |
| Repo | |
| Framework | |
