ACM Transactions on

Asian and Low-Resource Language Information Processing (TALLIP)

Latest Articles

Science Citation Index Listing

TALLIP will be listed in the Science Citation Index Expanded starting with the first 2015 issue, 14(1). TALLIP will be included in the 2017 Journal Citation Report, and the first Impact Factor will be published mid-2018.

New Name, Expanded Scope

This page provides information about the journal Transactions on Asian and Low-Resource Language Information Processing (TALLIP), a publication of the Association for Computing Machinery (ACM).

The journal was formerly known as the Transactions on Asian Language Information Processing (TALIP): see the editorial charter for information on the expanded scope of the journal.  

A Dependency Parser for Spontaneous Chinese Spoken Language

Response Selection and Automatic Message-Response Expansion in Retrieval-Based QA Systems using Semantic Dependency Pair Model

This study presents an approach to select suitable response and further automatically expand the message-response (MR) database from the unstructured data on the websites for a QA system. First, we manually construct an MR database as a baseline database based on the articles collected from the psychological consultation websites. The Chinese Knowledge and Information Processing PCFG is adopted to obtain the semantic dependency graphs (SDGs) of all the messages and responses in the baseline MR database. For each sentence in the MR database, all the semantic dependencies (SDs), each composed of two words and their semantic relation, are extracted from the SDG of the sentence to form a semantic dependency set. Finally, a matrix with the element representing the correlation between the SDs of the messages and their corresponding responses is constructed as a SD Pair Model (SDPM) for response selection. Moreover, as the MR pairs in the psychological consultation websites are increasing day by day, MR database in the QA system should be expanded to satisfy the new need from the user. For MR database expansion, the unstructured data from the message board are automatically collected. For the collected data, the supervised LDA is adopted for event detection and then the event-based delta-BIC is used for MR article segmentation. Each extracted message segment is then fed to the constructed retrieval-based QA system to find the best matched response segment and the matching score is also estimated to verify if the MR pair is suitable to be included in the expanded MR database. Compared to the traditional vector space model, the proposed approach achieved a more favorable performance according to a statistical significance test. The retrieval accuracy based on MR expansion was also evaluated and a satisfactory result was obtained confirming the effectiveness of the expanded MR database.

Novel Character Identification Utilizing Semantic Relation with Animate Nouns in Korean

For identifying speakers of quoted speech or extracting social networks from literature, it is indispensable to extract character names and nominals. However, detecting proper nouns in the novels translated into or written in Korean is harder than in English because Korean does not have capitalization feature. In addition, it is almost impossible for any proper noun dictionary to include all kind of character names which have been created or will be created by authors. Fortunately, a previous study shows that utilizing postpositions for animate nouns is a simple and effective tool for character identification in Korean novels without a proper noun dictionary and a training corpus. In this paper, we propose a character identification method utilizing the semantic relation with known animate nouns. For 80 novels in Korean, the proposed method increases the micro- and macro-average recall by 13.68% and 11.86%, respectively, while decreasing the micro-average precision by 0.28% and increasing the macro-average precision by 0.07% compared to the previous study. If we focus on characters that are responsible for more than 1% of the character name mentions in each novel, the micro- and macro-average F-measure of the proposed method are 96.98% and 97.32%, respectively.

The Rule-Based Sundanese Stemmer

Our research proposed an iterative Sundanese stemmer by removing the derivational affixes prior to the inflexional. This scheme was chosen because, in the Sundanese affixation, a confix (one of derivational affix) is applied in the last phase of a morphological process. Moreover, most of Sundanese affixes are derivational, so removing the derivational affix as the first step is reasonable. To handle ambiguity, the last recognized affix was returned as the result. As the baseline, a Confix-Stripping Approach which applies Porter Stemmer for the Indonesian language was used. This stemmer shares similarities in terms of affix type, but uses a different stemming order. To observe whether the baseline stems the Sundanese affixed word properly, some features that were not covered by the baseline, such as the infix and allomorph removal, were added. The evaluation was done using 4,453 unique affixed words collected from Sundanese online magazines. The experiment shows that, as a whole, our stemmer outperforms the modified baseline in terms of recognized affixed type accuracy and properly stemmed affixed words. Our stemmer recognized 68.87% of the Sundanese affixes types and produced 96.79% of the correctly affixed words; the modified baseline resulted in 21.70% and 71.59% respectively.

Improving Vector Space Word Representations Via Kernel Canonical Correlation Analysis

Cross-lingual word embeddings are representations for vocabularies of two or more languages in one common continuous vector space and are widely used in various NLP tasks. A simple yet efficient way to generate cross-lingual word embeddings is using canonical correlation analysis (CCA). However, CCA works with the assumption that the vector representations of similar words in different languages are related by a linear relationship. This assumption does not always hold true, especially for substantially different languages. We therefore propose to use kernel canonical correlation analysis (KCCA) to capture non-linear relationships between word embeddings of two languages. By extensively evaluating the resulting word embeddings on three tasks (word similarity, cross-lingual dictionary induction, cross-lingual document classification) across five language pairs, we show that our approach produces essentially better semantic vectors than CCA-based method, especially for substantially different languages.

CLASENTI: A Class-specific Sentiment Analysis Framework

Arabic text sentiment analysis suffers from low accuracy due to Arabic-specific challenges, (e.g., limited resources, morphological complexity, and dialects) and general linguistic issues (e.g., fuzziness, implicit, sarcasm, and spam). The limited resources problem requires efforts to build new and improve Arabic corpora and lexica. We propose a class-specific sentiment analysis (CLASENTI) framework. The framework includes a new annotation approach to build multi-faceted Arabic corpus and lexicon, which are simultaneously annotated with domains, dialects, linguistic issues and polarity strengths. The new corpus and lexicon annotation facilitate the development of new classification model and polarity strength calculation. For the new sentiment classification model, we propose a hybrid model combining corpus-based and lexicon-based models. The corpus-based model has two interrelated phases to build; 1) full-corpus classification models for all facets; and 2) class-specific models trained on filtered subsets of the corpus according to the performances of the full-corpus models. To calculate polarity strengths, the lexicon-based model filters the annotated lexicon based on the specific classes of the domain and dialect. As a case study, we have collected and annotated 15,274 reviews from various sources, including surveys, Facebook comments, and Twitter posts, pertaining to governmental services in an Arab country. CLASENTI framework reaches up to 95% accuracy and 93% F1-Score surpassing the best-known sentiment classifiers that achieve 82% accuracy and 81% F1-Score for Arabic when tested on the same dataset.

Using Communities of Words Derived from Multilingual Word Vectors for Cross-Language Informational Retrieval in Indian Languages

We investigate the use of word embeddings for query translation to improve precision in Cross Language Information Retrieval (CLIR). Word vectors represent words in a distributional space such that syntactically or semantically similar words are close to each other in this space. Multilingual word embeddings are constructed in such a way that similar words across languages have similar vector representations. We explore the effective use of bilingual and multilingual word embeddings learned from comparable corpora of Indic languages to the task of CLIR. We propose a clustering method based on the multilingual word vectors to group similar words across languages. For this we construct a graph with words from multiple languages as nodes and with edges connecting words with similar vectors. We use the Louvain Method for community detection to find communities in this graph. We show that choosing target language words as query translations from the clusters or communities containing the query terms helps in improving CLIR. We also find that better quality query translations are obtained when words from more languages are used to do the clustering even when the additional languages are neither the source of the target language. This is probably because having more similar words across multiple languages help define well-defined dense sub-clusters that help us obtain precise query translations. In this paper, we demonstrate the use of multilingual word embedding and word clusters for CLIR involving Indic languages. We also make available a tool for obtaining related words and the visualizations of the multilingual word vectors for English, Hindi, Bengali, Marathi, Gujarati and Tamil.

Domain-specific Named Entity Recognition with Document-level Optimization

Previous studies normally formulate named entity recognition (NER) as a sequence labeling task and optimize the solution in sentence level. In this paper, we address NER as a document-level optimization problem. First, we apply a state-of-the-art approach, i.e., long short term memory (LSTM), to perform word classification; Second, we define a global objective function with the obtained word classification results and achieve global optimization via Integer Linear Programming (ILP). Specifically, in the ILP-based approach, we propose four kinds of constrains, i.e., label transition, entity length, label consistency, and domain-specific regulation constrains, to incorporate various entity recognition knowledge in document level. Empirical studies demonstrate the effectiveness of the proposed approach to document-level NER.

Graph-based Bilingual Word Embedding for Statistical Machine Translation

Bilingual word embedding has been shown to be helpful for Statistical Machine Translation (SMT). However, most existing methods suffer from two obvious drawbacks. First, they only focus on simple contexts such as an entire document or a fixed sized sliding window to build word embedding and ignore latent useful information from the selected context. Second, the word sense but not the word should be the minimal semantic unit; however, most existing methods are still use word representation. To overcome these drawbacks, this paper presents a novel Graph-based Bilingual Word Embedding (GBWE) method that projects bilingual word senses into a multi-dimensional semantic space. First, a bilingual word co-occurrence graph is constructed using the co-occurrence and pointwise mutual information between the words. Then, maximum complete sub-graphs (cliques), which play the role of a minimal unit for bilingual sense representation, are dynamically extracted according to the contextual information. Consequently, correspondence analysis, principle component analyses and neural networks are used to summarize the clique-word matrix into lower dimensions to build the embedding model. Without contextual information, the proposed GBWE can be applied to lexical translation. In addition, given the contextual information, GBWE is able to give a dynamic solution for bilingual word representations, which can be applied to phrase translation and generation. Empirical results show that GBWE can enhance the performance of lexical translation and Chinese/French-to-English phrase-based SMT.

Optimizing Automatic Evaluation of Machine Translation with the ListMLE Approach

Automatic evaluation of machine translation is critical in the evaluation and development of machine translation systems. In this article, we propose a new model for automatic evaluation of machine translation. The proposed model combines standard n-gram precision features and sentence semantic mapping features with neural features, including neural language model probabilities and the embedding distances between translation outputs and their reference translations. We optimize the model with a representative list-wise learning to rank approach, ListMLE, in terms of human ranking assessments. The experimental results on WMT15 Metrics task indicate that the proposed approach has a significantly better correlation with human assessments than several state-of-the-art baseline approaches. In particular, the results confirm that the proposed list-wise learning to rank approach is useful and powerful for optimizing automatic evaluation metrics in terms of human ranking assessments. Deep analysis further reveals that optimizing automatic metrics with the ListMLE approach is reasonable and the neural features can gain considerable improvement over the traditional features.

Comparison of Methods to Annotate Named Entity Corpora

The authors compared two methods for annotating a corpus for the named entity (NE) recognition task using non-expert annotators: i) revising the results of an existing NE recognizer and ii) manually annotating the NEs completely. The annotation time, degree of agreement, and performance were evaluated based on the gold standard. Because there were two annotators for one text for each method, two performances were evaluated: the average performance of both annotators and the performance when at least one annotator is correct. The experiments reveal that semi-automatic annotation is faster, achieves better agreement, and performs better on average. However, they also indicate that sometimes, fully manual annotation should be used for some texts whose document types are substantially different from the training data document types. In addition, the machine learning experiments using semi- automatic and fully manually annotated corpora as training data indicate that the F-measures could be better for some texts when manual instead of semi-automatic annotation was used. Finally, experiments using the annotated corpora for training as additional corpora show that i) the NE recognition performance does not always correspond to the performance of the NE tag annotation and ii) the system trained with the manually annotated corpus outperforms the system trained with the semi-automatically annotated corpus with respect to newswires, even though the existing NE recognizer was mainly trained with newswires.

Weakly Supervised POS Tagging without Disambiguation

Weakly supervised part-of-speech (POS) tagging is to learn to predict the POS tag for a given word in context by making use of partial annotated data instead of the fully tagged corpora. Weakly supervised POS tagging would benefit various natural language processing applications in such languages where tagged corpora are mostly unavailable. In this paper, we propose a novel framework for weakly supervised POS tagging based on a dictionary of words with their possible POS tags. In the constrained error-correcting output codes (ECOC) based approach, a unique L-bit vector is assigned to each POS tag. The set of bitvectors is referred as coding matrix and denoted as M with value {1, -1}. Each column of the coding matrix M specifies a dichotomy over the tag space to learn a binary classifier. For each binary classifier, its training data is generated in the following way: each pair of word and its possible POS tags will be considered as a positive training example only if the whole set of its possible tags falls into the positive dichotomy specified by the column coding; and similarly for negative training examples. Given a word in context, its POS tag is predicted by concatenating the predictive outputs of the L binary classifiers and choosing the tag with the closest distance according to some measure. By incorporating the ECOC strategy, the set of all possible tags for each word is treated as an entirety without the need of performing disambiguation. Moreover, instead of manual feature engineering employed in most previous POS tagging approaches, features for training and testing in the proposed framework are automatically generated using neural language modeling. The proposed framework has been evaluated on three corpora for English, Italian and Malagasy POS tagging, achieving accuracies of 93.21%, 90.9% and 84.5% individually, which shows a significant improvement compared to the state-of-the-art approaches.

Input Method for Human Translators: a Novel Approach to Integrate Machine Translation Effectively and Imperceptibly

Computer-aided translation (CAT) systems are the most popular tool for helping human translators efficiently perform language translation. To further improve the translation efficiency, there is an increasing interest in applying machine translation (MT) technology to upgrade CAT. To thoroughly integrate MT into CAT systems, in this paper, we propose a novel approach: a new input method that makes full use of the knowledge adopted by MT systems, such as translation rules, decoding hypotheses and n-best translation lists. The proposed input method contains two parts: phrase generation model, allowing human translators to type target sentences quickly, and n-gram prediction model, helping users choose perfect MT fragments smoothly. In addition, to tune the underlying MT system to generate the input method preferable results, we design a new evaluation metric for the MT system. The well-designed input method integrates MT effectively and imperceptibly, and it is particularly suitable for many target languages with complex characters, such as Chinese and Japanese. The extensive experiments demonstrate that our method saves more than 23\% time and over 42\% keystrokes, and it also improves the translation quality by more than 5 absolute BLEU scores compared with the strong baseline, i.e., post-editing using Google Pinyin.

Word Segmentation for Burmese Based on Dual-Layer CRFs

Burmese is an isolated language, in which syllable is the smallest unit. syllable segmentation method based on matching leads to performance subject to the syllable segmentation effect. This paper proposes a word segmentation method with fusion conditions of double syllable feature. It puts word segmentation and segmentation of syllable as a whole process, thus reducing the impact of errors on the syllable segmentation of Burmese. In the first layer of CRFs, Burmese characters as atomic features are integrated into the Burma section of the Barkis Speech Paradigm (BNF) features, to realize the Burma syllable sequence tags. in the second layer CRFs model, with the syllable marked as input, it realizes the sequence markers through building feature template with syllable as atomic features. The experimental results show that the proposed method has a better effect compared with the method based on the matching of syllable.


Publication Years 2002-2018
Publication Count 338
Citation Count 1149
Available for Download 338
Downloads (6 weeks) 1253
Downloads (12 Months) 12888
Downloads (cumulative) 230868
Average downloads per article 683
Average citations per article 3
First Name Last Name Award
Baoli Li ACM Senior Member (2012)
Bing Liu ACM Fellows (2015)
Robert Luk ACM Senior Member (2007)
Tetsuya Sakai ACM Senior Member (2016)
Limsoon Wong ACM Fellows (2013)
Bulent Yener ACM Senior Member (2013)
Dong Zhou ACM Senior Member (2012)

First Name Last Name Paper Counts
Chengqing Zong 9
Chunghsien Wu 9
Guodong Zhou 7
Masao Utiyama 6
Eiichiro Sumita 6
Garygeunbae Lee 5
Jianfeng Gao 5
Sadao Kurohashi 5
Hitoshi Isahara 5
Yūji Matsumoto 4
Kevin Duh 4
Noriko Kando 4
Hsinmin Wang 4
Naoaki Okazaki 4
Isao Goto 4
Juifeng Yeh 4
Kentaro Inui 4
Berlin Chen 4
Andy Way 4
Phuoc Tran 3
Swapan Parui 3
Qun Liu 3
Susumu Horiguchi 3
Byeongchang Kim 3
Jianyun Nie 3
Jiajun Zhang 3
Pushpak Bhattacharyya 3
Akira Shimazu 3
Andrew Finch 3
Long Nguyen 3
Utpal Sharma 3
Tetsuya Sakai 3
Jugal Kalita 3
Kuilam Kwok 3
Prasenjit Majumder 3
Teruko Mitamura 3
Jonghoon Lee 3
Dien Dinh 3
Wenjie Li 3
Kamfai Wong 3
Umapada Pal 3
Masaki Murata 3
Pakchung Ching 2
Ralph Weischedel 2
Sanjeev Khudanpur 2
Jason Chang 2
Khaled Shaban 2
Wassim El-Hajj 2
Hsinhsi Chen 2
Jawad Sadek 2
Imed Zitouni 2
HungYu Su 2
Chienhsing Chen 2
Tatsunori Mori 2
Utpal Garain 2
Atsushi Fujita 2
Chinyew Lin 2
Pascale Fung 2
Hazem Hajj 2
Hideki Mima 2
Tiejun Zhao 2
Chenhui Chu 2
Pingche Yang 2
Jun’ichi Tsujii 2
Fumiyo Fukumoto 2
Wenlian Hsu 2
Dawei Song 2
Chungchian Hsu 2
Eiichiro Sumita 2
Debasis Ganguly 2
Anton Leuski 2
Qing Ma 2
Peyman Passban 2
Tan Lee 2
Inderjeet Mani 2
Garygeunbae Lee 2
Hailong Cao 2
Ali Farghaly 2
Sophia Ananiadou 2
Chenchen Ding 2
Stephan Vogel 2
Margaret Connell 2
Kehjiann Chen 2
Timothy Baldwin 2
Toru Ishida 2
Mu Li 2
Bonnie Dorr 2
Douglas Oard 2
Grace Ngai 2
Nizar Habash 2
Wenhsiang Lu 2
Xuanhieu Phan 2
Mandar Mitra 2
Toshiaki Nakazawa 2
Xiaodong Liu 2
Baoliang Lu 2
Chengwei Lee 2
Mikio Yamamoto 2
Jiaul Paik 2
Muhua Zhu 2
Tong Xiao 2
Junhui Li 2
Shaonan Wang 2
Kiyotaka Uchimoto 2
Jonghyeok Lee 2
Ramy Baly 2
Farid Meziane 2
Chungchi Huang 2
Neeta Nain 2
Jong Park 2
Jingbo Zhu 2
Bing Liu 2
Robert Luk 2
Suresh Sundaram 2
Angarai Ramakrishnan 2
Kalina Bontcheva 2
Kuanyu Chen 2
Hajime Tsukada 2
Yoshimi Suzuki 2
Chewlim Tan 2
Navanath Saharia 2
David Doermann 2
David Zajic 2
Leefeng Chien 2
Daisuke Kawahara 2
Alon Lavie 2
Qiaoming Zhu 2
Yusuke Miyao 2
Hideki Isozaki 2
Katsuhito Sudoh 2
Hai Zhao 2
Baoli Li 2
Chengwei Shih 2
Haitong Yang 2
Shihhung Wu 2
Degen Huang 2
Ming Zhou 2
Helen Meng 2
Ryu Iida 2
Dipasree Pal 2
Jacques Savoy 2
Takuya Matsuzaki 2
Kehyih Su 2
Min Zhang 2
Aiti Aw 2
Chaolin Liu 2
Xiaolong Wang 2
Jiajun Chen 2
Hanping Shen 2
Yuzhu Wang 1
Uchechukwu Chinedu 1
Yuan Ye 1
Arbi Nasution 1
Khalid Almeman 1
Hongseok Kwon 1
Peishan Tsai 1
Michael Nossal 1
Dina Demner-Fushman 1
Philip Resnik 1
Mingjun Chen 1
Abdelmajid Hamadou 1
Malinda Punchimudiyanse 1
Fang Kong 1
Shanta Phani 1
Shosaku Tanaka 1
Yoichi Tomiura 1
Hsijian Lee 1
PoChui Luk 1
Wajdi Zaghouani 1
Sukalpa Chanda 1
Oriol Terrades 1
Ayan Bandyopadhyay 1
Gareth Jones 1
Eziz Tursun 1
Christian Hettick 1
Meihua Chen 1
Deyuan Zhang 1
Yoshiaki Asada 1
Yang Lingpeng 1
Mingwen Wang 1
Hamdan Rahman 1
Manoj Sharma 1
Iskandar Keskes 1
Sanae Fujita 1
Sujay Jayakar 1
Jinhua Du 1
Fei Xia 1
Shibaprasad Sen 1
Pawan Singh 1
Shengbin Jia 1
Shijia E 1
Heba El-Fiqi 1
Yong Chen 1
ChunKai Chen 1
TienTeng Shih 1
Sriram Venkatapathy 1
Cristina España-Bonet 1
Hermann Moisl 1
Kenneth Church 1
Seunghoon Na 1
Helen Ashman 1
Yaoyong Li 1
Kun Wang 1
Jungjae Kim 1
Youngsook Hwang 1
Haechang Rim 1
Om Damani 1
Ngo Bach 1
Tianshun Yao 1
Ling Cao 1
Hideki Shima 1
Suman Mitra 1
Jinjing Xia 1
Janming Ho 1
Liming Tseng 1
Minyuh Day 1
TianJian Jiang 1
Leah Larkey 1
Mike Maxwell 1
Rebecca Hwa 1
Yuichi Ogawa 1
Yujia Li 1
Yuexian Hou 1
Shihting Huang 1
Le Sun 1
Woosung Kim 1
Diego Linares 1
Lishuang Li 1
Hisami Suzuki 1
Mehrnoush Shamsfard 1
Oumayma Al Dakkak 1
Kaiyu Huang 1
Sukhdeep Singh 1
Daya Lobiyal 1
Seyed Tahaghoghi 1
Dinh Dien 1
Tran Tri 1
Fumito Masui 1
Yingkuei Yang 1
Qing Li 1
Honglan Jin 1
Yuanxiang Li 1
Xinyu Dai 1
Fan Xu 1
Junsheng Zhou 1
Chuan Cheng 1
Mohd Murah 1
Shahin Salavati 1
Hwidong Na 1
JinSeok Lee 1
Ario Ohsato 1
Izumi Suzuki 1
Kumiko Tanaka-Ishii 1
Yanyan Jia 1
Shoushan Li 1
Shujie Liu 1
Yueshi Lee 1
Huanfeng Ma 1
Satoshi Sekine 1
Jun Luo 1
Hamish Cunningham 1
Marine Carpuat 1
Katsumi Tanaka 1
Takashi Inui 1
Kui Xu 1
Thu Nguyen 1
Kaifu Lee 1
Joshua Goodman 1
Sukomal Pal 1
Johannes Leveling 1
Arjun V 1
Junlin Zhou 1
Weibin Liang 1
Jeesoo Bang 1
Haiyang Hu 1
Taro Watanabe 1
Srinivas Bangalore 1
Xiao Liu 1
Robert Moore 1
Jean Gauvain 1
Jordi Centelles 1
Mark Truran 1
Yufeng Chen 1
Sungjin Lee 1
KwopPing Chan 1
Changning Huang 1
Goran Nenadic 1
A Kumaran 1
Tianyong Hao 1
Chunshen Zhu 1
MikeTianjian Jiang 1
Tsunghsien Lee 1
Saras Saraswathi 1
Xianchao Wu 1
Taichi Asami 1
Koichi Takeda 1
Hiroshi Kanayama 1
Utpal Roy 1
Nimit Dhulekar 1
Ting Liu 1
Jengwei Lin 1
Christopher Cieri 1
Richard Cohen 1
Sriparna Saha 1
Tadaaki Oshio 1
Sumio Fujita 1
Setsuko Nara 1
David Evans 1
Hiroshi Matsuda 1
Gregory Grefenstette 1
Norbert Dinstl 1
Longhua Qian 1
Yongsheng Yang 1
Minh Le Nguyen 1
Liyun Ru 1
Atsuhiro Takasu 1
Keysun Choi 1
Weizheng Yuan 1
Robert Dale 1
Heyan Huang 1
Hyunsun Hwang 1
Muhua Zhu 1
Amita Jain 1
Richard Tsai 1
Bobby Nazief 1
Yutaka Matsuo 1
Tsuneaki Kato 1
Niu Zhengyu 1
Yueting Zhuang 1
Guihong Cao 1
Qin Lu 1
Hao Zhou 1
Huadong Chen 1
Suliana Sulaiman 1
Nazlia Omar 1
Lamia Belguith 1
Sriganesh Madhvanath 1
Xu Sun 1
Houfeng Wang 1
Albert Brouillette 1
Dipti Sharma 1
Deng Cai 1
Yang Xin 1
Ikechukwu Onyenwe 1
Yohei Murakami 1
Xiyao Cheng 1
Hyun Kim 1
Himangshu Sarma 1
Franz Och 1
Ulrich Germann 1
Eduard Hovy 1
Daqing He 1
Aesun Yoon 1
Hyukchul Kwon 1
Gilbert Badaro 1
Zejing Chuang 1
Faramarz Hendessi 1
Wafa Wali 1
Shibamouli Lahiri 1
Qiang Ma 1
Takao Doi 1
Yujie Zhang 1
Jennifer Baldwin 1
James Pustejovsky 1
Donna Harman 1
Sucharita Sanyal 1
Yayun Huang 1
Ashish Kankaria 1
Turghun Osman 1
Ghalip Abdukerim 1
Ramisettyrajeshwara Rao 1
Dan Parvaz 1
Christine Doran 1
Charles Blake 1
Radu Florian 1
Minwoo Jeong 1
Ali Salhi 1
Sherief Abdallah 1
Junejei Kuo 1
Mitsuru Ishizuka 1
Josef Van Genabith 1
Limsoon Wong 1
Sarmad Hussain 1
Masaaki Nagata 1
Manabu Okumura 1
Tomohide Shibata 1
Abdullah Talib 1
Lambert Schomaker 1
Özgür Ulusoy 1
Stephanie Strassel 1
Lori Levin 1
Erik Peterson 1
Ying Zhang 1
Toshiya Ueda 1
HoChing Yen 1
José Benedí 1
Yuming Hsieh 1
Hsinhsi Chen 1
Yabin Zheng 1
Lixing Xie 1
Rajib Das 1
Michael Tepper 1
Sanae Fujita 1
Feifan Liu 1
Atsushi Matsumura 1
Jonghoon Oh 1
TzeLeung Chung 1
Ram Sarkar 1
Kaushik Roy 1
Shahram Salami 1
Ercan Solak 1
Olcay Yıldız 1
Lina Sherkawi 1
Wei Lu 1
Anuj Sharma 1
ChiaHung Lin 1
Mitsuru Ishizuka 1
Makoto Haraguchi 1
Tang Li 1
Hanxi Li 1
Keisuke Sakanushi 1
Shujian Huang 1
A Bharath 1
Leigh Gathings 1
Goutham Tholpadi 1
Steve Gunn 1
Kareem Darwish 1
Jianqiang Wang 1
Jungyun Seo 1
Miyoung Kang 1
Jyhshing Jang 1
T Gulliver 1
Ahmad Al Sallab 1
Philips Prasetyo 1
Wenliang Chen 1
Quangthuy Ha 1
Y Wong 1
KamFai Wong 1
Frank Schilder 1
Carol Peters 1
Ganesh Ramakrishnan 1
Hiroki Hanaoka 1
Chutamanee Onsuwan 1
Seth Kulick 1
Lemao Liu 1
Conghui Zhu 1
Yanjun Ma 1
Dong Zhou 1
Lluís Màrquez 1
Yassine Benajiba 1
Maad Shatnawi 1
Tim Brailsford 1
Minwoo Jeong 1
Seiichi Nakagawa 1
Yuqing Guo 1
Daniel Andrade 1
Cheongjae Lee 1
Eunju Kim 1
Kyungmi Park 1
WenLian Hsu 1
Nguyenle Minh 1
Tran Oanh 1
Takaaki Fukunishi 1
Genichiro Kikui 1
Hiroya Takamura 1
Lu Qin 1
Pyung Kim 1
Le Zhang 1
Keita Nabeshima 1
Toru Tanaka 1
Mukesh Goswami 1
Tongtao Zhang 1
Ye Thu 1
Feipei Lai 1
YiHsun Lee 1
Asif Ekbal 1
Phil Vines 1
Motoko Ishikawa 1
Yuki Funakoshi 1
David Hull 1
Sora Choi 1
Nianwen Xue 1
Boxing Chen 1
Zhiyuan Liu 1
Sunam Kim 1
Xiaohan She 1
Yang Xiang 1
Jizhou Huang 1
Shiqiang Ding 1
Haifeng Wang 1
Ting Liu 1
Karthik Krishnamurthi 1
Xiuming Qiao 1
Hussein Abbass 1
Liangliang Liu 1
Jelita Asian 1
Indu Chhabra 1
Natthawut Kertkeidkachorn 1
Atiwong Suchato 1
Mirna Adriani 1
Hugh Williams 1
Nigel Collier 1
Irit Gefner 1
Yuhsien Chiu 1
Haizhou Li 1
Jinghui Xiao 1
Yasushi Inoguchi 1
Rong Jin 1
Mohammad Basiri 1
Shujian Huang 1
Yu Zhou 1
Rui Wang 1
Yue Zhang 1
Anwitaman Datta 1
Yoshihide Chubachi 1
Miguel Lezcano 1
Taisuke Harada 1
Chiranjib Bhattacharyya 1
Shirish Shevade 1
Chongde Shi 1
Dongyan Zhao 1
Bixiao Cheng 1
Tan Le 1
Nilanjana Bhattacharya 1
Partha Roy 1
Muhammad Malik 1
Waikit Lo 1
Ada Brunstein 1
Tamotsu Shirado 1
A Ghayoori 1
Bilel Gargouri 1
Hsuchun Yen 1
Wencheng Lin 1
RuYng Chang 1
Ramachandran Jayadevan 1
Beth Sundheim 1
Peifeng Li 1
Andrew Freeman 1
C Rytting 1
Paul Rodrigues 1
Tim Buckwalter 1
Dickson Chiu 1
Lori Lamel 1
Eiichrio Sumita 1
Takashi Tsunakawa 1
Patrick Nguyen 1
Abdelkhalek Messaoudi 1
Subhash Panwar 1
Xiaoqing Li 1
Garygeunbae Lee 1
Jun’ichi Tsujii 1
Hongling Wang 1
Yu Song 1
Jeongwon Cha 1
Seonho Kim 1
Mitesh Khapra 1
Manoj Chinnakotla 1
Satoshi Sato 1
Tomoya Iwakura 1
Zhao Liu 1
Eric Nichols 1
Heng Ji 1
Bülent Yener 1
Liming Zhao 1
Sheng Li 1
YuRen Chen 1
Fei Huang 1
Nasreen Abduljaleel 1
Katharina Probst 1
James Allan 1
Kanwen Tien 1
Justin Zobel 1
Tadataka Matsubayashi 1
Makoto Iwayama 1
Daisuke Noda 1
Shuilung Chuang 1
Benfeng Chen 1
Shuling Huang 1
Gina Levow 1
Maochuan Su 1
Francis Bond 1
Takaaki Tanaka 1
Jyh Jang 1
Patrick Ye 1
Razieh Ehsani 1
Cong Zhang 1
Jianjun Ma 1
Eleni Petraki 1
Tingxuan Wang 1
Proadpran Punyabukkana 1
Kwokping Chan 1
Jun'ichi Fukumoto 1
Xiaoqing Ding 1
Le Nguyen 1
Yi Liu 1
Arman Kabiri 1
Yinggong Zhao 1
Bilel Elayeb 1
Khairuddin Omar 1
Debasis Samanta 1
Kyumars Esmaili 1
Lauren Hinkle 1
Zhongye Jia 1
Anja Chaibi 1
Chao Lv 1
Sreelekha S 1
Ralph Grishman 1
Michael Subotin 1
Wei Li 1
Andrew McCallum 1
Harksoo Kim 1
Ravinda Meegama 1
Chiching Lin 1
Cam Nguyen 1
Wai Lau 1
Jun'ichi Tsujii 1
Mingjing Li 1
Benjamin Han 1
Samaresh Maiti 1
Thanaruk Theeramunkong 1
Sarah Wayland 1
Yi Zhuang 1
Qing Li 1
Philipp Koehn 1
Mei Yang 1
Adnan Yahya 1
Jannik Strötgen 1
Ayser Armiti 1
Tran Van Canh 1
Michael Gertz 1
Deepti Khanduja 1
Marta Costa-Jussà 1
Mairidan Wushouer 1
Donghui Lin 1
Ryuichiro Higashinaka 1
Nguyentuan Duc 1
Haifeng Wang 1
Kyoungduk Kim 1
Smruthi Mukund 1
Sana Gul 1
Kuniko Saito 1
Jingbo Zhu 1
Minh Pham 1
Yotaro Watanabe 1
Junta Mizuno 1
Makoto Yasuhara 1
Tapan Bhowmik 1
Aritra Chowdhury 1
Kevin Knight 1
Prakash Choudhary 1
Oguz Yilmaz 1
Wanxiang Che 1
Chenglung Sung 1
Chiawei Wu 1
Ariadna Llitjos 1
Rachel Reynolds 1
Minhua Lai 1
Hisao Mase 1
Makoto Koyama 1
Peng Zhang 1
Qun Liu 1
Wenyi Chen 1
Shihhsiang Lin 1
Haizhou Li 1
Chengjie Sun 1
Maosong Sun 1
Yang Zhang 1
Lian Zhao 1
David Martínez 1
Yang Liu 1
Jiangchun Chen 1
Jun Adachi 1
Diklun Lee 1
Ankan Bhattacharyya 1
Nada Ghneim 1
Ping Jian 1
Jiahuan Pei 1
Maozhen Li 1
Vijayapal Panuganti 1
Vishnu Bulusu 1
Cungen Cao 1
Pham Thao 1
Ji Donghong 1
Jinshea Kuo 1
Yi Zhuang 1
Lei Chen 1
Maoxi Li 1
Ibrahim Bounhas 1
Diab Abuaiadah 1
Hirona Touji 1
Xinyu Dai 1
Jonghyeok Lee 1
Yoshiki Mikami 1
Haoran Li 1
Hai Zhao 1
Marwa Naili 1
Ying Chen 1
Hunyoung Jung 1
Seunghoon Na 1
Arafat Awajan 1
JiannCherng Shieh 1
Daming Shi 1
Liang Zhou 1
Jonathan May 1
Valentin Tablan 1
Diana Maynard 1
Satoko Marumoto 1
YuChung Lin 1
Arindam Biswas 1
Shihhung Liu 1
Wenlian Hsu 1
Toru Hitaka 1
Hirofumi Yamamoto 1
Fuliang Weng 1
YuSheng Lai 1
Seokbae Jang 1
Ljiljana Dolamic 1
Chienlung Chou 1
Yating Yang 1
Nitin Ramrakhiyani 1
Nongnuch Ketui 1
B Kumari 1
Muhammad Abdul-Mageed 1
Sherri Condon 1
John Aberdeen 1
Minhwa Chung 1
Michael Paul 1
David Chiang 1
Jesús Giménez 1
Julian Zell 1
Yuji Matsumoto 1
Jinsik Lee 1
Welly Naptali 1
Byoungkee Yi 1
Rohini Srihari 1
Erik Peterson 1
T Geetha 1
Afifah Waseem 1
Seiichi Yamamoto 1
Tomoko Izumi 1
Yu Shiwen 1
Sunghyon Myaeng 1
Xipeng Qiu 1
Hideki Isozaki 1
Xuanjing Huang 1
Richardtzonghan Tsai 1
Dil Hakro 1
Rifat Ozcan 1
Nitin Madnani 1
Jaime Carbonell 1
Jinxi Xu 1
Kousaku Arita 1
Yan Qu 1
Toshihiko Manabe 1
Yao Qian 1
Chienchung Huang 1
Joan Sánchez 1
Minghong Bai 1
Lunghao Lee 1
Peng Wang 1
Benjamin Marie 1
Pengcheng Zhang 1
Emad Mohamed 1
Sangkeun Jung 1
Changki Lee 1
Yair Wiseman 1
Masaharu Yoshioka 1
Masanori Nozawa 1
Jing Bai 1
Tubao Ho 1
Joyce Chai 1
Abhisek Chakrabarty 1
Farah Zitoune 1
Victoria Rubin 1
Akinori Fujino 1
Arjun Das 1
Riyaz Bhat 1
Irshad Bhat 1
Henda Ghézala 1
Mark Hepple 1
Ignatius Ezeani 1
Yansong Feng 1
Pierre Isabelle 1
Robert Damper 1
Richard Schwartz 1
Prem Natarajan 1
Chunjen Lee 1
Yulun Hsieh 1
Nabin Sharma 1
Jerry Hobbs 1
Feng Pan 1
Deboshree Modak 1
Chiahui Chang 1
Sumire Uematsu 1
M Awad 1
Zhiang Wu 1
Jason Chang 1
Xiaodong He 1
Khaled Shaalan 1
K Shaalan 1
Seokhwan Kim 1
Akihiro Tamura 1
Katsutoshi Hirayama 1
Danushka Bollegala 1
Lidan Zhang 1
Masatoshi Tsuchiya 1
Yulan He 1
Katsumori Matsushima 1
Avijit Satoskar 1
Kenji Imamura 1
Minh Nguyen 1
Katsuma Narisawa 1
Junya Norimatsu 1
Erdem Sarigil 1
İsmail Altıngövde 1
Alex Waibel 1
Necip Ayan 1
Victor Lavrenko 1
Yihsuan Chuang 1
Chiaying Lee 1
Linshan Lee 1
Baotu Ho 1
Fei Cheng 1
Baoxun Wang 1

Affiliation Paper Counts
Zhejiang Gongshang University 1
National Institute of Advanced Industrial Science and Technology 1
Ritsumeikan University, Biwako-Kusatsu 1
Cornell University 1
Chungnam National University 1
Macquarie University 1
Damascus University 1
New York University Abu Dhabi 1
National Research Council Canada 1
United Arab Emirates University 1
Emirates College of Technology 1
Jawaharlal Nehru Technological University, Hyderabad 1
Jawaharlal Nehru Technological University, Kakinada 1
The University of Western Ontario 1
AT&T Inc. 1
Tianjin University 1
University of Hamburg 1
Information and Communications University 1
Istituto di Scienza e Tecnologie dell'Informazione A. Faedo 1
Jawaharlal Nehru University 1
Chonbuk National University 1
University of the Punjab Lahore 1
Waikato Institute of Technology 1
Japan Society for the Promotion of Science 1
University of Teesside 1
University of Texas at Austin 1
Pondicherry Engineering College 1
Japan Patent Information Organization 1
Newcastle University, United Kingdom 1
University Michigan Ann Arbor 1
University of Canberra 1
Institute of Computing Technology Chinese Academy of Sciences 1
Universiti Sains Malaysia 1
Turgut Ozal University 1
Nnamdi Azikiwe University 1
Princess Sumaya University 1
Ritsumeikan University 1
University of Colorado at Colorado Springs 1
University of Victoria 1
Nagoya University 1
Universidad Javeriana 1
Yuan Ze University 1
Open University of Sri Lanka 1
Gokaraju Rangaraju Institute of Engineering & Technology 1
University of Sindh 1
Universitas Islam Riau 1
University of Kurdistan 1
Industrial Technology Research Institute of Taiwan 1
University of Edinburgh 1
Cairo University Faculty of Engineering 1
Shanghai University of International Business and Economics 1
Dharmsinh Desai University 1
Baosteel Co., Ltd. 1
Bose Institute 1
Ming Chuan University 1
Hangzhou Dianzi University 1
Mie University 1
Anna University 1
The Institute of Behavioral Sciences 1
Christ University, Bangalore 1
Institute of Scientific and Technical Information of China 1
Al Qassim University 1
Indian Institute of Technology Roorkee 1
Nanjing Normal University 1
Universiti Pendidikan Sultan Idris 1
Tunghai University 1
National Chiao Tung University Taiwan 1
Sogang University 1
Ryukoku University 1
Columbia University 1
Space and Naval Warfare Systems Center San Diego 1
National Institute of Standards and Technology 1
SK Telecom Co., Ltd. 1
National Institute of Technology Manipur 1
Kobe University Faculty of Maritime Sciences 1
Robert Bosch GmbH 1
University of Michigan 1
Fujitsu Ltd. 1
Brunel University London 1
University of Sri Jayewardenepura 1
Middle East Technical University 1
University of Quebec in Montreal 1
Catholic University of Daegu 1
Janya, Inc. 1
Seoul National University 1
Singapore University of Technology and Design 2
Zhejiang University 2
University of Indonesia 2
Hebrew University of Jerusalem 2
Uiduk University 2
New York University 2
University of Pittsburgh 2
Higher Institute for Applied Sciences and Technology Syria 2
Indian Institute of Engineering Science and Technology, Shibpur, Howrah, India 2
University of New South Wales 2
Chaoyang University of Technology 2
Vietnam National University 2
University of Texas at Dallas 2
HP Labs 2
University at Buffalo, State University of New York 2
City University of New York 2
University of Groningen 2
University of Nottingham 2
Microsoft Corporation 2
Robert Gordon University 2
Doshisha University 2
Universidad Politecnica de Valencia 2
Jadavpur University 2
University of Qatar 2
University of Calcutta 2
Brandeis University 2
Monterey Institute of International Studies 2
Tokyo Institute of Technology 2
Shahid Beheshti University 2
National Taiwan University of Science and Technology 2
Kangwon National University 2
Huawei Technologies Co., Ltd. 2
Japan Science and Technology Agency 2
Indian Institute of Technology, Kharagpur 2
Hokkaido University 2
Isfahan University of Technology 2
IBM, Japan 2
Birzeit University 2
Indiana University 2
Dhirubhai Ambani Institute of Information and Communication Technology 2
Shahrekord University 2
Universite de Toulouse 2
Open University 2
University of Southampton 2
Bilkent University 3
Michigan State University 3
University of Neuchatel 3
Chulalongkorn University 3
Korea University 3
Panjab University 3
University of Manouba 3
Johns Hopkins University 3
China Agricultural University 3
Ton-Duc-Thang University 3
University of Southern California 3
Pusan National University 3
Kyushu University 3
Thammasat University 3
Nanyang Technological University 3
Research Organization of Information and Systems National Institute of Informatics 3
Queens College, City University of New York 3
IBM Thomas J. Watson Research Center 3
Indian Institute of Technology 3
British University in Dubai 3
Toyohashi University of Technology 3
University of Manchester 3
Nagaoka University of Technology 3
Isik University 3
Tongji University 3
National University of Computer and Emerging Sciences Lahore 3
Northeastern University China 3
Laobratoire d'Informatique pour la Mecanique et les Sciences de l'Ingenieur 3
International Institute of Information Technology Hyderabad 3
University of Sfax 4
National University of Singapore 4
Advanced Telecommunications Research Institute International (ATR) 4
Yokohama National University 4
University of Colorado at Boulder 4
Georgetown University 4
Tezpur University 4
University of Yamanashi 4
Hitachi, Ltd. 4
University of Washington, Seattle 4
Universiti Kebangsaan Malaysia 4
Korea Advanced Institute of Science & Technology 4
Toshiba Corporation 4
National Central University Taiwan 4
University of Salford 4
Jiangxi Normal University 4
Fudan University 4
Beijing Institute of Technology 4
Xinjiang Technical Institute of Physics and Chemistry 4
City University of Hong Kong 4
Universitat Politecnica de Catalunya 5
National Chengchi University 5
University of Melbourne 5
University of Montreal 5
National Chiayi University 5
Rensselaer Polytechnic Institute 5
University of Heidelberg 5
University of Pennsylvania 5
The University of Hong Kong 5
RMIT University 5
Indian Institute of Science, Bangalore 6
National Yunlin University of Science and Technology 6
Northeastern University 6
National Taiwan Normal University 6
BBN Technologies 7
American University of Beirut 7
Hong Kong University of Science and Technology 7
JustSystems Corporation 7
MITRE Corporation 7
Chinese Academy of Sciences 8
University of Massachusetts Amherst 8
Shanghai Jiaotong University 8
Institute for Infocomm Research, A-Star, Singapore 8
University of Southern California, Information Sciences Institute 9
Dalian University of Technology 9
Microsoft Research 9
University of Tsukuba 9
University of Sheffield 9
Tsinghua University 9
Peking University 9
Hong Kong Polytechnic University 11
Nanjing University 11
Microsoft Research Asia 11
Indian Institute of Technology, Bombay 11
National Taiwan University 12
Tohoku University 13
Japan Advanced Institute of Science and Technology 14
Nara Institute of Science and Technology 15
Institute of Automation Chinese Academy of Sciences 15
Kyoto University 16
Dublin City University 16
National Tsing Hua University 16
Soochow University 16
Chinese University of Hong Kong 17
Carnegie Mellon University 17
Harbin Institute of Technology 20
University of Tokyo 20
Nippon Telegraph and Telephone Corporation 20
Indian Statistical Institute, Kolkata 22
National Cheng Kung University 25
University of Maryland 27
Pohang University of Science and Technology 27
Academia Sinica Taiwan 28
Japan National Institute of Information and Communications Technology 40

ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP)

Volume 17 Issue 4, May 2018  Issue-in-Progress
Volume 17 Issue 3, May 2018
Volume 17 Issue 2, February 2018

Volume 17 Issue 1, November 2017
Volume 16 Issue 4, September 2017
Volume 16 Issue 3, April 2017

Volume 16 Issue 2, December 2016 TALLIP Notes and Regular Papers
Volume 16 Issue 1, December 2016 TALLIP Notes and Regular Papers
Volume 15 Issue 4, June 2016
Volume 15 Issue 3, March 2016
Volume 15 Issue 2, February 2016
Volume 15 Issue 1, January 2016

Volume 14 Issue 4, October 2015 Special Issue on Chinese Spell Checking
Volume 14 Issue 3, June 2015
Volume 14 Issue 2, March 2015
Volume 14 Issue 1, January 2015

Volume 13 Issue 4, December 2014
Volume 13 Issue 3, September 2014
Volume 13 Issue 2, June 2014
Volume 13 Issue 1, February 2014

Volume 12 Issue 4, October 2013
Volume 12 Issue 3, August 2013
Volume 12 Issue 2, June 2013
Volume 12 Issue 1, March 2013

Volume 11 Issue 4, December 2012 Special Issue on RITE
Volume 11 Issue 3, September 2012
Volume 11 Issue 2, June 2012
Volume 11 Issue 1, March 2012

Volume 10 Issue 4, December 2011
Volume 10 Issue 3, September 2011
Volume 10 Issue 2, June 2011
Volume 10 Issue 1, March 2011

Volume 9 Issue 4, December 2010
Volume 9 Issue 3, September 2010
Volume 9 Issue 2, June 2010
Volume 9 Issue 1, March 2010

Volume 8 Issue 4, December 2009
Volume 8 Issue 3, August 2009
Volume 8 Issue 2, May 2009
Volume 8 Issue 1, March 2009

Volume 7 Issue 4, November 2008
Volume 7 Issue 3, August 2008
Volume 7 Issue 2, June 2008
Volume 7 Issue 1, February 2008

Volume 6 Issue 4, December 2007
Volume 6 Issue 3, November 2007
Volume 6 Issue 2, September 2007
Volume 6 Issue 1, April 2007

Volume 5 Issue 4, December 2006
Volume 5 Issue 3, September 2006
Volume 5 Issue 2, June 2006
Volume 5 Issue 1, March 2006

Volume 4 Issue 4, December 2005
Volume 4 Issue 3, September 2005
Volume 4 Issue 2, June 2005
Volume 4 Issue 1, March 2005

Volume 3 Issue 4, December 2004
Volume 3 Issue 3, September 2004
Volume 3 Issue 2, June 2004
Volume 3 Issue 1, March 2004 Special Issue on Temporal Information Processing

Volume 2 Issue 4, December 2003
Volume 2 Issue 3, September 2003
Volume 2 Issue 2, June 2003
Volume 2 Issue 1, March 2003

Volume 1 Issue 4, December 2002
Volume 1 Issue 3, September 2002
Volume 1 Issue 2, June 2002
Volume 1 Issue 1, March 2002
All ACM Journals | See Full Journal Index

enter search term and/or author name