December 11-16 2016 Osaka Japan

More documents

Recommendations

Info

Stephan Peitz, Markus Freitag, Arne Mauser, and Hermann Ney. 2011. Modeling punctuation prediction as machine translation. In IWSLT, pages 238–245. Andreas Stolcke et al. 2002. Srilm-an extensible language modeling toolkit. In INTERSPEECH. Andreas Stolcke and Elizabeth Shriberg. 1996. Automatic linguistic segmentation of conversational speech. In Spoken Language, 1996. ICSLP 96. Proceedings., Fourth International Conference on, volume 2, pages 1005– 1008. IEEE. Andreas Stolcke, Elizabeth Shriberg, Rebecca A Bates, Mari Ostendorf, Dilek Hakkani, Madelaine Plauche, Gökhan Tür, and Yu Lu. 1998. Automatic detection of sentence boundaries and disfluencies based on recognized words. In ICSLP, pages 2247–2250. Toshiyuki Takezawa, Eiichiro Sumita, Fumiaki Sugaya, Hirofumi Yamamoto, and Seiichi Yamamoto. 2002. Toward a broad-coverage bilingual corpus for speech translation of travel conversations in the real world. In LREC, pages 147–152. Lawrence Venuti. 2012. The translation studies reader. Routledge. Mahsa Yarmohammadi, Vivek Kumar Rangarajan Sridhar, Srinivas Bangalore, and Baskaran Sankaran. 2013. Incremental segmentation and decoding strategies for simultaneous translation. In IJCNLP, pages 1032–1036. 148
Similar Southeast Asian Languages: Corpus-Based Case Study on Thai-Laotian and Malay-Indonesian Chenchen Ding, Masao Utiyama, Eiichiro Sumita Advanced Translation Technology Laboratory, ASTREC National Institute of Information and Communications Technology 3-5 Hikaridai, Seikacho, Sorakugun, Kyoto, 619-0289, Japan {chenchen.ding, mutiyama, eiichiro.sumita}@nict.go.jp Abstract This paper illustrates the similarity between Thai and Laotian, and between Malay and Indonesian, based on an investigation on raw parallel data from Asian Language Treebank. The crosslingual similarity is investigated and demonstrated on metrics of correspondence and order of tokens, based on several standard statistical machine translation techniques. The similarity shown in this study suggests a possibility on harmonious annotation and processing of the language pairs in future development. 1 Introduction Research and technique development of natural languages processing (NLP) on many understudied and low-resource Southeast Asian languages are launched in recent years. Some attempts on transferring available techniques on a well-developed language to an understudied language have been proved efficient (Ding et al., 2014). However, such a research direction must be established on an a priori observation on the similarity between languages. Generally, linguistically oriented issues, i.e., etymology, vocabulary, or syntactic structure, are discussed when two (or more) languages are referred to as “similar to each other”. In engineering practice, however, statistical metrics, i.e., word alignment precision, or word order differences, are more addressed in NLP applications. In this study, we focus on two Southeast Asian languages pairs, Thai-Laotian and Malay-Indonesian. Both language pairs have mutual intelligibility to a certain extend in spoken form. We conducted a datadriven investigation of the language pairs, trying to figure out the similarity from an engineering viewpoint, which can provide a basis of further NLP techniques development on these languages. The Asian Language Treebank (ALT) 1 (Utiyama and Sumita, 2015; Riza et al., 2016), containing approximately 20, 000 parallel sentence pairs on several Asian languages, facilitates statistical approaches. Specifically, we conducted word aligning on the two language pairs to find out the accordance on token-level, and translation experiments to find out the accordance on sentence-level. The experimental results reveal that the similarity on Thai-Laotian pair is nearly as same as that of Japanese-Korean, i.e., an extremely similar East Asian language pair; for the case of Malay-Indonesian, they are extremely similar to each other that basically they can be considered as two registers of one language. Based on the observation, we think the Thai-Laotian and Malay-Indonesian pairs can be handled simultaneously and harmoniously in further research, including corpus annotation, technique development, and NLP applications. The remaining of the paper is arranged as following. In section 2, we introduce the background of the languages discussed in this paper. In section 3, we describe the experiment settings used and discuss the numerical results obtained. Section 4 concludes the paper and provides our future work. 2 Background Specific approaches to process similar languages is an interesting topic in NLP (Vilar et al., 2007; Ding et al., 2015). In this research direction, a priori knowledge of the languages is required and specific approaches can thus be designed by taking advantage of the similarities to outperform a general approach. Here we provide outlines of linguistic features of the four languages mentioned in this paper. 1 http://www2.nict.go.jp/astrec-att/member/mutiyama/ALT/index.html 149 Proceedings of the 3rd Workshop on Asian Translation, pages 149–156, Osaka, Japan, December 11-17 2016.
Page 1 and 2:
WAT 2016 The 3rd Workshop on Asian
Page 3:
Preface Many Asian countries are ra
Page 6 and 7:
Technical Collaborators Luis Fernan
Page 9 and 10:
Table of Contents Overview of the 3
Page 11 and 12:
Conference Program December 12, 201
Page 13 and 14:
December 12, 2016 (continued) 12:00
Page 15 and 16:
Overview of the 3rd Workshop on Asi
Page 17 and 18:
LangPair Train Dev DevTest Test JPC
Page 19 and 20:
ASPEC JPC IITB BPPT pivot System ID
Page 21 and 22:
3.6 Tree-to-String Syntax-based SMT
Page 23 and 24:
• Use of other resources in addit
Page 25 and 26:
ASPEC JPC BPPT IITBC pivot Team ID
Page 27 and 28:
ut the adequacy is worse. As for AS
Page 29 and 30:
Figure 3: Official evaluation resul
Page 31 and 32:
Page 33 and 34:
Page 35 and 36:
Page 37 and 38:
Figure 11: Official evaluation resu
Page 39 and 40:
Figure 13: Official evaluation resu
Page 41 and 42:
Annotator A Annotator B all weighte
Page 43 and 44:
Kyoto-U 2 bjtu nlp UT-KAY 1 UT-KAY
Page 45 and 46:
Online B IITP-MT EHR Online A ≫
Page 47 and 48:
SYSTEM ID ID METHOD OTHER RESOURCES
Page 49 and 50:
SYSTEM ID ID METHOD OTHER BLEU RIBE
Page 51 and 52:
Page 53 and 54:
Page 55 and 56:
Page 57 and 58:
Page 59 and 60:
Hyoung-Gyu Lee, JaeSong Lee, Jun-Se
Page 61 and 62:
Translation of Patent Sentences wit
Page 63 and 64:
Chinese sentences contain fewer tha
Page 65 and 66:
Figure 3: NMT decoding with technic
Page 67 and 68:
Table 1: Automatic evaluation resul
Page 69 and 70:
Figure 6: Example of correct transl
Page 71 and 72:
K. Papineni, S. Roukos, T. Ward, an
Page 73 and 74:
Table 1: Examples of title, ingredi
Page 75 and 76:
text. In this section, we explain t
Page 77 and 78:
Table 3: Automatic evaluation BLEU/
Page 79 and 80:
Table 5: Number of fluency errors i
Page 81 and 82:
Kenneth Heafield. 2011. Kenlm: Fast
Page 83 and 84:
under-studied. MorphInd, a morphana
Page 85 and 86:
dimensions of 150 units in second h
Page 87 and 88:
distribution as received in JPO ade
Page 89 and 90:
Domain Adaptation and Attention-Bas
Page 91 and 92:
Once s M , which represents the ent
Page 93 and 94:
3.4.2 Ensemble of Attention Scores
Page 95 and 96:
Type Count Ratio (A) Correct 76 30.
Page 97 and 98:
Minh-Thang Luong, Hieu Pham, and Ch
Page 99 and 100:
Pair 1 Japanese [[ A ][ B ][ C ]
Page 101 and 102:
ID n-grams len freq m1 prevent, | 1
Page 103 and 104:
prediction accuracy with respect to
Page 105 and 106:
Reference: [ A To provide] [ B a to
Page 107 and 108:
Philipp Koehn. 2004. Statistical si
Page 109 and 110:
Therefore, we propose to use phrase
Page 111 and 112: Figure 2: An NRM considering phrase
Page 113 and 114: Mono Swap D right D left Acc. The r
Page 115 and 116: Method ja-en en-ja BLEU RIBES WER B
Page 117 and 118: Peng Li, Yang Liu, and Maosong Sun.
Page 119 and 120: Figure 1: The framework of NMT. Whe
Page 121 and 122: For long sentence, we discarded all
Page 123 and 124: As shown in the above tables and fi
Page 125 and 126: Translation systems and experimenta
Page 127 and 128: The number of TM training sentence
Page 129 and 130: where, f, p and e means a source, p
Page 131 and 132: former system can translate more th
Page 133 and 134: Lexicons and Minimum Risk Training
Page 135 and 136: 2.2 Parameter Optimization If we de
Page 137 and 138: ML (λ=0.0) ML (λ=0.8) MR (λ=0.0)
Page 139 and 140: Graham Neubig. 2013. Travatar: A fo
Page 141 and 142: Feature Space Common (h ) Domain 1
Page 143 and 144: Preprocessing Training Translation
Page 145 and 146: JPC ASPEC LM Method Ja-En En-Ja Ja-
Page 147 and 148: Translation Using JAPIO Patent Corp
Page 149 and 150: 4 Results Table 1 shows official ev
Page 151 and 152: Table 3: Examples of translation er
Page 153 and 154: An Efficient and Effective Online S
Page 155 and 156: #$ #%$ #$ !""
Page 157 and 158: This formula requires a context of
Page 159 and 160: Sentence Segmenter Parameters Dev.
Page 161: a meaningful baseline for related r
Page 165 and 166: τ around 0.71, and the Malay-Indon
Page 167 and 168: -0.9 -0.8 -0.7 -0.6 -0.5 -0.4 -0.3
Page 169 and 170: 1.800 1.600 1.400 1.200 1.000 0.800
Page 171 and 172: Integrating empty category detectio
Page 173 and 174: 3 Preordering with empty categories
Page 175 and 176: We performed the tests under two co
Page 177 and 178: the decoded sentence and the refere
Page 179 and 180: Kenneth Heafield. 2011. Kenlm: Fast
Page 181 and 182: Figure 1: Overview of KyotoEBMT. Th
Page 183 and 184: proportionally slower to compute (a
Page 185 and 186: 3.6 Ensembling Ensembling has previ
Page 187 and 188: when Chinese is also the language m
Page 189 and 190: Character-based Decoding in Tree-to
Page 191 and 192: where W s ∈ R d×d is a matrix an
Page 193 and 194: Model BLEU (BP) RIBES Character-bas
Page 195 and 196: The word-based NMT models cannot us
Page 197 and 198: Razvan Pascanu, Tomas Mikolov, and
Page 199 and 200: governs the grammaticality of the t
Page 201 and 202: 2.1 Quantization and Binarization o
Page 203 and 204: 3 Results Team Other Resources Syst
Page 205 and 206: Peter F Brown, John Cocke, Stephen
Page 207 and 208: Yonghui Wu, Mike Schuster, Zhifeng
Page 209 and 210: Language Sentence Chinese 该 / 钽
Page 211 and 212: Chinese or Japanese sentences Chine
Page 213 and 214:
4 Experiments and Results 4.1 Chine
Page 215 and 216:
6 Conclusion and Future Work In thi
Page 217 and 218:
Controlling the Voice of a Sentence
Page 219 and 220:
Figure 2: Flow of the voice predict
Page 221 and 222:
ecause the number of passive senten
Page 223 and 224:
controlling the sentence length wit
Page 225 and 226:
Chinese-to-Japanese Patent Machine
Page 227 and 228:
using the reordering oracles over t
Page 229 and 230:
Conference on Natural Language Proc
Page 231 and 232:
Figure 1: Hierarchical approach wit
Page 233 and 234:
newswire test and development set o
Page 235 and 236:
Source: the rain and cold wind on W
Page 237 and 238:
Residual Stacking of RNNs for Neura
Page 239 and 240:
2.2 Generalized Minimum Bayes Risk
Page 241 and 242:
5.0 4.5 4.0 Baseline model Enlarged
Page 243:
Felix Hill, Kyunghyun Cho, Sebastie
show all

December 11-16 2016 Osaka Japan

Create successful ePaper yourself

Delete template?

Save as template?