Wednesday was the final day of the IPSJ meeting. I’ve got more comments on the papers that I saw that day below.<\/p>\n
<\/p>\n
Yoshihisa Shinozawa – “Extended simple recurrent networks by using
\nbigram” – Keio University<\/p>\n
I had a tough time understanding this paper: I don’t know much about
\n word nets using perceptrons. I also had a tough time following his
\n Japanese. <\/p>\n
—<\/p>\n
Takashi Kawakami, Hisashi Suzuki – “A calculation of Word Similarity
\nusing Decision Lists” – Chuo University. <\/p>\n
Given two “words” (kana, kanji or kanji, kanji or probably kana, kana)
\nthe system will return a number from 0 to 1, where 0 is not similar,
\nand 1 similar. Can we use this for disambiguation? They are using
\ndecision lists. The look at thing have been categorized and not \u590f\u306f
\n\u5bd2\u3044\u3067\u3059 and \u51ac\u306f\u5bd2\u3044\u3067\u3059\u3000and check how similar the two are to each
\nother. Use 12 novels available for free on the internet. In the
\npaper they present a table with similar terms. There are lots of
\nnumbers (1 and 2 are similar, and some antonyms as well, such as
\nmother, father.) <\/p>\n
There were lots of questions on this paper as well. In the table he
\npresents, also “\u6708” and “\u5e74” came out to be similar. In some ways
\nthey are only similar in some certain contexts. <\/p>\n
—<\/p>\n
Akiko Aizawaq – “On the Effect of Corpus Size in Words Similarity
\nCalculation” – National Institute of Informatics<\/p>\n
The main focus is on how the corpus quality for extracting synonyms
\nchanges the output. There are two ways to do the extraction:
\npattern-based (A such as B) and co-occurrence vectors. When the
\ncorpora are made larger, does that help? (Particularly in the case of
\nthe vector-based approaches?) The conclusion is that larger corpora
\nhelp, but you need to use a simple filter to avoid bias that emerges
\nfrom high frequency words. <\/p>\n
—<\/p>\n
Takahiro Ono, Akira Suganuma, Rin-ichiro Taniguchi – “Extraction of
\nthe sentences whose modification relation is misunderstood for a
\nwriting tool” – Kyuushyuu Daigaku<\/p>\n
They do work on automatic text revision. Their focus here is
\nindicating sentences which are difficult to understand and might
\neasily be misinterpreted. They focus on nouns with multiple
\nmodifiers and dependency structure between clauses. It was very
\ninteresting for me, but of course I had trouble following some of the
\nJapanese grammar vocabulary. <\/p>\n
They did an experiment with humans. <\/p>\n
—<\/p>\n
Yu Akiyama, Masahiro Fukaya, Hajime Ohiwa, Masakazu Tateno –
\n“Extending Kwic Concordance by Standardization of sentence pattern” –
\nKeio University \/ Fuji Xerox<\/p>\n
This one was skipped – cancelled at the last minute.<\/p>\n
—<\/p>\n
Yoshinobu Kano, Yusuke Miyao, Junichi Tsuji – “Candidate Reduction in
\nSyntactic Structure Analysis with Pure Incremental Processing” –
\nUniversity of Tokyo<\/p>\n
I didn’t really follow this talk. I’m not strong on parsing, and
\ncertainly not strong on parsing when it is discussed in Japanese.<\/p>\n
—<\/p>\n
Manuel Medina Gonzalex and Hirosato Nomura – “A Cross-Lingual Grammar
\nModel and its Application to Japanese-Spanish Machine Translation” –
\nKyuushyuu University<\/p>\n
First talk in English. Their translation model is based on the Alt\/JE
\nmodel. They try to predict certain Spanish features based on the
\nJapanese sentence (for features that do not exist in Spanish.) For
\nexample, gender and number. <\/p>\n
—<\/p>\n
Yohei Seki, Koji Eguchi, Noriko Kando, Masaki Aono – “An Analysis of
\nOpinion-focused Summarization using Opinion Annotation” – Toyohashi
\nUniversity of Technology \/ National Institute of Informatics<\/p>\n
—<\/p>\n
Shunpei Tatebayashi, Makoto Haraguchi – “A Coherent Text Summarization
\nMethod based on Semantic Correlations between Sentences” – Hokkaidou
\nDaigaku <\/p>\n
They want to summarize the important parts of long stories,
\nabstracting out the events and common themes in the stories. I
\nthink. They are looking at summarization the preserves and reflects
\nthe structure of the input – so analyze the segments in the text, and
\nwhen summarizing only extract segments that are related. They compare
\nto some graph-based summarization methods too, so it might be
\ninterested to read in further detail later. <\/p>\n
—<\/p>\n
Hu Bai, Ueda Yoshihiro, Oka Mamiko – “Phrase-Representation
\nSummarization Method for Chinese” – Fuji Xerox<\/p>\n
The second (and final) talk in English.
\nPhrase based summarization for Chinese for IR support. The Japanese
\nversion that this is based on does something like sentence
\nsimplification for summarization based on a dependency structure
\nparse. They use LFG to parse the Chinese, and generate the summary
\nsentence using a syntactical pattern. <\/p>\n","protected":false},"excerpt":{"rendered":"
Wednesday was the final day of the IPSJ meeting. I’ve got more comments on the papers that I saw that day below. Yoshihisa Shinozawa – “Extended simple recurrent networks by using bigram” – Keio University I had a tough time understanding this paper: I don’t know much about word nets using perceptrons. I also had […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[10],"tags":[],"_links":{"self":[{"href":"https:\/\/fugutabetai.com\/blog\/wp-json\/wp\/v2\/posts\/139"}],"collection":[{"href":"https:\/\/fugutabetai.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/fugutabetai.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/fugutabetai.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/fugutabetai.com\/blog\/wp-json\/wp\/v2\/comments?post=139"}],"version-history":[{"count":0,"href":"https:\/\/fugutabetai.com\/blog\/wp-json\/wp\/v2\/posts\/139\/revisions"}],"wp:attachment":[{"href":"https:\/\/fugutabetai.com\/blog\/wp-json\/wp\/v2\/media?parent=139"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/fugutabetai.com\/blog\/wp-json\/wp\/v2\/categories?post=139"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/fugutabetai.com\/blog\/wp-json\/wp\/v2\/tags?post=139"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}