tag:blogger.com,1999:blog-9145120678290195131.post5491702584360494696..comments2024-03-21T16:22:06.514+02:00Comments on Probably Approximately a Scientific Blog: AntonymyVered Shwartzhttp://www.blogger.com/profile/17531957962535846245noreply@blogger.comBlogger4125tag:blogger.com,1999:blog-9145120678290195131.post-36079654214715780432016-11-23T21:43:23.370+02:002016-11-23T21:43:23.370+02:00I think it depends on the application, and in the ...I think it depends on the application, and in the case of search it's probably a trade-off between precision (not to include antonyms of the query) and recall (to include also hyponyms/hypernyms of the query). It's best if we could have a model that accurately predicts all these relations, but as you know we're not there yet :)<br /><br />Sure! I currently work on predicate alignment, but in the future I definitely plan to go back to work on the relations that are harder to recognize (synonyms and antonyms).Vered Shwartzhttps://www.blogger.com/profile/17531957962535846245noreply@blogger.comtag:blogger.com,1999:blog-9145120678290195131.post-89843855839113138182016-11-23T21:14:31.329+02:002016-11-23T21:14:31.329+02:00Ah yes, we considered both antonymy and hypernymy ...Ah yes, we considered both antonymy and hypernymy in the ACL paper. To be honest, I have always felt that antonyms are more interesting than hypernyms linguistically, and that detecting them is probably more useful for downstream applications (to reuse your search example to illustrate this point: should the results include "public transport" maps in addition to "subway" maps? Maybe, maybe not?). So I was glad when I saw your paper(s) at the CogALex workshop! <br /><br />Your post to me suggests that you are interested in continuing work in this direction. Is that correct? If so, I think that would be great. :)microthhttps://www.blogger.com/profile/11282420025485235953noreply@blogger.comtag:blogger.com,1999:blog-9145120678290195131.post-15403349892449811692016-11-23T20:38:03.143+02:002016-11-23T20:38:03.143+02:00Hi Michael, thanks for the comment and the referen...Hi Michael, thanks for the comment and the references! I actually read your ACL paper a few months ago, but I read it as related work for hypernymy detection so it slipped my mind now :) I will give it another reading and add the other references to my reading list. Thanks!<br /><br />By the way, most of the posts in my blog only touch the surface of the topics they discuss, both because I write about topics other than my main research, and because I try to simplify it. So comments with complementary information and references are always welcome!<br /><br />Regarding the same POS tag, I thought about related contrasting words (e.g. thirsty/drink), which I don't consider as antonyms, but I didn't think of derivations. That makes sense.Vered Shwartzhttps://www.blogger.com/profile/17531957962535846245noreply@blogger.comtag:blogger.com,1999:blog-9145120678290195131.post-56272419704564292062016-11-23T20:06:34.274+02:002016-11-23T20:06:34.274+02:00> the two words within each pair both share the...> the two words within each pair both share the same<br />> part of speech (comment if you can think of <br />> a negative example!)<br />><br /><br />Well, there is some discussion on this in the linguistic literature (e.g., Fellbaum, 1995). But typical examples involve words that are derived from (or are at least related to) a word from the other word category (e.g. loving/hate, loved/hatred).<br /><br />In general, there are lot of ideas/definitions/studies in the linguistic literature that this article only touches the surface of (e.g., the difference between opposites/antonmys and the question whether antonymy is a relation between words or between concepts). If you were interested in more background material, I would recommend (parts of) Stephen Jones' book. That and work by M. Lynne Murphy were basically the starting points for our work on paradigmatic relations at ACL 2014 (apologies for the shameless plug :)).<br /><br />Fellbaum, C. 1995. Co-Occurrence and Antonymy. International Journal of Lexicography, 8 (1995), pp. 281--303.<br /><br />Jones, S. 2002. Antonymy: a corpus-based perspective. London, Routledge.<br /><br />Roth, M. and Schulte im Walde, S. 2014. Combining word patterns and discourse markers for paradigmatic relation classification. Proceedings of ACL (Vol. 2), pp. 524--530.microthhttps://www.blogger.com/profile/11282420025485235953noreply@blogger.com