ESSLLI Workshop on Distributional Lexical Semantics Bridging the gap

نویسندگان

  • Marco Baroni
  • Stefan Evert
  • John A. Bullinaria
  • Yves Peirsman
  • Kris Heylen
  • Dirk Geeraerts
چکیده

This paper presents a series of new results on corpus derived semantic representations based on vectors of simple word co-occurrence statistics, with particular reference to word categorization performance as a function of window type and size, semantic vector dimension, and corpus size. A number of outstanding problems and difficulties with this approach are identified and discussed.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Modeling metaphor perception with distributional semantics vector space models

In this paper, we present a novel application of a computational model of word meaning to capture human judgments of the linguistic properties of metaphoricity, familiarity, and meaningfulness. We present data gathered from human subjects regarding their ratings of these properties over a set of word pairs specifically designed to exhibit varying degrees of metaphoricity. We then investigate wh...

متن کامل

Mapping conceptual features to referential properties

We report on initial work on bridging the conceptto-reference gap using distributional semantics. Specifically, we aim at predicting properties of countries, using distributional vectors to infer database information. Our results are highly encouraging, since we achieve an error reduction of 30% over the baseline and are not far from the upper bound.

متن کامل

Quantifiers and visual cognition: the processing of proportional and superlative most in Bulgarian and Polish

I provide experimental evidence that quantifier semantics guides visual verification processes (Lidz et al. 2011). I tested the processing of two majority quantifiers in Bulgarian and Polish: the proportional Most1, the counterpart of English most, and the superlative/relative Most2. Three obtained notable results have been obtained: (i) Most1 is verified by a Subtraction strategy, directly rep...

متن کامل

Proceedings of the Fifth International Workshop on Inference in Computational Semantics

s of Invited Talks Expressive Power and Complexity of Underspecified Representations . . . . . . . . . . . . . . . . . . 1 Christian Ebert Knowledge Harvesting and Fusion from Small and Large Corpora . . . . . . . . . . . . . . . . . . . . . 3 Patrick Pantel Bridging the gap between formal and computational semantics . . . . . . . . . . . . . . . . . . . . . . . . 5 Stephen Pulman

متن کامل

Can distributional approaches improve on Good Old-Fashioned Lexical Semantics?

In this position paper, I discuss some linguistic problems that computational work on lexical semantics has attempted to address in the past and the implications for alternative models which incorporate distributional information. I concentrate in particular on phenomena involving count/mass distinctions, where older approaches attempted to use lexical semantics in their models of syntax. I out...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2008