Detecting Compositionality in Multi-Word Expressions.
Korkontzelos, Ioannis and Manandhar, Suresh

Article Structure

Abstract

Identifying whether a multi-word expression (M WE) is compositional or not is important for numerous NLP applications.

Introduction and related work

Multi-word expressions (M WEs) are sequences of words that tend to cooccur more frequently than chance and are either idiosyncratic or decomposable into multiple simple words (Baldwin, 2006).

Proposed approach

Let us consider the non-compositional M WE “red carpet”.

Test set of M WEs

To the best of our knowledge there are no noun compound datasets accompanied with compositionality judgements available.

Evaluation setting and results

The sense induction component of our algorithm depends upon 3 parameters: P1 is the G2 threshold below which noun are removed from corpora.

Unsupervised parameter tuning

We followed Korkontzelos et al.

Conclusion and Future Work

We hypothesized that sense induction can assist in identifying compositional M WEs.

Topics

similarity measures

Appears in 5 sentences as: similarity measure (2) similarity measures (3)
In Detecting Compositionality in Multi-Word Expressions.
  1. In this paper, we propose a novel unsupervised approach that compares the major senses of a MWE and its semantic head using distributional similarity measures to test the compositionality of the MWE.
    Page 1, “Introduction and related work”
  2. Lee (1999) shows that J performs better than other symmetric similarity measures such as cosine, Jensen-Shannon divergence, etc.
    Page 2, “Proposed approach”
  3. Given the major uses of a MWE and its semantic head, the MWE is considered as compositional, when the corresponding distributional similarity measure (Jc or 197,) value is above a parameter threshold, sim.
    Page 2, “Proposed approach”
  4. Our method was evaluated for each (P1, P2, P3) combination and similarity measures J0 and 197,, separately.
    Page 3, “Evaluation setting and results”
  5. The best performing distributional similarity measure is an.
    Page 4, “Unsupervised parameter tuning”

See all papers in Proc. ACL 2009 that mention similarity measures.

See all papers in Proc. ACL that mention similarity measures.

Back to top.

WordNet

Appears in 5 sentences as: WordNet (5)
In Detecting Compositionality in Multi-Word Expressions.
  1. The evaluation set is derived from WordNet in a semi-supervised way.
    Page 1, “Abstract”
  2. Thirdly, we propose a semi-supervised approach for extracting non-compositional MWEs from WordNet , to decrease annotation cost.
    Page 1, “Introduction and related work”
  3. Given a MWE, a set of queries is created: All synonyms of the M WE extracted from WordNet are collectedl.
    Page 2, “Proposed approach”
  4. For each of the 52, 217 MWEs of WordNet 3.0 (Miller, 1995) we collected:
    Page 2, “Test set of M WEs”
  5. We proposed a semi-supervised way to extract non-compositional MWEs from WordNet .
    Page 4, “Conclusion and Future Work”

See all papers in Proc. ACL 2009 that mention WordNet.

See all papers in Proc. ACL that mention WordNet.

Back to top.

distributional similarity

Appears in 4 sentences as: distributional similarity (4)
In Detecting Compositionality in Multi-Word Expressions.
  1. In this paper, we propose a novel unsupervised approach that compares the major senses of a MWE and its semantic head using distributional similarity measures to test the compositionality of the MWE.
    Page 1, “Introduction and related work”
  2. We used two techniques to measure the distributional similarity of major uses of the M WE and its semantic head, both based on Jaccard coefi‘icient (J).
    Page 2, “Proposed approach”
  3. Given the major uses of a MWE and its semantic head, the MWE is considered as compositional, when the corresponding distributional similarity measure (Jc or 197,) value is above a parameter threshold, sim.
    Page 2, “Proposed approach”
  4. The best performing distributional similarity measure is an.
    Page 4, “Unsupervised parameter tuning”

See all papers in Proc. ACL 2009 that mention distributional similarity.

See all papers in Proc. ACL that mention distributional similarity.

Back to top.

semi-supervised

Appears in 3 sentences as: semi-supervised (3)
In Detecting Compositionality in Multi-Word Expressions.
  1. The evaluation set is derived from WordNet in a semi-supervised way.
    Page 1, “Abstract”
  2. Thirdly, we propose a semi-supervised approach for extracting non-compositional MWEs from WordNet, to decrease annotation cost.
    Page 1, “Introduction and related work”
  3. We proposed a semi-supervised way to extract non-compositional MWEs from WordNet.
    Page 4, “Conclusion and Future Work”

See all papers in Proc. ACL 2009 that mention semi-supervised.

See all papers in Proc. ACL that mention semi-supervised.

Back to top.

PDF available from www.aclweb.org.
Send us an email