Bilingual Co-Training for Monolingual Hyponymy-Relation Acquisition
Oh, Jong-Hoon and Uchimoto, Kiyotaka and Torisawa, Kentaro

Article Structure

Abstract

This paper proposes a novel framework called bilingual co-training for a large-scale, accurate acquisition method for monolingual semantic knowledge.

Motivation

Acquiring and accumulating semantic knowledge are crucial steps for developing high-level NLP applications such as question answering, although it remains difficult to acquire a large amount of highly accurate semantic knowledge.

Bilingual Co-Training

Let S and T be two different languages, and let CL be a set of class labels to be obtained as a result of leaming/classification.

Acquisition of Hyponymy Relations from Wikipedia

Our system, which acquires hyponymy relations from Wikipedia based on bilingual co-training, is described in Figure 3.

Experiments

We used the MAY 2008 version of English Wikipedia and the JUNE 2008 version of Japanese Wikipedia for our experiments.

Related Work

Li and Li (2002) proposed bilingual bootstrapping for word translation disambiguation.

Conclusion

We proposed a bilingual co-training approach and applied it to hyponymy-relation acquisition from Wikipedia.

Topics

feature sets

Appears in 6 sentences as: feature set (2) feature sets (4)
In Bilingual Co-Training for Monolingual Hyponymy-Relation Acquisition
  1. Since the learning settings ( feature sets , feature values, training data, corpora, and so on) are usually different in two languages, the reliable part in one language may be overlapped by an unreliable part in another language.
    Page 1, “Motivation”
  2. (2008) but LFl—LF5 and SFl-SFQ are the same as their feature set .
    Page 4, “Acquisition of Hyponymy Relations from Wikipedia”
  3. Let us provide an overview of the feature sets used in Sumida et al.
    Page 4, “Acquisition of Hyponymy Relations from Wikipedia”
  4. These are the feature sets used in Sumida et al.
    Page 4, “Acquisition of Hyponymy Relations from Wikipedia”
  5. We also added some new items to the above feature sets .
    Page 4, “Acquisition of Hyponymy Relations from Wikipedia”
  6. We extract triples (infobox name, attribute type, attribute value) from the Wikipedia infoboxes and encode such information related to hyper and hypo in our feature set I F.3
    Page 5, “Acquisition of Hyponymy Relations from Wikipedia”

See all papers in Proc. ACL 2009 that mention feature sets.

See all papers in Proc. ACL that mention feature sets.

Back to top.

semantic relations

Appears in 6 sentences as: semantic relation (2) semantic relations (7)
In Bilingual Co-Training for Monolingual Hyponymy-Relation Acquisition
  1. This paper proposes a novel framework for a large-scale, accurate acquisition method for monolingual semantic knowledge, especially for semantic relations between nominals such as hyponymy and meronymy.
    Page 1, “Motivation”
  2. The acquisition of semantic relations between nominals can be seen as a classification task of semantic relations — to determine whether two nominals hold a particular semantic relation (Girju et al., 2007).
    Page 1, “Motivation”
  3. Recently, there has been increased interest in semantic relation acquisition from corpora.
    Page 8, “Related Work”
  4. Some regarded Wikipedia as the corpora and applied handcrafted or machine-learned rules to acquire semantic relations (Herbelot and Copestake, 2006; Kazama and Torisawa, 2007; Ruiz-casado et al., 2005; Nastase and Strube, 2008; Sumida et al., 2008; Suchanek et al., 2007).
    Page 8, “Related Work”
  5. Several researchers who participated in SemEval-07 (Girju et al., 2007) proposed methods for the classification of semantic relations between simple nominals in English sentences.
    Page 8, “Related Work”
  6. However, the previous work seldom considered the bilingual aspect of semantic relations in the acquisition of monolingual semantic relations .
    Page 8, “Related Work”

See all papers in Proc. ACL 2009 that mention semantic relations.

See all papers in Proc. ACL that mention semantic relations.

Back to top.

F-measure

Appears in 3 sentences as: F-measure (3)
In Bilingual Co-Training for Monolingual Hyponymy-Relation Acquisition
  1. Experimental results show that our approach improved the F-measure by 3.6—10.3%.
    Page 1, “Abstract”
  2. (2008), which was only applied for Japanese and achieved around 80% in F-measure .
    Page 2, “Motivation”
  3. Experimental results showed that our method based on bilingual co-training improved the performance of monolingual hyponymy-relation acquisition about 3.6—10.3% in the F-measure .
    Page 2, “Motivation”

See all papers in Proc. ACL 2009 that mention F-measure.

See all papers in Proc. ACL that mention F-measure.

Back to top.

hypernym

Appears in 3 sentences as: hypernym (3)
In Bilingual Co-Training for Monolingual Hyponymy-Relation Acquisition
  1. In their approach, a common substring in a hypernym and a hyponym is assumed to be one strong clue for recognizing that the two words constitute a hyponymy relation.
    Page 2, “Motivation”
  2. A hyponymy-relation candidate is then extracted from the tree structure by regarding a node as a hypemym candidate and all its subordinate nodes as hyponym candidates of the hypernym candidate (e.g., (TIGER, TAXONOMY) and (TIGER, SIBERIAN TIGER) from Figure 4).
    Page 4, “Acquisition of Hyponymy Relations from Wikipedia”
  3. For example, “List of artists” is converted into “artists” by lexical pattern “list of Hyponymy-relation candidates whose hypernym candidate matches such a lexical pattern are likely to be valid (e.g., (List of artists, Leonardo da Vinci)).
    Page 4, “Acquisition of Hyponymy Relations from Wikipedia”

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

See all papers in Proc. ACL that mention hypernym.

Back to top.

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