Acquistion of the morphological structure of the lexicon based on lexical similarity and formal analogy

Hathout, Nabil

doi:10.3115/1627328.1627329

Cited by 14 publications

(16 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analogy is a relationship between four objects: A, B, C, and D usually noted as A : B :: C : D . It states that A is to B as C is to D where the ratio between A and B is the same as the ratio between C and D. Here, we consider analogy as a possible way to explain derivation between words as it is already used from the ancient Greek and Latin grammatical tradition up to recent works on computational linguistics, like (Hathout, 2008(Hathout, , 2009. Various formalisations of analogy have been proposed in (Yvon, 2003;Lepage, 2004;Stroppa and Yvon, 2005).…”

Section: Proportional Analogymentioning

confidence: 99%

Untitled

Fam¹,

Lepage

2018

Proceedings of The

View full text Add to dashboard Cite

This paper presents the system submitted by IPS-WASEDA University for CoNLL-SIGMORPHON 2018 Shared Task 1: Type level inflection. We develop a system based on a holistic approach which considers wholeword form as a unit, instead of breaking them into smaller pieces (e,g. morphemes) like the baseline systems does. We also implement an encoder-decoder model which has recently become the new standard in many natural language processing (NLP) tasks. The results show that the neural approach outperforms the baseline and our holistic approach on bigger resources settings. The use of data augmentation helps to improve the performance of the model in lower resources settings, although it still cannot beat the other systems. In the end, for the low resources setting, our holistic approach performs best in comparison to the baseline and the neural approach (even with data augmentation).

show abstract

Section: Proportional Analogymentioning

confidence: 99%

Untitled

Fam¹,

Lepage

2018

Proceedings of The

View full text Add to dashboard Cite

show abstract

“…We use the method proposed by (Hathout, 2008) to capture this semantic similarity. Definientia are described by a large number of redundant features based on lemmata, POSs and syntactic dependencies.…”

Section: Semantic Typing Of the Morphological Definitionsmentioning

confidence: 99%

Acquisition and enrichment of morphological and morphosemantic knowledge from the French Wiktionary

Hathout¹,

Sajous²,

Calderone³

2014

Proceedings of Workshop on Lexical and Grammatical Resources for Language Processing

Self Cite

View full text Add to dashboard Cite

To cite this version:Nabil Hathout, Franck Sajous, Basilio Calderone. Acquisition and enrichment of morphological and morphosemantic knowledge from the French Wiktionary. Workshop on Lexical and Grammatical Resources for Language Processing, COLING 2014, 2014 AbstractWe present two approaches to automatically acquire morphologically related words from Wiktionary. Starting with related words explicitly mentioned in the dictionary, we propose a method based on orthographic similarity to detect new derived words from the entries' definitions with an overall accuracy of 93.5%. Using word pairs from the initial lexicon as patterns of formal analogies to filter new derived words enables us to rise the accuracy up to 99%, while extending the lexicon's size by 56%. In a last experiment, we show that it is possible to semantically type the morphological definitions, focusing on the detection of process nominals.

show abstract

“…We used Proxinette, a measure of morphological similarity defined in (Hathout, 2008), to identify the morphological definitions. Proxinette is designed to reduce the search space for derivational analogies.…”

Section: Morphological Definitionsmentioning

confidence: 99%

“…Along the same line, Zweigenbaum and Grabar (2003) acquire semantic information from a medical corpus and use it to detect morphologically derived words. More recently, Hathout (2008) uses the TLFi to discover morphologically related words by combining orthographic and semantic similarity with formal analogy.…”

Section: Related Workmentioning

confidence: 99%

Proceedings of Workshop on Lexical and Grammatical Resources for Language Processing

Baptista¹,

Bhattacharyya

Fellbaum³

et al. 2014

View full text Add to dashboard Cite

ii IntroductionThe first instance of the Workshop on Lexical and Grammatical Resources for Language Processing (LG-LP 2014) took place on August 24th in Dublin, in conjunction with COLING 2014. It was co-sponsored by ASIALEX and endorsed by SIGLEX.The workshop aimed to bring together members of the language-resource (LR) landscape, focusing on complex linguistic knowledge that requires linguistic expertise, e.g. on dictionaries, ontologies and grammars. Such manually-built resources are key to the development of natural language processing (NLP) tools and applications. We intended to strengthen the cohesion of the scientific 'production chain' spanning from the construction of LRs to their exploitation in hybrid or symbolic NLP. It is necessary to increase mutual awareness between researchers along this production chain, regarding their activities, skills and needs, in view of improving the building processes of the resources, their validation and their exploitation.Many linguists are comfortable with descriptive tasks such as checking lexical entries for a given feature, even if each entry requires analysing or pondering. On the other hand, computer scientists are familiar with formalization and, usually, with notions such as falsifiability or reproducibility, which are fundamental to sciences. Combining all these skills is likely to stimulate innovation. The workshop offered an opportunity of interaction which is required to overcome the compartmentalization between humanities and sciences, and to intensify co-operation between the two ends of the chain. Researchers were encouraged to exchange about how they manage to face several challenges:• the context of this production chain requires that they not be content with understanding phenomena, but also achieve actual production of formalized results;• resulting resources should reach a reasonable level of verifiability, e.g. by finding formal or syntactic bases as a support to semantic description;• methods which are able to cover the most diverse languages are to be preferred;• the format of manual construction of complex LRs must be highly readable, so that errors can be easily detected and corrected;• conceptual models are not easy to assign to large amounts of language data; due to idiosyncratic behaviour of lexical entries, it is often required to manually examine them individually as regards syntax or semantics;• many multiword expressions, including support-verb constructions, are somewhere halfway between compositional and non-compositional constructs;• actual implementation of NLP systems and real-world applications may provide feedback on complex lexical and grammatical LRs used in them, but experimentation is required to accurately relate features of the LRs with features of results obtained in NLP.We received 31 submissions and accepted 19: an acceptance rate of 61%. We scheduled 10 papers for oral presentation and 9 as posters. The workshop closed with a general discussion.We would like to thank the members of the Program Committee for their timely...

show abstract

Acquistion of the morphological structure of the lexicon based on lexical similarity and formal analogy

Cited by 14 publications

References 21 publications

Untitled

Untitled

Acquisition and enrichment of morphological and morphosemantic knowledge from the French Wiktionary

Proceedings of Workshop on Lexical and Grammatical Resources for Language Processing

Contact Info

Product

Resources

About