Unknown lexical items present a major obstacle to the development of broadcoverage semantic role labeling systems. We address this problem with a semisupervised learning approach which acquires training instances for unseen verbs from an unlabeled corpus. Our method relies on the hypothesis that unknown lexical items will be structurally and semantically similar to known items for which annotat...

The role of lexical resources is often understated in NLP research. The complexity of Chinese, Japanese and Korean (CJK) poses special challenges to developers of NLP tools, especially in the area of word segmentation (WS), information retrieval (IR), named entity extraction (NER), and machine translation (MT). These difficulties are exacerbated by the lack of comprehensive lexical resources, e...

In this paper, we present our system addressing Task 1 of CL-SciSumm Shared Task at BIRNDL 2016. Our system makes use of lexical and syntactic dependency cues, and applies rule-based approach to extract text spans in the Reference Paper that accurately reflect the citances. Further, we make use of lexical cues to identify discourse facets of the paper to which cited text belongs. The lexical an...

Many NLP systems are based on lexical data. The development costs of such data are a major drawback in such NLP systems. In order to cut these costs, we adopt a strategy inspired from "opensource" projects to allow volunteers to collaborate in the creation of a multilingual lexical database. For this, we had to specify and develop tools to manage a lexical database containing information comple...

The lack of large-scale, freely available and durable lexical resources, and the consequences for NLP, is widely acknowledged but the attempts to cope with usual bottlenecks preventing their development often result in dead-ends. This article introduces a language-independent, semi-automatic and endogenous method for enriching lexical resources, based on collaborative editing and random walks t...

Relational databases have been used to represent lexical knowledge since the days of machine-readable dictionaries. However, although software engineering provides a methodological framework for the construction of databases, most developing efforts focus on content, implementation and timesaving issues, and forget about the software engineering aspects of database construction. We have defined...

This paper discusses the issue of language sampling in the development of a framework for multilingual lexical representation (MLR). The approach to MLR adopted here aims at developing a hierarchical lexical structure which permits sharing of information across languages. The multilingual nature of such a lexical hierarchy raises methodological and theoretical issues for its design and developm...

The term lexical approach was introduced in 1993 by Michael Lewis, who observed that "language consists of grammaticalized lexis, not lexicalised grammar" (The Lexical Approach, 1993).

BACKGROUND children with Specific Language Impairment (SLI) have difficulties with speech processing. These difficulties affect the development of phonologic representations. AIM to evaluate the abilities of children with normal language development (NLD) and those with SLI in distinguishing words from non-words in a lexical decision task. METHOD two groups were involved in this study: the ...