Meni Adler

An Unsupervised Morpheme-Based HMM for Hebrew Morphological Disambiguation

Morphological disambiguation is the process of assigning one set of morphological features to each individual word in a text. When the word is ambiguous (there are several possible analyses for the word), a disambiguation procedure based on the word context must be applied. This paper deals with morphological disambiguation of the Hebrew language, which combines morphemes into a word in both agglutinative and fusional ways. We present an un-supervised stochastic model - the only resource we use is a morphological analyzer-which deals with the data sparseness problem caused by the affixational morphology of the Hebrew language.We present a text encoding method for languages with affixational morphology in which the knowledge of word formation rules (which are quite restricted in Hebrew) helps in the disambiguation. We adapt HMM algorithms for learning and searching this text representation, in such a way that segmentation and tagging can be learned in parallel in one step. Results on a large scale evaluation indicate that this learning improves disambiguation for complex tag sets. Our method is applicable to other languages with affix morphology.

Enhancing Unlexicalized Parsing Performance Using a Wide Coverage Lexicon, Fuzzy Tag-Set Mapping, and EM-HMM-Based Lexical Probabilities

We present a framework for interfacing a PCFG parser with lexical information from an external resource following a different tagging scheme than the treebank. This is achieved by defining a stochastic mapping layer between the two resources. Lexical probabilities for rare events are estimated in a semi-supervised manner from a lexicon and large unannotated corpora. We show that this solution greatly enhances the performance of an unlexicalized Hebrew PCFG parser, resulting in state-of-the-art Hebrew parsing results both when a segmentation oracle is assumed, and in a real-word parsing scenario of parsing unsegmented tokens.

Ontology Evaluation through Text Classification

We present a new method to evaluate a search ontology, which relies on mapping ontology instances to textual documents. On the basis of this mapping, we evaluate the adequacy of ontology relations by measuring their classification potential over the textual documents. This data-driven method provides concrete feedback to ontology maintainers and a quantitative estimation of the functional adequacy of the ontology relations towards search experience improvement. We specifically evaluate whether an ontology relation can help a semantic search engine support exploratory search. We test this ontology evaluation method on an ontology in the Movies domain, that has been acquired semi-automatically from the integration of multiple semi-structured and textual data sources (e.g., IMDb and Wikipedia). We automatically construct a domain corpus from a set of movie instances by crawling the Web for movie reviews (both professional and user reviews). The 1-1 relation between textual documents (reviews) and movie instances in the ontology enables us to translate ontology relations into text classes. We verify that the text classifiers induced by key ontology relations (genre, keywords, actors) achieve high performance and exploit the properties of the learned text classifiers to provide concrete feedback on the ontology. The proposed ontology evaluation method is general and relies on the possibility to automatically align textual documents to ontology instances.

Noun Phrase Chunking in Hebrew: Influence of Lexical and Morphological Features

We present a method for Noun Phrase chunking in Hebrew. We show that the traditional definition of base-NPs as non-recursive noun phrases does not apply in Hebrew, and propose an alternative definition of Simple NPs. We review syntactic properties of Hebrew related to noun phrases, which indicate that the task of Hebrew SimpleNP chunking is harder than base-NP chunking in English. As a confirmation, we apply methods known to work well for English to Hebrew data. These methods give low results (F from 76 to 86) in Hebrew. We then discuss our method, which applies SVM induction over lexical and morphological features. Morphological features improve the average precision by ~0.5%, recall by ~1%, and F-measure by ~0.75, resulting in a system with average performance of 93% precision, 93.4% recall and 93.2 F-measure.

Multi-Level Alignments As An Extensible Representation Basis for Textual Entailment Algorithms

A major problem in research on Textual Entailment (TE) is the high implementation effort for TE systems. Recently, interoperable standards for annotation and preprocessing have been proposed. In contrast, the algorithmic level remains unstandardized, which makes component re-use in this area very difficult in practice. In this paper, we introduce multi-level alignments as a central, powerful representation for TE algorithms that encourages modular, reusable, multilingual algorithm development. We demonstrate that a pilot open-source implementation of multi-level alignment with minimal features competes with state-of-theart open-source TE engines in three languages.

Specifying and Annotating Reduced Argument Span Via QA-SRL

Prominent semantic annotations take an inclusive approach to argument span annotation, marking arguments as full constituency subtrees. Some works, however, showed that identifying a reduced argument span can be beneficial for various semantic tasks. While certain practical methods do extract reduced argument spans, such as in Open-IE , these solutions are often ad-hoc and system-dependent, with no commonly accepted standards. In this paper we propose a generic argument reduction criterion, along with an annotation procedure, and show that it can be consistently and intuitively annotated using the recent QA-SRL paradigm.

A Consolidated Open Knowledge Representation for Multiple Texts

We propose progressing from Open Information Extraction (OIE) to Open Knowledge Representation (OKR), aiming to represent the information conveyed jointly in a set of texts in an open text-based manner. We do so by consolidating OIE extractions based on entity and predicate coreference, while modeling information containment between coreferring elements via lexical entailment. We suggest that generating OKR structures can be a useful step in the NLP pipeline, to get semantic applications an easy handle on consolidated information across multiple texts.