Author name cluster

Michael Elhadad

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

AAAI Conference 2016 Conference Paper

Topic Concentration in Query Focused Summarization Datasets

Tal Baumel
Raphael Cohen
Michael Elhadad

Query-Focused Summarization (QFS) summarizes a document cluster in response to a specific input query. QFS algorithms must combine query relevance assessment, central content identification, and redundancy avoidance. Frustratingly, state of the art algorithms designed for QFS do not significantly improve upon generic summarization methods, which ignore query relevance, when evaluated on traditional QFS datasets. We hypothesize this lack of success stems from the nature of the dataset. We define a task-based method to quantify topic concentration in datasets, i. e. , the ratio of sentences within the dataset that are relevant to the query, and observe that the DUC 2005, 2006 and 2007 datasets suffer from very high topic concentration. We introduce TD-QFS, a new QFS dataset with controlled levels of topic concentration. We compare competitive baseline algorithms on TD-QFS and report strong improvement in ROUGE performance for algorithms that properly model query relevance as opposed to generic summarizers. We further present three new and simple QFS algorithms, RelSum, ThresholdSum, and TFIDF-KLSum that outperform state of the art QFS algorithms on the TD-QFS dataset by a large margin.

PDF Details

AAAI Conference 1993 Conference Paper

Generating Argumentative Judgment Determiners

Michael Elhadad

This paper presents a procedure to generate judgment determiners, e. g. , many, few. Although such determiners carry very little objective information, they are extensively used in everyday language. The paper presents a precise characterization of a class of such determiners using three semantic tests. A conceptual representation for sets is then derived from this characterization which can serve as an input to a generator capable of producing judgment determiners. In a second part, a set of syntactic features controlling the realization of complex determiner sequences is presented. The ma@ing from the conceptual input to this set of syntactic features is then presented. The presented procedure relies on a description of the speaker’ s arg-gumentative intent to control this mapping and to select appropriate judgment determiners.

PDF Details

AAAI Conference 1991 Conference Paper

Generating Adjectives to Express the Speaker’s Argumentative Intent

Michael Elhadad

We address the problem of generating adjectives in a text generation system. We distinguish between usages of adjectives informing the hearer of a property of an object and usages expressing an intention of the speaker, or an argumentative orientation. For such argumentative usages, we claim that a generator cannot simply map from information in the knowledge base to adjectives. Instead, we identify various knowledge sources necessary to decide whether to use an adjective, what adjective should be selected and what syntactic function it should have. We show how these decisions interact with lexical properties of adjectives and the syntax of the clause. We propose a mechanism for adjective selection and illustrate it in the context of the eXpktnatiOn component of the ADVISORexpert system. We describe an implementation of adjective selection using a version of Functional Unification Grammars.

PDF Details