Articles

Meaning Representation Parsing Charles Welch1, Jonathan K. Kummerfeld1, Song Feng2, Rada Mihalcea1 University of Michigan1, IBM Research2 {cfwelch, jkummerf, mihalcea}@umich.edu, sfeng@us.ibm.com Abstract In this paper we explore the role played by world knowledge in semantic parsing. We look at the types of errors that currently exist in a state-of-the-art Abstract …...

We present new data and semantic parsing methods for the problem of mapping English sentences to Bash commands (NL2Bash). Our long-term goal is to enable any user to perform operations such as file manipulation, search, and application-specific scripting by simply stating their goals in English. We take a first step …...

Noun compounds are interesting constructs in Natural Language Processing (NLP). Interpretation of noun compounds is the task of uncovering a relationship between component nouns of a noun compound. There has not been much progress in this field due to lack of a standardized set of relation inventory and associated annotated …...

Temporal relations between events and time expressions in a document are often modeled in an unstructured manner where relations between individual pairs of time expressions and events are considered in isolation. This often results in inconsistent and incomplete annotation and computational modeling. We propose a novel annotation approach where events …...

Meaning Representations for Spanish Noelia Migueles-Abraira, Rodrigo Agerri, Arantza Diaz de Ilarraza IXA NLP Group, University of the Basque Country UPV/EHU noeliamigueles@gmail.com,{rodrigo.agerri,a.diazdeilarraza}@ehu.eus Abstract Until recently, semantic annotations for different semantic phenomena were independent and unconnected. The Abstract Meaning Representation (AMR) project arised out of the need to create a broad-coverage …...

This paper describes a method for browsing relations between terms and unveiling the terminological structure of a specialized domain. The method consists in expanding a graph that takes as input the relations encoded in a multilingual terminological resource called the DiCoEnviro that contains terms in the field of the environment. …...

We introduce work on the detection of definitory contexts designed to speed up two lexicographical tasks: searching for the exact meaning(s) of terms and providing usable input for paraphrasing. Our database is built from a specialized web corpus using a robust pattern-based extraction method. The corresponding interface displays information for …...

Implicit Semantic Role Labeling is a challenging task: it requires high-level understanding of the text while annotated data is very limited. Due to the lack of training data, most researches either resort to simplistic machine learning methods or focus on automatically acquiring training data. In this paper, we explore the …...

Museums and other cultural heritage institutions have large databases of information about the objects in their collections, and existing Natural Language Generation (NLG) systems can generate fluent and adaptive texts for visitors, given appropriate input data, but there is typically a large amount of expert human effort required to bridge …...

We explore a novel research idea, that we call Musical Language Processing (MLP), which investigates the possibility of a musical input to speech interaction systems. We present the first attempts at finding a mapping between musical pieces and dialogues, based on the frequency of musical patterns. Our findings on one …...

The generation of natural language from Resource Description Framework (RDF) data has recently gained significant attention due to the continuous growth of Linked Data. A number of these approaches generate natural language in languages other than English, however, no work has been proposed to generate Brazilian Portuguese texts out of …...

In this paper, we present a new method to obtain large volumes of high-quality text corpora with event data for studying identity and reference relations. We report on the current methods to create event reference data by annotating texts and deriving the event data a posteriori. Our method starts from …...

We present a detailed evaluation and analysis of neural sequence-to-sequence models for text simplification on two distinct datasets: Wikipedia and Newsela. We employ both human and automatic evaluation to investigate the capacity of neural models to generalize across corpora, and we highlight challenges that these models face when tested on …...

We present a generic deep realizer called GenDR, which takes as input an abstract semantic representation of predicate-argument relations, and produces corresponding syntactic dependency structures in English, French, Lithuanian and Persian, with the possibility to fairly easily add more languages. It is generic in that it is designed to operate …...

Wordnets are rich lexico-semantic resources. Linked wordnets are extensions of wordnets, which link similar concepts in wordnets of different languages. Such resources are extremely useful in many Natural Language Processing (NLP) applications, primarily those based on knowledge-based approaches. In such approaches, these resources are considered as gold standard/oracle. Thus, it …...

We present a taxonomy for classifying speech overlap in natural language dialogue. The scheme classifies overlap on the basis of several features, including onset point, local dialogue history, and management behavior. We describe the various dimensions of this scheme and show how it was applied to a corpus of remote, …...

In this paper, we propose Extended HowNet 2.0 – an entity-relation common-sense representation model. Comparing to HowNet and Extended HowNet, E-HowNet 2.0 has the following improvements: (a) Reorganizing the hierarchical structure of primitives and basic concepts; (b) Rich lexical information: In addition to sense definition, each entry of lexical sense …...

We report on the practical application of a black-box testing methodology for the validation of the knowledge encoded in WordNet, SUMO and their mapping by using automated theorem provers. Our proposal is based on the part-whole information provided by WordNet, out of which we automatically create a large set of …...

In this paper we proceed with a systematic gathering of design requirements for wordnet browsers that permit to consult the content of wordnets. This is undertaken together with a review of the functionalities of existing browsers. On the basis of this analysis, we present a new wordnet browser we developed …...

Since 2013, the thesaurus of the Bibliography of Linguistic Literature (BLL Thesaurus) has been applied in the context of the Lin ��gu ��is ��tik portal, a hub for linguistically relevant information. Several consecutive projects focus on the modeling of the BLL Thesaurus as ontology and its linking to terminological repositories …...