Abstract | Semantic Role Labeling (SRL) has become one of the standard tasks of natural language processing and proven useful as a source of information for a number of other applications. |
Background and Motivation | Semantic role labeling has proven useful in many natural language processing tasks, such as question answering (Shen and Lapata, 2007; Kaisser and Webber, 2007), textual entailment (Sammons et al., 2009), machine translation (Wu and Fung, 2009; Liu and Gildea, 2010; Gao and Vogel, 2011) and dialogue systems (Basili et al., 2009; van der Plas et al., 2009). |
Background and Motivation | Multiple models have been designed to automatically predict semantic roles , and a considerable amount of data has been annotated to train these models, if only for a few more popular languages. |
Background and Motivation | A number of approaches to the construction of semantic role labeling models for new languages |
Setup | The purpose of the study is not to develop a yet another semantic role labeling system — any existing SRL system can (after some modification) be used in this setup — but to assess the practical applicability of cross-lingual model transfer to this problem, compare it against the alternatives and identify its strong/weak points depending on a particular setup. |
Setup | 2.1 Semantic Role Labeling Model |
Setup | We consider the dependency-based version of semantic role labeling as described in Hajic et al. |
Abstract | This paper presents a novel deterministic algorithm for implicit Semantic Role Labeling. |
Conclusions and Future Work | In this work we have presented a robust deterministic approach for implicit Semantic Role Labeling. |
Conclusions and Future Work | We have shown the importance of this phenomenon for recovering the implicit information about semantic roles . |
Conclusions and Future Work | As input it only needs the document with explicit semantic role labeling and Super-Sense annotations. |
Introduction | Traditionally, Semantic Role Labeling (SRL) systems have focused in searching the fillers of those explicit roles appearing within sentence boundaries (Gildea and Jurafsky, 2000, 2002; Carreras and Marquez, 2005; Surdeanu et al., 2008; Hajic et al., 2009). |
Introduction | for Implicit Semantic Role Labelling |
Related Work | The first attempt for the automatic annotation of implicit semantic roles was proposed by Palmer et al. |
Related Work | SEMAFOR (Chen et al., 2010) is a supervised system that extended an existing semantic role labeler to enlarge the search window to other sentences, replacing the features defined for regular arguments with two new semantic features. |
Abstract | In our experiments, using the NLP tasks of semantic role labeling and entity-relation extraction, we demonstrate that with the margin-based algorithm, we need to call the inference engine only for a third of the test examples. |
Conclusion | We show via experiments that these methods individually give a reduction in the number of calls made to an inference engine for semantic role labeling and entity-relation extraction. |
Experiments and Results | We report the performance of inference on two NLP tasks: semantic role labeling and the task of extracting entities and relations from text. |
Experiments and Results | Semantic Role Labeling (SRL) Our first task is that of identifying arguments of verbs in a sentence and annotating them with semantic roles (Gildea and Jurafsky, 2002; Palmer et al., 2010) . |
Experiments and Results | For the semantic role labeling task, we need to call the solver only for one in six examples while for the entity-relations task, only one in four examples require a solver call. |
Introduction | We evaluate the two schemes and their combination on two NLP tasks where the output is encoded as a structure: PropBank semantic role labeling (Punyakanok et al., 2008) and the problem of recognizing entities and relations in text (Roth and Yih, 2007; Kate and Mooney, 2010). |
Related Work | (2012) for semantic role labeling and Kwiatkowski et al. |
Related Work | Semantic role labeling (SRL) schemes bear similarity to the foundational layer, due to their focus on argument structure. |
Related Work | PropBank and NomBank are built on top of the PTB annotation, and provide for each verb (PropBank) and noun (NomBank), a delineation of their arguments and their categorization into semantic roles . |
Experimental Setup | Documents are processed by a full NLP pipeline, including token and sentence segmentation, parsing, semantic role labeling, and an information extraction pipeline consisting of mention detection, NP coreference, cross-document resolution, and relation detection (Florian et al., 2004; Luo et al., 2004; Luo and Zitouni, 2005). |
The Framework | semantic role overlap |
The Framework | We also derive the semantic role overlap and relation instance overlap between the query and each sentence. |
The Framework | Cross-document coreference resolution, semantic role labeling and relation extraction are accomplished Via the methods described in Section 5. |
Introduction | Caseframes are shallow approximations of semantic roles which are well suited to characterizing a domain by its slots. |
Theoretical basis of our analysis | A caseframe is a shallow approximation of the semantic role structure of a proposition-bearing unit like a verb, and are |
Theoretical basis of our analysis | In particular, they are (gov, role) pairs, where gov is a proposition-bearing element, and role is an approximation of a semantic role with gov as its head (See Figure 1 for examples). |
Theoretical basis of our analysis | Caseframes do not consider the dependents of the semantic role approximations. |
Example | This observation argues for enforcing agreement of entity-level semantic properties during inference, specifically properties relating to permitted semantic roles . |
Experiments | We consider clusterings that take as input pairs (n, 7“) of a noun head n and a string 7“ which contains the semantic role of n (or some approximation thereof) conjoined with its governor. |
Models | Throughout this section, let cc be a variable containing the words in a document along with any relevant precomputed annotation (such as parse information, semantic roles , etc. |
Comparative Study | (Feng et al., 2012) propose two structure features from semantic role labeling (SRL) results. |
Comparative Study | During decoding process, the first feature will report how many event layers that one search state violates and the second feature will report the amount of semantic roles that one search state violates. |
Introduction | (Feng et al., 2012) present a method that utilizes predicate-argument structures from semantic role labeling results as soft constraints. |
Evaluation framework | This is based on work that uses paths between head nouns and verbs (Shen et al., 2005), semantic roles (Moschitti, 2008), and all dependency paths except those that occur between words in the same base chunk (e.g. |
Selection method for catenae | We use a pseudo-projective joint dependency parse and semantic role labelling system (J ohansson and |
Selection method for catenae | Dependency path features: Part-of-speech tags and semantic roles have been used to filter dependency paths. |
Introduction | The combination of our two models approaches a simplified level of semantic role definition but only relies on dependency information that is considerably easier and cheaper to define and obtain than a very high quality semantic parser and/or a corpus annotated with semantic role information. |
Introduction | Integrating semantic role information into SMT has been demonstrated by various researchers to improve translation quality (cf. |
Introduction | Wu and Fung (2009b) who demonstrated that on the one hand 84% of verb syntactic functions in a 50-sentence test corpus projected from Chinese to English, and that on the other hand about 15% of the subjects were not translated into subjects, but their semantic roles were preserved across language. |
Discussion | SemTree features capture the differences between semantic roles for the same frame, and between the same semantic role in different frames. |
Methods | FrameNet defines hundreds of frames, each of which represents a scenario associated with semantic roles , or frame elements, that serve as participants in the scenario the frame signifies. |
Related Work | Semantic role labeling using FrameNet has been used to identify an opinion with its holder and topic (Kim and Hovy, 2006). |
Related Work | Kim and Hovy (2006) identifies opinion holders and targets by using their semantic roles related to opinion words. |
Related Work | (2008) argued that semantic role labeling is not sufficient for identifying opinion holders and targets. |
Related Work | Joint inference has also been applied to semantic role labeling (Punyakanok et al., 2008; Srikumar and Roth, 2011; Das et al., 2012), where the goal is to jointly identify semantic arguments for given lexical predicates. |
Background | Besides Predictive Annotation, our work is closest to structured retrieval, which covers techniques of dependency path mapping (Lin and Pantel, 2001; Cui et al., 2005; Kaisser, 2012), graph matching with Semantic Role Labeling (Shen and Lapata, 2007) and answer type checking (Pinchak et al., 2009), etc. |
Background | (2007) proposed indexing text with their semantic roles and named entities. |
Background | Queries then include constraints of semantic roles and named entities for the predicate and its arguments in the question. |