Adding semantic roles to the Chinese Treebank

2009 ◽  
Vol 15 (1) ◽  
pp. 143-172 ◽  
Author(s):  
NIANWEN XUE ◽  
MARTHA PALMER

AbstractWe report work on adding semantic role labels to the Chinese Treebank, a corpus already annotated with phrase structures. The work involves locating all verbs and their nominalizations in the corpus, and semi-automatically adding semantic role labels to their arguments, which are constituents in a parse tree. Although the same procedure is followed, different issues arise in the annotation of verbs and nominalized predicates. For verbs, identifying their arguments is generally straightforward given their syntactic structure in the Chinese Treebank as they tend to occupy well-defined syntactic positions. Our discussion focuses on the syntactic variations in the realization of the arguments as well as our approach to annotating dislocated and discontinuous arguments. In comparison, identifying the arguments for nominalized predicates is more challenging and we discuss criteria and procedures for distinguishing arguments from non-arguments. In particular we focus on the role of support verbs as well as the relevance of event/result distinctions in the annotation of the predicate-argument structure of nominalized predicates. We also present our approach to taking advantage of the syntactic structure in the Chinese Treebank to bootstrap the predicate-argument structure annotation of verbs. Finally, we discuss the creation of a lexical database of frame files and its role in guiding predicate-argument annotation. Procedures for ensuring annotation consistency and inter-annotator agreement evaluation results are also presented.

Author(s):  
Diane Massam

This book presents a detailed descriptive and theoretical examination of predicate-argument structure in Niuean, a Polynesian language within the Oceanic branch of the Austronesian family, spoken mainly on the Pacific island of Niue and in New Zealand. Niuean has VSO word order and an ergative case-marking system, both of which raise questions for a subject-predicate view of sentence structure. Working within a broadly Minimalist framework, this volume develops an analysis in which syntactic arguments are not merged locally to their thematic sources, but instead are merged high, above an inverted extended predicate which serves syntactically as the Niuean verb, later undergoing movement into the left periphery of the clause. The thematically lowest argument merges as an absolutive inner subject, with higher arguments merging as applicatives. The proposal relates Niuean word order and ergativity to its isolating morphology, by equating the absence of inflection with the absence of IP in Niuean, which impacts many aspects of its grammar. As well as developing a novel analysis of clause and argument structure, word order, ergative case, and theta role assignment, the volume argues for an expanded understanding of subjecthood. Throughout the volume, many other topics are also treated, such as noun incorporation, word formation, the parallel internal structure of predicates and arguments, null arguments, displacement typology, the role of determiners, and the structure of the left periphery.


2021 ◽  
pp. 1-48
Author(s):  
Zuchao Li ◽  
Hai Zhao ◽  
Shexia He ◽  
Jiaxun Cai

Abstract Semantic role labeling (SRL) is dedicated to recognizing the semantic predicate-argument structure of a sentence. Previous studies in terms of traditional models have shown syntactic information can make remarkable contributions to SRL performance; however, the necessity of syntactic information was challenged by a few recent neural SRL studies that demonstrate impressive performance without syntactic backbones and suggest that syntax information becomes much less important for neural semantic role labeling, especially when paired with recent deep neural network and large-scale pre-trained language models. Despite this notion, the neural SRL field still lacks a systematic and full investigation on the relevance of syntactic information in SRL, for both dependency and both monolingual and multilingual settings. This paper intends to quantify the importance of syntactic information for neural SRL in the deep learning framework. We introduce three typical SRL frameworks (baselines), sequence-based, tree-based, and graph-based, which are accompanied by two categories of exploiting syntactic information: syntax pruningbased and syntax feature-based. Experiments are conducted on the CoNLL-2005, 2009, and 2012 benchmarks for all languages available, and results show that neural SRL models can still benefit from syntactic information under certain conditions. Furthermore, we show the quantitative significance of syntax to neural SRL models together with a thorough empirical survey using existing models.


2019 ◽  
Vol 5 (2) ◽  
pp. 122-129
Author(s):  
A.A.A Ngr. Adriyanti Weda Ningrat ◽  
I Nyoman Kardana ◽  
Mirsa Umiyati

This study reveals the semantic fields from the "to see" verb in Javanese. The aims of this research is to describe the shape, function, meaning and role of semantic of each variant of the verb "to see". To realize this goal, qualitative research design was applied in this study and the semantic role theory of Vole and Van Valin (1984). Was also oriented in data analysis. Verbs that have semantic fields that are associated with the "to see" verb with intentional entities numbering 33. Each of them is ndêlok, ndêlêng, ningali, mirsani, ndeleng sacleraman, ndêlêng tênanên, ningali saestu, mirsani saestu, ningali sekedhap, mirsani sekedhap, mlengos, ngwasi, ngêmatake, ngematakên, ndhangak, dingkluk, nginceng, ngêlirêk, mêntêlêngi, ndelok mburi, and maca. The semantic roles of the arguments of each verb consist of agents and themes. This study only sheds light on the meaning field verb "to see" of the type of variant and a little about the general semantic role. For this reason, a more detailed study of the specific role of each variant of the verb is a topic that can be raised in the next study.


Linguistics ◽  
2019 ◽  
Vol 57 (4) ◽  
pp. 769-814
Author(s):  
Berit Gehrke ◽  
Louise McNally

AbstractThe syntactic literature on idioms contains some proposals that are surprising from a compositional perspective. For example, there are proposals that, in the case of verb-object idioms, the verb combines directly with the noun inside its DP complement, and the determiner is introduced higher up in the syntactic structure, or is late-adjoined. This seems to violate compositionality insofar as it is generally assumed that the semantic role of the determiner is to convert a noun to the appropriate semantic type to serve as the argument to the function denoted by the verb. In this paper, we establish a connection between this line of analysis and lines of work in semantics that have developed outside of the domain of idioms, particularly work on incorporation and work that combines formal and distributional semantic modelling. This semantic work separates the composition of descriptive content from that of discourse referent introducing material; our proposal shows that this separation offers a particularly promising way to handle the compositional difficulties posed by idioms, including certain patterns of variation in intervening determiners and modifiers.


2021 ◽  
Vol 16 ◽  
pp. 358-380
Author(s):  
Birutė Spraunienė ◽  
Vaiva Žeimantienė

This paper surveys Lithuanian impersonal constructions with predicative present passive participles containing non-promoted accusative objects. It is shown that the construction, hitherto considered very rare, is well-attested and productive with one verb class, namely, transitive reflexives. In terms of semantics, transitive reflexives in Lithuanian may be classified as autobenefactives. Autobenefactive reflexives do not exhibit a change in argument structure with respect to their non-reflexive counterparts. In the case of autobenefactives, the morpheme -si- attached to the verb adds the meaning that the subject, which mostly has the semantic role of an agent, benefits from the event expressed by the predicate. On the basis of corpus data, we have analysed how widespread impersonal constructions with accusative objects are within the domain of transitive reflexives and which pattern—the accusative or the nominative—is dominant when both are attested. Lastly, we briefly discuss the temporal-aspectual meaning of reflexive-based impersonals as well as the referential properties of implied agents


2008 ◽  
Vol 34 (2) ◽  
pp. 225-255 ◽  
Author(s):  
Nianwen Xue

In this article we report work on Chinese semantic role labeling, taking advantage of two recently completed corpora, the Chinese PropBank, a semantically annotated corpus of Chinese verbs, and the Chinese Nombank, a companion corpus that annotates the predicate-argument structure of nominalized predicates. Because the semantic role labels are assigned to the constituents in a parse tree, we first report experiments in which semantic role labels are automatically assigned to hand-crafted parses in the Chinese Treebank. This gives us a measure of the extent to which semantic role labels can be bootstrapped from the syntactic annotation provided in the treebank. We then report experiments using automatic parses with decreasing levels of human annotation in the input to the syntactic parser: parses that use gold-standard segmentation and POS-tagging, parses that use only gold-standard segmentation, and fully automatic parses. These experiments gauge how successful semantic role labeling for Chinese can be in more realistic situations. Our results show that when hand-crafted parses are used, semantic role labeling accuracy for Chinese is comparable to what has been reported for the state-of-the-art English semantic role labeling systems trained and tested on the English PropBank, even though the Chinese PropBank is significantly smaller in size. When an automatic parser is used, however, the accuracy of our system is significantly lower than the English state of the art. This indicates that an improvement in Chinese parsing is critical to high-performance semantic role labeling for Chinese.


2009 ◽  
Vol 32 (1) ◽  
pp. 99-123 ◽  
Author(s):  
Fayssal Tayalati ◽  
Marleen Van Peteghem

The aim of this paper is to propose a unified account of dative assignment for both verbs and adjectives in French. We will show that both types of predicates assign dative case to their second internal argument, provided that this argument is situated in a higher position in the thematic hierarchy than the first internal argument. This hypothesis, which considers the dative in French as a structural rather than a semantic case, can easily account for all three-argument verbs, for most two-argument verbs and even for adjunct datives. As for the adjectival predicates, we will show that only ergative adjectives, whose first argument is an internal argument, can assign dative to their second internal argument. The few exceptions to this hypothesis can be explained by the fact that, although the dative is not a semantic case, it is associated with certain semantic roles, given that its semantic role is situated in the thematic hierarchy between the role of the external argument and the role of the first internal argument.


Adeptus ◽  
2019 ◽  
Author(s):  
Justyna Maria Małek

Basic linguistic ontology and plants: A semantic sketchThis article is devoted to verbs collocating with the Polish lexeme roślina ‘plant’. The aim of the study is to determine the linguistic status of the plant and to investigate whether it is ‘someone’ or ‘something’ in view of the semantics of the verbs in question. The author analyses cases in which the plant appears in the semantic role of the agent. She makes conclusions about how the lexeme roślina functions in Polish and defines its unique features (semantic connectivity) and semantic roles. The study is based on language surveys conducted among native speakers of Polish. Language analysis reveals the place of the plant in the hierarchy of living organisms. Elementarna ontologia językowa rośliny – szkic semantycznyPrzedmiotem artykułu są polskie czasowniki, które zgodnie z łączliwością semantycznoskładniową występują z leksemem roślina. Celem tekstu jest ustalenie językowego statusu rośliny oraz, dzięki badaniu semantyki czasowników, znalezienie odpowiedzi na pytanie, czy roślina jest kimś, czy czymś. Autorka analizuje czasowniki, w których roślina występuje w semantycznej roli agensa; następnie na podstawie badań językowych formułuje wnioski dotyczące sposobu funkcjonowania leksemu roślina w języku polskim, określając jego cechy unikatowe (łączliwość semantyczną) oraz role semantyczne. Metody wykorzystane w pracy to testy językowe na materiale pozytywnym i negatywnym oparte na kompetencji językowej użytkowników polszczyzny. Analiza językowa odkrywa miejsce wyznaczone dla rośliny w hierarchii organizmów żywych.


Author(s):  
Tyler Peterson

The Tsimshianic languages are entirely morphologically ergative in the agreement system. While there is a split in Tsimshianic, conditioned by both clause type and a person hierarchy, the other side of the split is not the expected nominative-accusative alignment. Rather, other logical groupings of semantic roles are found that are still ergative. This chapter presents a description of the agreement patterns across Tsimshianic, with the aim of explaining these expansions of ergativity, by undertaking a comparative analysis of the individual languages in the Tsimshianic family. This is analysis is extended to the connectives, which are complex, determiner-like morphemes that appear to be sensitive to the semantic role of the NP. This leads to four distinct alignments (nominative, ergative, neutral, and contrastive). An understanding of the alignments in the agreement system can shed light on this complexity, and a comparative analysis eliminates the multiple alignments in the connective system, thus revealing a fairly standard set of determiners.


2018 ◽  
Vol 92 (5) ◽  
Author(s):  
Ignazio Mauro Mirto

This paper will address the predicative nature of manner adverb(ial)s and of three types of sentence adverbs (subject-oriented, modal, and evaluative) in Italian. Predication often becomes overt by means of morphological correlates. Is it possible to find any such evidence with invariable adverbs? To unveil their predicative nature, a procedure will be suggested in which two sentences, one with a -mente adverb, the other with its cognate adjective (a) share the content morphemes (identity of the signifiant) and (b) entail each other (identity of the signifié as regards semantic roles). A number of such pairs will be discussed, examples of which include: Intelligentemente, Leo intervenne ‘Cleverly, Leo intervened’ and Leo fu intelligente a intervenire ‘Leo was clever to intervene’. We aim to ascertain if the argument structure of the adjective and the semantic role(s) which it assigns can shed light on the very same properties of the cognate adverb.


Sign in / Sign up

Export Citation Format

Share Document